Ändra sökning
Avgränsa sökresultatet
1234 1 - 50 av 183
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Alexanderson, Simon
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Tal, musik och hörsel, TMH.
    Henter, Gustav Eje
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Tal, musik och hörsel, TMH.
    Kucherenko, Taras
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Beskow, Jonas
    KTH, Tidigare Institutioner (före 2005), Tal, musik och hörsel.
    Style-Controllable Speech-Driven Gesture SynthesisUsing Normalising Flows2020Konferensbidrag (Refereegranskat)
    Abstract [en]

    Automatic synthesis of realistic gestures promises to transform the fields of animation, avatars and communicative agents. In off-line applications, novel tools can alter the role of an animator to that of a director, who provides only high-level input for the desired animation; a learned network then translates these instructions into an appropriate sequence of body poses. In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters. In this paper we address some of the core issues towards these ends. By adapting a deep learning-based motion synthesis method called MoGlow, we propose a new generative model for generating state-of-the-art realistic speech-driven gesticulation. Owing to the probabilistic nature of the approach, our model can produce a battery of different, yet plausible, gestures given the same input speech signal. Just like humans, this gives a rich natural variation of motion. We additionally demonstrate the ability to exert directorial control over the output style, such as gesture level, speed, symmetry and spacial extent. Such control can be leveraged to convey a desired character personality or mood. We achieve all this without any manual annotation of the data. User studies evaluating upper-body gesticulation confirm that the generated motions are natural and well match the input speech. Our method scores above all prior systems and baselines on these measures, and comes close to the ratings of the original recorded motions. We furthermore find that we can accurately control gesticulation styles without unnecessarily compromising perceived naturalness. Finally, we also demonstrate an application of the same method to full-body gesticulation, including the synthesis of stepping motion and stance.

  • 2.
    Almeida, Diogo
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Dual-Arm Robotic Manipulation under Uncertainties and Task-Based Redundancy2019Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    Robotic manipulators are mostly employed in industrial environments, where their tasks can be prescribed with little to no uncertainty. This is possible in scenarios where the deployment time of robot workcells is not prohibitive, such as in the automotive industry. In other contexts, however, the time cost of setting up a classical robotic automation workcell is often prohibitive. This is the case with cellphone manufacturing, for example, which is currently mostly executed by human workers. Robotic automation is nevertheless desirable in these human-centric environments, as a robot can automate the most tedious parts of an assembly. To deploy robots in these environments, however, requires an ability to deal with uncertainties and to robustly execute any given task. In this thesis, we discuss two topics related to autonomous robotic manipulation. First, we address parametric uncertainties in manipulation tasks, such as the location of contacts during the execution of an assembly. We propose and experimentally evaluate two methods that rely on force and torque measurements to produce estimates of task related uncertainties: a method for dexterous manipulation under uncertainties which relies on a compliant rotational degree of freedom at the robot's gripper grasp point and exploits contact  with an external surface, and a cooperative manipulation system which is able to identify the kinematics of a two degrees of freedom mechanism. Then, we consider redundancies in dual-arm robotic manipulation. Dual-armed robots offer a large degree of redundancy which can be exploited to ensure a more robust task execution. When executing an assembly task, for instance, robots can freely change the location of the assembly in their workspace without affecting the task execution. We discuss methods that explore these types of redundancies in relative motion tasks in the form of asymmetries in their execution. Finally, we approach the converse problem by presenting a system which is able to balance measured forces and torques at its end-effectors by leveraging relative motion between them, while grasping a rigid tray. This is achieved through discrete sliding of the grasp points, which constitutes a novel application of bimanual dexterous manipulation.

    Ladda ner fulltext (pdf)
    fulltext
  • 3.
    Almeida, Diogo
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL. KTH.
    Ambrus, Rares
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Caccamo, Sergio
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Chen, Xi
    KTH.
    Cruciani, Silvia
    Pinto Basto De Carvalho, Joao F
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Haustein, Joshua
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Marzinotto, Alejandro
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Vina, Francisco
    KTH.
    Karayiannidis, Yannis
    KTH.
    Ögren, Petter
    KTH, Skolan för teknikvetenskap (SCI), Matematik (Inst.), Optimeringslära och systemteori.
    Jensfelt, Patric
    KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL.
    Team KTH’s Picking Solution for the Amazon Picking Challenge 20162017Ingår i: Warehouse Picking Automation Workshop 2017: Solutions, Experience, Learnings and Outlook of the Amazon Robotics Challenge, 2017Konferensbidrag (Övrig (populärvetenskap, debatt, mm))
    Abstract [en]

    In this work we summarize the solution developed by Team KTH for the Amazon Picking Challenge 2016 in Leipzig, Germany. The competition simulated a warehouse automation scenario and it was divided in two tasks: a picking task where a robot picks items from a shelf and places them in a tote and a stowing task which is the inverse task where the robot picks items from a tote and places them in a shelf. We describe our approach to the problem starting from a high level overview of our system and later delving into details of our perception pipeline and our strategy for manipulation and grasping. The solution was implemented using a Baxter robot equipped with additional sensors.

  • 4.
    Almeida, Diogo
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Ataer-Cansizoglu, Esra
    Wayfair, Boston, MA 02116, USA.
    Corcodel, Radu
    Mitsubishi Electric Research Labs (MERL), Cambridge, MA 02139, USA.
    Detection, Tracking and 3D Modeling of Objects with Sparse RGB-D SLAM and Interactive Perception2019Ingår i: IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    We present an interactive perception system that enables an autonomous agent to deliberately interact with its environment and produce 3D object models. Our system verifies object hypotheses through interaction and simultaneously maintains 3D SLAM maps for each rigidly moving object hypothesis in the scene. We rely on depth-based segmentation and a multigroup registration scheme to classify features into various object maps. Our main contribution lies in the employment of a novel segment classification scheme that allows the system to handle incorrect object hypotheses, common in cluttered environments due to touching objects or occlusion. We start with a single map and initiate further object maps based on the outcome of depth segment classification. For each existing map, we select a segment to interact with and execute a manipulation primitive with the goal of disturbing it. If the resulting set of depth segments has at least one segment that did not follow the dominant motion pattern of its respective map, we split the map, thus yielding updated object hypotheses. We show qualitative results with a Fetch manipulator and objects of various shapes, which showcase the viability of the method for identifying and modelling multiple objects through repeated interactions.

    Ladda ner fulltext (pdf)
    fulltext
  • 5.
    Almeida, Diogo
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Karayiannidis, Yiannis
    A Lyapunov-Based Approach to Exploit Asymmetries in Robotic Dual-Arm Task Resolution2019Ingår i: 58th IEEE Conference on Decision and Control (CDC), 2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    Dual-arm manipulation tasks can be prescribed to a robotic system in terms of desired absolute and relative motion of the robot’s end-effectors. These can represent, e.g., jointly carrying a rigid object or performing an assembly task. When both types of motion are to be executed concurrently, the symmetric distribution of the relative motion between arms prevents task conflicts. Conversely, an asymmetric solution to the relative motion task will result in conflicts with the absolute task. In this work, we address the problem of designing a control law for the absolute motion task together with updating the distribution of the relative task among arms. Through a set of numerical results, we contrast our approach with the classical symmetric distribution of the relative motion task to illustrate the advantages of our method.

    Ladda ner fulltext (pdf)
    fulltext
  • 6.
    Almeida, Diogo
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Karayiannidis, Yiannis
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Asymmetric Dual-Arm Task Execution using an Extended Relative Jacobian2019Ingår i: The International Symposium on Robotics Research, 2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    Coordinated dual-arm manipulation tasks can be broadly characterized as possessing absolute and relative motion components. Relative motion tasks, in particular, are inherently redundant in the way they can be distributed between end-effectors. In this work, we analyse cooperative manipulation in terms of the asymmetric resolution of relative motion tasks. We discuss how existing approaches enable the asymmetric execution of a relative motion task, and show how an asymmetric relative motion space can be defined. We leverage this result to propose an extended relative Jacobian to model the cooperative system, which allows a user to set a concrete degree of asymmetry in the task execution. This is achieved without the need for prescribing an absolute motion target. Instead, the absolute motion remains available as a functional redundancy to the system. We illustrate the properties of our proposed Jacobian through numerical simulations of a novel differential Inverse Kinematics algorithm.

    Ladda ner fulltext (pdf)
    fulltext
  • 7.
    Almeida, Diogo
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Karayiannidis, Yiannis
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL. Dept. of Electrical Eng., Chalmers University of Technology.
    Cooperative Manipulation and Identification of a 2-DOF Articulated Object by a Dual-Arm Robot2018Ingår i: 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) / [ed] IEEE, 2018, s. 5445-5451Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this work, we address the dual-arm manipula-tion of a two degrees-of-freedom articulated object that consistsof two rigid links. This can include a linkage constrainedalong two motion directions, or two objects in contact, wherethe contact imposes motion constraints. We formulate theproblem as a cooperative task, which allows the employment ofcoordinated task space frameworks, thus enabling redundancyexploitation by adjusting how the task is shared by the robotarms. In addition, we propose a method that can estimate thejoint location and the direction of the degrees-of-freedom, basedon the contact forces and the motion constraints imposed bythe object. Experimental results demonstrate the performanceof the system in its ability to estimate the two degrees of freedomindependently or simultaneously.

    Ladda ner fulltext (pdf)
    fulltext
  • 8.
    Almeida, Diogo
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Karayiannidis, Yiannis
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL. Chalmers University of Technology.
    Folding Assembly by Means of Dual-Arm Robotic Manipulation2016Ingår i: 2016 IEEE International Conference on Robotics and Automation, IEEE conference proceedings, 2016, s. 3987-3993Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper, we consider folding assembly as an assembly primitive suitable for dual-arm robotic assembly, that can be integrated in a higher level assembly strategy. The system composed by two pieces in contact is modelled as an articulated object, connected by a prismatic-revolute joint. Different grasping scenarios were considered in order to model the system, and a simple controller based on feedback linearisation is proposed, using force torque measurements to compute the contact point kinematics. The folding assembly controller has been experimentally tested with two sample parts, in order to showcase folding assembly as a viable assembly primitive.

    Ladda ner fulltext (pdf)
    fulltext
  • 9.
    Antonova, Rika
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Centrum för autonoma system, CAS. KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kokic, Mia
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Centrum för autonoma system, CAS. KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Stork, Johannes A.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Centrum för autonoma system, CAS. KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Centrum för autonoma system, CAS. KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation2018Ingår i: Proceedings of The 2nd Conference on Robot Learning, PMLR 87, 2018, s. 641-650Konferensbidrag (Refereegranskat)
    Abstract [en]

    We develop an approach that benefits from large simulated datasets and takes full advantage of the limited online data that is most relevant. We propose a variant of Bayesian optimization that alternates between using informed and uninformed kernels. With this Bernoulli Alternation Kernel we ensure that discrepancies between simulation and reality do not hinder adapting robot control policies online. The proposed approach is applied to a challenging real-world problem of task-oriented grasping with novel objects. Our further contribution is a neural network architecture and training pipeline that use experience from grasping objects in simulation to learn grasp stability scores. We learn task scores from a labeled dataset with a convolutional network, which is used to construct an informed kernel for our variant of Bayesian optimization. Experiments on an ABB Yumi robot with real sensor data demonstrate success of our approach, despite the challenge of fulfilling task requirements and high uncertainty over physical properties of objects.

    Ladda ner fulltext (pdf)
    fulltext
  • 10.
    Arnekvist, Isac
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Stork, Johannes A.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL. Center for Applied Autonomous Sensor Systems, Örebro University, Sweden.
    Vpe: Variational policy embedding for transfer reinforcement learning2019Ingår i: 2019 International Conference on Robotics And Automation (ICRA), Institute of Electrical and Electronics Engineers (IEEE), 2019, s. 36-42Konferensbidrag (Refereegranskat)
    Abstract [en]

    Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training allows for feasible training times, but on the other hand suffer from a reality-gap when applied in real-world settings. This raises the need of efficient adaptation of policies acting in new environments. We consider the problem of transferring knowledge within a family of similar Markov decision processes. We assume that Q-functions are generated by some low-dimensional latent variable. Given such a Q-function, we can find a master policy that can adapt given different values of this latent variable. Our method learns both the generative mapping and an approximate posterior of the latent variables, enabling identification of policies for new tasks by searching only in the latent space, rather than the space of all policies. The low-dimensional space, and master policy found by our method enables policies to quickly adapt to new environments. We demonstrate the method on both a pendulum swing-up task in simulation, and for simulation-to-real transfer on a pushing task.

    Ladda ner fulltext (pdf)
    fulltext
  • 11.
    Baldassarre, Federico
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Explainability Techniques for Graph Convolutional Networks2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them. In this work, we study the explainability of Graph Network decisions using two main classes of techniques, gradient-based and decomposition-based, on a toy dataset and a chemistry task. Our study sets the ground for future development as well as application to real-world problems.

    Ladda ner fulltext (pdf)
    fulltext
  • 12.
    Barbosa, Fernando S.
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Duberg, Daniel
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Jensfelt, Patric
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Tumova, Jana
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Guiding Autonomous Exploration with Signal Temporal Logic2019Ingår i: IEEE Robotics and Automation Letters, ISSN 2377-3766, E-ISSN 1949-3045, Vol. 4, nr 4, s. 3332-3339Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Algorithms for autonomous robotic exploration usually focus on optimizing time and coverage, often in a greedy fashion. However, obstacle inflation is conservative and might limit mapping capabilities and even prevent the robot from moving through narrow, important places. This letter proposes a method to influence the manner the robot moves in the environment by taking into consideration a user-defined spatial preference formulated in a fragment of signal temporal logic (STL). We propose to guide the motion planning toward minimizing the violation of such preference through a cost function that integrates the quantitative semantics, i.e., robustness of STL. To demonstrate the effectiveness of the proposed approach, we integrate it into the autonomous exploration planner (AEP). Results from simulations and real-world experiments are presented, highlighting the benefits of our approach.

  • 13.
    Barbosa, Fernando S.
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Lindemann, Lars
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Reglerteknik.
    Dimarogonas, Dimos V.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Reglerteknik.
    Tumova, Jana
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Integrated motion planning and control under metric interval temporal logic specifications2019Ingår i: 2019 18th European Control Conference, ECC 2019, Institute of Electrical and Electronics Engineers (IEEE), 2019, s. 2042-2049, artikel-id 8795925Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper proposes an approach that combines motion planning and hybrid feedback control design in order to find and follow trajectories fulfilling a given complex mission involving time constraints. We use Metric Interval Temporal Logic (MITL) as a rich and rigorous formalism to specify such missions. The solution builds on three main steps: (i) using sampling-based motion planning methods and the untimed version of the mission specification in the form of Zone automaton, we find a sequence of waypoints in the workspace; (ii) based on the clock zones from the satisfying run on the Zone automaton, we compute time-stamps at which these waypoints should be reached; and (iii) to control the system to connect two waypoints in the desired time, we design a low-level feedback controller leveraging Time-varying Control Barrier Functions. Illustrative simulation results are included.

  • 14.
    Billard, Aude
    et al.
    Ecole Polytech Fed Lausanne, Learning Algorithms & Syst Lab, Lausanne, Switzerland..
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Trends and challenges in robot manipulation2019Ingår i: Science, ISSN 0036-8075, E-ISSN 1095-9203, Vol. 364, nr 6446, s. 1149-+Artikel, forskningsöversikt (Refereegranskat)
    Abstract [en]

    Dexterous manipulation is one of the primary goals in robotics. Robots with this capability could sort and package objects, chop vegetables, and fold clothes. As robots come to work side by side with humans, they must also become human-aware. Over the past decade, research has made strides toward these goals. Progress has come from advances in visual and haptic perception and in mechanics in the form of soft actuators that offer a natural compliance. Most notably, immense progress in machine learning has been leveraged to encapsulate models of uncertainty and to support improvements in adaptive and robust control. Open questions remain in terms of how to enable robots to deal with the most unpredictable agent of all, the human.

  • 15.
    Björklund, Linnea
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Knock on Wood: Does Material Choice Change the Social Perception of Robots?2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Denna uppsats undersöker huruvida det finns en skillnad i hur socialt interaktiva robotar uppfattas baserat på vilket material de är tillverkade i. Två studier gjordes för att ta reda på detta: En pilotstudie som skedde fysiskt, och huvudstudien skedde online. Deltagarna ombads att skatta tre versioner av samma robotdesign, där en var byggd i trä, en i plast och en täckt i päls. Dessa användes sedan i två studier för att bedöma deltagarnas uppfattning av robotarnas kompetens, värme och obehag, samt skillnaderna i dessa mellan de tre materialen. Statistiskt signifikanta skillnader hittades i uppfattningen av värme och obehag.

    Ladda ner fulltext (pdf)
    fulltext
  • 16.
    Blom, Fredrik
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Unsupervised Feature Extraction of Clothing Using Deep Convolutional Variational Autoencoders2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    I takt med att E-handeln fortsätter att växa och kunderna i ökad utsträckning rör sig online, genereras stora mängder värdefull data, exempelvis transaktions- och sökhistorik, och specifikt för klädeshandeln, välstrukturerade bilder av kläder. Genom att använda oövervakad maskininlärning (unsupervised machine learning) är det möjligt att utnyttja denna, nästan obegränsade mängd data. Detta arbete syftar till att utreda i vilken utsträckning generativa modeller, särskilt djupa självkodande neurala faltningsnätverk (deep convolutional variational autoencoders), kan användas för att automatiskt extrahera definierande drag från bilder av kläder. Genom att granska olika varianter av självkodaren framträder en optimal relation mellan storleken på den latenta vektorn och komplexiteten på den bilddata som nätverket tränades på. Vidare noterades att dragen kan fördeladas unikt på variablerna, i detta fall t-shirts och toppar, genom att vikta den latenta förlustfunktionen.

    Ladda ner fulltext (pdf)
    fulltext
  • 17.
    Bore, Nils
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Ekekrantz, Johan
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Jensfelt, Patric
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Folkesson, John
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Detection and Tracking of General Movable Objects in Large Three-Dimensional Maps2019Ingår i: IEEE Transactions on robotics, ISSN 1552-3098, E-ISSN 1941-0468, Vol. 35, nr 1, s. 231-247Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper studies the problem of detection and tracking of general objects with semistatic dynamics observed by a mobile robot moving in a large environment. A key problem is that due to the environment scale, the robot can only observe a subset of the objects at any given time. Since some time passes between observations of objects in different places, the objects might be moved when the robot is not there. We propose a model for this movement in which the objects typically only move locally, but with some small probability they jump longer distances through what we call global motion. For filtering, we decompose the posterior over local and global movements into two linked processes. The posterior over the global movements and measurement associations is sampled, while we track the local movement analytically using Kalman filters. This novel filter is evaluated on point cloud data gathered autonomously by a mobile robot over an extended period of time. We show that tracking jumping objects is feasible, and that the proposed probabilistic treatment outperforms previous methods when applied to real world data. The key to efficient probabilistic tracking in this scenario is focused sampling of the object posteriors.

  • 18.
    Bore, Nils
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Torroba, Ignacio
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Folkesson, John
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Sparse Gaussian Process SLAM, Storage and Filtering for AUV Multibeam Bathymetry2018Ingår i: AUV 2018 - 2018 IEEE/OES Autonomous Underwater Vehicle Workshop, Proceedings, Institute of Electrical and Electronics Engineers Inc. , 2018Konferensbidrag (Refereegranskat)
    Abstract [en]

    With dead-reckoning from velocity sensors, AUVs may construct short-term, local bathymetry maps of the sea floor using multibeam sensors. However, the position estimate from dead-reckoning will include some drift that grows with time. In this work, we focus on long-term onboard storage of these local bathymetry maps, and the alignment of maps with respect to each other. We propose using Sparse Gaussian Processes for this purpose, and show that the representation has several advantages, including an intuitive alignment optimization, data compression, and sensor noise filtering. We demonstrate these three key capabilities on two real-world datasets.

    Ladda ner fulltext (pdf)
    fulltext
  • 19.
    Broomé, Sofia
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Bech Gleerup, Karina
    Haubro Andersen, Pia
    Kjellström, Hedvig
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Dynamics are important for the recognition of equine pain in video2019Ingår i: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    A prerequisite to successfully alleviate pain in animals is to recognize it, which is a great challenge in non-verbal species. Furthermore, prey animals such as horses tend to hide their pain. In this study, we propose a deep recurrent two-stream architecture for the task of distinguishing pain from non-pain in videos of horses. Different models are evaluated on a unique dataset showing horses under controlled trials with moderate pain induction, which has been presented in earlier work. Sequential models are experimentally compared to single-frame models, showing the importance of the temporal dimension of the data, and are benchmarked against a veterinary expert classification of the data. We additionally perform baseline comparisons with generalized versions of state-of-the-art human pain recognition methods. While equine pain detection in machine learning is a novel field, our results surpass veterinary expert performance and outperform pain detection results reported for other larger non-human species. 

  • 20.
    Brucker, Manuel
    et al.
    German Aerosp Ctr DLR, Inst Robot & Mechatron, D-82234 Oberpfaffenhofen, Germany..
    Durner, Maximilian
    German Aerosp Ctr DLR, Inst Robot & Mechatron, D-82234 Oberpfaffenhofen, Germany..
    Ambrus, Rares
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL. KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Centrum för autonoma system, CAS.
    Marton, Zoltan Csaba
    German Aerosp Ctr DLR, Inst Robot & Mechatron, D-82234 Oberpfaffenhofen, Germany..
    Wendt, Axel
    Robert Bosch, Corp Res, St Joseph, MI USA.;Robert Bosch, Corp Res, Gerlingen, Germany..
    Jensfelt, Patric
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL. KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Centrum för autonoma system, CAS.
    Arras, Kai O.
    Robert Bosch, Corp Res, St Joseph, MI USA.;Robert Bosch, Corp Res, Gerlingen, Germany..
    Triebel, Rudolph
    German Aerosp Ctr DLR, Inst Robot & Mechatron, D-82234 Oberpfaffenhofen, Germany.;Tech Univ Munich, Dep Comp Sci, Munich, Germany..
    Semantic Labeling of Indoor Environments from 3D RGB Maps2018Ingår i: 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), IEEE Computer Society, 2018, s. 1871-1878Konferensbidrag (Refereegranskat)
    Abstract [en]

    We present an approach to automatically assign semantic labels to rooms reconstructed from 3D RGB maps of apartments. Evidence for the room types is generated using state-of-the-art deep-learning techniques for scene classification and object detection based on automatically generated virtual RGB views, as well as from a geometric analysis of the map's 3D structure. The evidence is merged in a conditional random field, using statistics mined from different datasets of indoor environments. We evaluate our approach qualitatively and quantitatively and compare it to related methods.

  • 21.
    Buda, Mateusz
    et al.
    Duke Univ, Dept Radiol, Sch Med, Durham, NC 27710 USA.;KTH Royal Inst Technol, Sch Elect Engn & Comp Sci, Stockholm, Sweden..
    Maki, Atsuto
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Mazurowski, Maciej A.
    Duke Univ, Dept Radiol, Sch Med, Durham, NC 27710 USA.;Duke Univ, Dept Elect & Comp Engn, Durham, NC USA..
    A systematic study of the class imbalance problem in convolutional neural networks2018Ingår i: Neural Networks, ISSN 0893-6080, E-ISSN 1879-2782, Vol. 106, s. 249-259Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that completely eliminates the imbalance, whereas the optimal undersampling ratio depends on the extent of imbalance; (iv) as opposed to some classical machine learning models, oversampling does not cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest. 

  • 22.
    Butepage, Judith
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Cruciani, Silvia
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kokic, Mia
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Welle, Michael
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    From Visual Understanding to Complex Object Manipulation2019Ingår i: Annual Review of Control, Robotics, and Autonomous Systems, Vol. 2, s. 161-179Artikel, forskningsöversikt (Refereegranskat)
    Abstract [en]

    Planning and executing object manipulation requires integrating multiple sensory and motor channels while acting under uncertainty and complying with task constraints. As the modern environment is tuned for human hands, designing robotic systems with similar manipulative capabilities is crucial. Research on robotic object manipulation is divided into smaller communities interested in, e.g., motion planning, grasp planning, sensorimotor learning, and tool use. However, few attempts have been made to combine these areas into holistic systems. In this review, we aim to unify the underlying mechanics of grasping and in-hand manipulation by focusing on the temporal aspects of manipulation, including visual perception, grasp planning and execution, and goal-directed manipulation. Inspired by human manipulation, we envision that an emphasis on the temporal integration of these processes opens the way for human-like object use by robots.

  • 23.
    Butepage, Judith
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kjellström, Hedvig
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Anticipating many futures: Online human motion prediction and generation for human-robot interaction2018Ingår i: 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), IEEE COMPUTER SOC , 2018, s. 4563-4570Konferensbidrag (Refereegranskat)
    Abstract [en]

    Fluent and safe interactions of humans and robots require both partners to anticipate the others' actions. The bottleneck of most methods is the lack of an accurate model of natural human motion. In this work, we present a conditional variational autoencoder that is trained to predict a window of future human motion given a window of past frames. Using skeletal data obtained from RGB depth images, we show how this unsupervised approach can be used for online motion prediction for up to 1660 ms. Additionally, we demonstrate online target prediction within the first 300-500 ms after motion onset without the use of target specific training data. The advantage of our probabilistic approach is the possibility to draw samples of possible future motion patterns. Finally, we investigate how movements and kinematic cues are represented on the learned low dimensional manifold.

  • 24.
    Båberg, Fredrik
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.
    Petter, Ögren
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL. KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Centrum för autonoma system, CAS.
    Formation Obstacle Avoidance using RRT and Constraint Based Programming2017Ingår i: 2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR), IEEE conference proceedings, 2017, artikel-id 8088131Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper, we propose a new way of doing formation obstacle avoidance using a combination of Constraint Based Programming (CBP) and Rapidly Exploring Random Trees (RRTs). RRT is used to select waypoint nodes, and CBP is used to move the formation between those nodes, reactively rotating and translating the formation to pass the obstacles on the way. Thus, the CBP includes constraints for both formation keeping and obstacle avoidance, while striving to move the formation towards the next waypoint. The proposed approach is compared to a pure RRT approach where the motion between the RRT waypoints is done following linear interpolation trajectories, which are less computationally expensive than the CBP ones. The results of a number of challenging simulations show that the proposed approach is more efficient for scenarios with high obstacle densities.

  • 25.
    Bütepage, Judith
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Generative models for action generation and action understanding2019Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [sv]

    Frågan om hur man bygger intelligenta maskiner väcker frågan om hur man kanrepresentera världen för att möjliggöra intelligent beteende. I naturen bygger en sådanrepresentation på samspelet mellan en organisms sensoriska intryck och handlingar.Kopplingar mellan sinnesintryck och handlingar gör att många komplexa beteendenkan uppstå naturligt. I detta arbete tar vi dessa sensorimotoriska kopplingar som eninspiration för att bygga robotarsystem som autonomt kan interagera med sin miljöoch med människor. Målet är att bana väg för robotarsystem som självständiga kan lärasig att kontrollera sina rörelser och relatera sina egen sensorimotoriska upplevelser tillobserverade mänskliga handlingar. Genom att relatera robotens rörelser och förståelsenav mänskliga handlingar, hoppas vi kunna underlätta smidig och intuitiv interaktionmellan robotar och människor.För att modellera robotens sensimotoriska kopplingar och mänskligt beteende an-vänder vi generativa modeller. Eftersom generativa modeller representerar en multiva-riat fördelning över relevanta variabler, är de tillräckligt flexibla för att uppfylla demkrav som vi ställer här. Generativa modeller kan representera variabler från olika mo-daliteter, modellera temporala dynamiska system, modellera latenta variabler och re-presentera variablers varians - alla dessa egenskaper är nödvändiga för att modellerasensorimotoriska kopplingar. Genom att använda generativa modeller kan vi förutseutvecklingen av variablerna i framtiden, vilket är viktigt för att ta intelligenta beslut.Vi presenterar arbete som går i två riktningar. För det första kommer vi att fokuserapå självständig inlärande av rörelse kontroll med hjälp av sensorimotoriska kopplingar.Baserat på Gaussian Process forward modeller visar vi hur roboten kan röra på sigmot ett mål med hjälp av planeringstekniker eller förstärkningslärande. För det andrapresenterar vi ett antal tillvägagångssätt för att modellera mänsklig aktivitet, allt frånatt förutse hur människan kommer röra på sig till att inkludera semantisk information.Här använder vi djupa generativa modeller, nämligen Variational Autoencoders, föratt modellera 3D-skelettpositionen av människor över tid och, om så krävs, inkluderasemantisk information. Dessa två ideer kombineras sedan för att hjälpa roboten attinteragera med människan.Våra experiment fokuserar på realtidsscenarion, både när det gäller robot experi-ment och mänsklig aktivitet modellering. Eftersom många verkliga scenarier inte hartillgång till avancerade sensorer, kräver vi att våra modeller hanterar osäkerhet. Yt-terligare krav är maskininlärningsmodeller som inte behöver mycket data, att systemsfungerar i realtid och under säkerhetskrav. Vi visar hur generativa modeller av senso-rimotoriska kopplingar kan hantera dessa krav i våra experiment tillfredsställande.

    Ladda ner fulltext (pdf)
    fulltext
  • 26.
    Bütepage, Judith
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kjellström, Hedvig
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity ModelingManuskript (preprint) (Övrigt vetenskapligt)
    Abstract [en]

    Human behavior is a continuous stochastic spatio-temporal process which is governed by semantic actions and affordances as well as latent factors. Therefore, video-based human activity modeling is concerned with a number of tasks such as inferring current and future semantic labels, predicting future continuous observations as well as imagining possible future label and feature sequences. In this paper we present a semi-supervised probabilistic deep latent variable model that can represent both discrete labels and continuous observations as well as latent dynamics over time. This allows the model to solve several tasks at once without explicit fine-tuning. We focus here on the tasks of action classification, detection, prediction and anticipation as well as motion prediction and synthesis based on 3D human activity data recorded with Kinect. We further extend the model to capture hierarchical label structure and to model the dependencies between multiple entities, such as a human and objects. Our experiments demonstrate that our principled approach to human activity modeling can be used to detect current and anticipate future semantic labels and to predict and synthesize future label and feature sequences. When comparing our model to state-of-the-art approaches, which are specifically designed for e.g. action classification, we find that our probabilistic formulation outperforms or is comparable to these task specific models.

    Ladda ner fulltext (pdf)
    fulltext
  • 27.
    Caccamo, Sergio
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Enhancing geometric maps through environmental interactions2018Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    The deployment of rescue robots in real operations is becoming increasingly commonthanks to recent advances in AI technologies and high performance hardware. Rescue robots can now operate for extended period of time, cover wider areas andprocess larger amounts of sensory information making them considerably more usefulduring real life threatening situations, including both natural or man-made disasters.

    In this thesis we present results of our research which focuses on investigating ways of enhancing visual perception for Unmanned Ground Vehicles (UGVs) through environmental interactions using different sensory systems, such as tactile sensors and wireless receivers.

    We argue that a geometric representation of the robot surroundings built upon vision data only, may not suffice in overcoming challenging scenarios, and show that robot interactions with the environment can provide a rich layer of new information that needs to be suitably represented and merged into the cognitive world model. Visual perception for mobile ground vehicles is one of the fundamental problems in rescue robotics. Phenomena such as rain, fog, darkness, dust, smoke and fire heavily influence the performance of visual sensors, and often result in highly noisy data, leading to unreliable or incomplete maps.

    We address this problem through a collection of studies and structure the thesis as follow:Firstly, we give an overview of the Search & Rescue (SAR) robotics field, and discuss scenarios, hardware and related scientific questions.Secondly, we focus on the problems of control and communication. Mobile robotsrequire stable communication with the base station to exchange valuable information. Communication loss often presents a significant mission risk and disconnected robotsare either abandoned, or autonomously try to back-trace their way to the base station. We show how non-visual environmental properties (e.g. the WiFi signal distribution) can be efficiently modeled using probabilistic active perception frameworks based on Gaussian Processes, and merged into geometric maps so to facilitate the SAR mission. We then show how to use tactile perception to enhance mapping. Implicit environmental properties such as the terrain deformability, are analyzed through strategic glancesand touches and then mapped into probabilistic models.Lastly, we address the problem of reconstructing objects in the environment. Wepresent a technique for simultaneous 3D reconstruction of static regions and rigidly moving objects in a scene that enables on-the-fly model generation. Although this thesis focuses mostly on rescue UGVs, the concepts presented canbe applied to other mobile platforms that operates under similar circumstances. To make sure that the suggested methods work, we have put efforts into design of user interfaces and the evaluation of those in user studies.

    Ladda ner fulltext (pdf)
    KTH_Thesis_SergioCaccamo_RPL_RoboticsComputerVision
  • 28.
    Caccamo, Sergio Salvatore
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Joint 3D Reconstruction of a Static Scene and Moving Objects2017Ingår i: Proceedings of the 2017International Conference on 3D Vision (3DV’17), IEEE, 2017Konferensbidrag (Övrigt vetenskapligt)
  • 29.
    Carlsson, Stefan
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC), Beräkningsvetenskap och beräkningsteknik (CST).
    Razavian, Ali Sharif
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Sullivan, Josephine
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Smith, Kevin
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Beräkningsvetenskap och beräkningsteknik (CST).
    The Preimage of Rectifier Network Activities2017Ingår i: International Conference on Learning Representations (ICLR), 2017Konferensbidrag (Refereegranskat)
    Abstract [en]

    The preimage of the activity at a certain level of a deep network is the set of inputs that result in the same node activity. For fully connected multi layer rectifier networks we demonstrate how to compute the preimages of activities at arbitrary levels from knowledge of the parameters in a deep rectifying network. If the preimage set of a certain activity in the network contains elements from more than one class it means that these classes are irreversibly mixed. This implies that preimage sets which are piecewise linear manifolds are building blocks for describing the input manifolds specific classes, ie all preimages should ideally be from the same class. We believe that the knowledge of how to compute preimages will be valuable in understanding the efficiency displayed by deep learning networks and could potentially be used in designing more efficient training algorithms.

    Ladda ner fulltext (pdf)
    fulltext
  • 30.
    Carvalho, J. Frederico
    et al.
    KTH. KTH, CAS, RPL, Royal Inst Technol, Stocholm, Sweden..
    Vejdemo-Johansson, Mikael
    CUNY Coll Staten Isl, Math Dept, Staten Isl, NY 10314 USA.;CUNY, Grad Ctr, Comp Sci, New York, NY USA..
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL. KTH, CAS, RPL, Royal Inst Technol, Stocholm, Sweden..
    Pokorny, Florian T.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL. KTH, CAS, RPL, Royal Inst Technol, Stocholm, Sweden..
    Path Clustering with Homology Area2018Ingår i: 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), IEEE Computer Society, 2018, s. 7346-7353Konferensbidrag (Refereegranskat)
    Abstract [en]

    Path clustering has found many applications in recent years. Common approaches to this problem use aggregates of the distances between points to provide a measure of dissimilarity between paths which do not satisfy the triangle inequality. Furthermore, they do not take into account the topology of the space where the paths are embedded. To tackle this, we extend previous work in path clustering with relative homology, by employing minimum homology area as a measure of distance between homologous paths in a triangulated mesh. Further, we show that the resulting distance satisfies the triangle inequality, and how we can exploit the properties of homology to reduce the amount of pairwise distance calculations necessary to cluster a set of paths. We further compare the output of our algorithm with that of DTW on a toy dataset of paths, as well as on a dataset of real-world paths.

  • 31.
    Carvalho, Joao Frederico
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Vejdemo-Johansson, Mikael
    CUNY, Math Dept, Coll Staten Isl, New York, NY 10021 USA..
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Pokorny, Florian T.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    An algorithm for calculating top-dimensional bounding chains2018Ingår i: PEERJ COMPUTER SCIENCE, ISSN 2376-5992, artikel-id e153Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We describe the Coefficient-Flow algorithm for calculating the bounding chain of an (n-1)-boundary on an n-manifold-like simplicial complex S. We prove its correctness and show that it has a computational time complexity of O(vertical bar S(n-1)vertical bar) (where S(n-1) is the set of (n-1)-faces of S). We estimate the big-O coefficient which depends on the dimension of S and the implementation. We present an implementation, experimentally evaluate the complexity of our algorithm, and compare its performance with that of solving the underlying linear system.

    Ladda ner fulltext (pdf)
    fulltext
  • 32.
    Chen, Xi
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Ghadirzadeh, Ali
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Folkesson, John
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Björkman, Mårten
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Jensfelt, Patric
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments2018Ingår i: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018Konferensbidrag (Refereegranskat)
    Abstract [en]

    Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multifaceted navigation skill by learning and exploiting a number of manageable navigation behaviors. We also introduce a domain randomization technique to improve the versatility of the training samples. We demonstrate experimentally a significant improvement in terms of data-efficiency, success rate, robustness against irrelevant sensory data, and also the quality of the maneuver skills.

  • 33.
    Colledanchise, Michele
    et al.
    Istituto Italiano di Tecnologia - IIT, Genoa, Italy.
    Almeida, Diogo
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Ögren, Petter
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Towards Blended Reactive Planning and Acting using Behavior Trees2019Ingår i: 2019 International Conference on Robotics And Automation (ICRA), IEEE Robotics and Automation Society, 2019, s. 8839-8845Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper, we show how a planning algorithm can be used to automatically create and update a Behavior Tree (BT), controlling a robot in a dynamic environment. The planning part of the algorithm is based on the idea of back chaining. Starting from a goal condition we iteratively select actions to achieve that goal, and if those actions have unmet preconditions, they are extended with actions to achieve them in the same way. The fact that BTs are inherently modular and reactive makes the proposed solution blend acting and planning in a way that enables the robot to effectively react to external disturbances. If an external agent undoes an action the robot re- executes it without re-planning, and if an external agent helps the robot, it skips the corresponding actions, again without re- planning. We illustrate our approach in two different robotics scenarios.

    Ladda ner fulltext (pdf)
    fulltext
  • 34. Colledancise, Michele
    et al.
    Parasuraman, Ramviyas Nattanmai
    Petter, Ögren
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Learning of Behavior Trees for Autonomous Agents2018Ingår i: IEEE Transactions on Games, ISSN 2475-1502Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In this paper, we study the problem of automatically synthesizing a successful Behavior Tree (BT) in an a-priori unknown dynamic environment. Starting with a given set of behaviors, a reward function, and sensing in terms of a set of binary conditions, the proposed algorithm incrementally learns a switching structure in terms of a BT, that is able to handle the situations encountered. Exploiting the fact that BTs generalize And-Or-Trees and also provide very natural chromosome mappings for genetic pro- gramming, we combine the long term performance of Genetic Programming with a greedy element and use the And-Or analogy to limit the size of the resulting structure. Finally, earlier results on BTs enable us to provide certain safety guarantees for the resulting system. Using the testing environment Mario AI we compare our approach to alternative methods for learning BTs and Finite State Machines. The evaluation shows that the proposed approach generated solutions with better performance, and often fewer nodes than the other two methods.

  • 35.
    Correia, Filipa
    et al.
    Univ Lisbon, INESC ID, Inst Super Tecn, Lisbon, Portugal..
    Mascarenhas, Samuel F.
    Univ Lisbon, INESC ID, Inst Super Tecn, Lisbon, Portugal..
    Gomes, Samuel
    Univ Lisbon, INESC ID, Inst Super Tecn, Lisbon, Portugal..
    Arriaga, Patricia
    CIS IUL, Inst Univ Lisboa ISCTE IUL, Lisbon, Portugal..
    Leite, Iolanda
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Prada, Rui
    Univ Lisbon, INESC ID, Inst Super Tecn, Lisbon, Portugal..
    Melo, Francisco S.
    Univ Lisbon, INESC ID, Inst Super Tecn, Lisbon, Portugal..
    Paiva, Ana
    Univ Lisbon, INESC ID, Inst Super Tecn, Lisbon, Portugal..
    Exploring Prosociality in Human-Robot Teams2019Ingår i: HRI '19: 2019 14TH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, IEEE , 2019, s. 143-151Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper explores the role of prosocial behaviour when people team up with robots in a collaborative game that presents a social dilemma similar to a public goods game. An experiment was conducted with the proposed game in which each participant joined a team with a prosocial robot and a selfish robot. During 5 rounds of the game, each player chooses between contributing to the team goal (cooperate) or contributing to his individual goal (defect). The prosociality level of the robots only affects their strategies to play the game, as one always cooperates and the other always defects. We conducted a user study at the office of a large corporation with 70 participants where we manipulated the game result (winning or losing) in a between-subjects design. Results revealed two important considerations: (1) the prosocial robot was rated more positively in terms of its social attributes than the selfish robot, regardless of the game result; (2) the perception of competence, the responsibility attribution (blame/credit), and the preference for a future partner revealed significant differences only in the losing condition. These results yield important concerns for the creation of robotic partners, the understanding of group dynamics and, from a more general perspective, the promotion of a prosocial society.

  • 36.
    Cruciani, Silvia
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Vision-Based In-Hand Manipulation with Limited Dexterity2019Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [sv]

    In-hand manipulation gör det möjligt att ändra fattningen om ett objekt utan att behöva släppa det. Detta är en viktig komponent och gör det möjligt att lösa många uppgifter.Den mänskliga händen är ett flexibelt instrument som är lämpligt för att flytta föremål inuti handen. Det är dock inte vanligt att robotar är utrustade med lika flexibla händer på grund av utmaningar inom reglerteknik och design av mekaniska system. I själva verket är robotar ofta utrustade med enkla parallel gripper, som är robusta men saknar finmotorik. Denna avhandling fokuserar på att uppnå in-hand manipulation med begränsad finmotorik. De föreslagna lösningarna baseras endast på visuell perception, utan behov av ytterligare sensorer i robotens hand.

    Extrinsic dexterity (extrinsisk finmotorik) gör att enkla robothänder kan utföra in-hand manipulation tack vare utnyttjandet av externa stöd. Denna avhandling introducerar nya metoder för att lösa in-hand manipulation med tröghetskrafter, kontrollerad friktion och yttre tryck som ytterligare stöd för att förbättra robotens manipuleringsförmåga. Pivoting ses som en möjlig lösning för enkla greppförändringar: två metoder som hanterar inexakt friktionsmodellering presenteras samt som gungning är framgångsrikt integrerats i en fullständig manipuleringsuppgift. För storskalig in-hand manipulation introduceras Dexterous Manipulation Graph som en ny representation av objektet. Denna graf är ett användbart verktyg för att planera ändring av grepp via in-hand manipulation. Det kan också utnyttjas för att kombinera både in-hand manipulation och regrasping för att öka möjligheterna att justera greppet. Dessutom utvidgas denna metod för att uppnå in-hand manipulation även för föremål med okänd form. För att utföra de planerade objektrörelserna i robothanden utnyttjas dubbelarmade robotar för att förbättra den dåliga färdigheten hos parallel gripper: den andra armen ses som ett ytterligare stöd som hjälper till att skjuta och hålla objektet för att framgångsrikt justera greppkonfigurationen.

    Denna avhandling presenterar exempel på framgångsrika utföranden av uppgifter där manuell manipulation är ett grundläggande steg i manipuleringsprocessen och visar hur de föreslagna metoderna är en rimlig och effektiv lösning för att uppnå handmanipulation med begränsad finmotorik.

    Ladda ner fulltext (pdf)
    fulltext
  • 37.
    Cruciani, Silvia
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Almeida, Diogo
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL. KTH.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Karayiannidis, Yiannis
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Discrete Bimanual Manipulation for Wrench BalancingManuskript (preprint) (Övrigt vetenskapligt)
    Abstract [en]

    Dual-arm robots can overcome grasping force and payload limitations of a single arm by jointly grasping an object.However, if the distribution of mass of the grasped object is not even, each arm will experience different wrenches that can exceed its payload limits.In this work, we consider the problem of balancing the wrenches experienced by  a dual-arm robot grasping a rigid tray.The distribution of wrenches among the robot arms changes due to objects being placed on the tray.We present an approach to reduce the wrench imbalance among arms through discrete bimanual manipulation.Our approach is based on sequential sliding motions of the grasp points on the surface of the object, to attain a more balanced configuration.%This is achieved in a discrete manner, one arm at a time, to minimize the potential for undesirable object motion during execution.We validate our modeling approach and system design through a set of robot experiments.

    Ladda ner fulltext (pdf)
    fulltext
  • 38.
    Cruciani, Silvia
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Hang, Kaiyu
    Yale University.
    Smith, Christian
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Dual-Arm In-Hand Manipulation Using Visual Feedback2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this work, we address the problem of executing in-hand manipulation based on visual input. Given an initial grasp, the robot has to change its grasp configuration without releasing the object. We propose a method for in-hand manipulation planning and execution based on information on the object’s shape using a dual-arm robot. From the available information on the object, which can be a complete point cloud but also partial data, our method plans a sequence of rotations and translations to reconfigure the object’s pose. This sequence is executed using non-prehensile pushes defined as relative motions between the two robot arms.

  • 39.
    Cruciani, Silvia
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Hang, Yin
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    In-Hand Manipulation of Objects with Unknown ShapesManuskript (preprint) (Övrigt vetenskapligt)
    Abstract [en]

    This work addresses the problem of changing grasp configurations on objects with an unknown shape through in-hand manipulation. Our approach leverages shape priors,learned as deep generative models, to infer novel object shapesfrom partial visual sensing. The Dexterous Manipulation Graph method is extended to build upon incremental data and account for estimation uncertainty in searching a sequence of manipulation actions. We show that our approach successfully solves in-hand manipulation tasks with unknown objects, and demonstrate the validity of these solutions with robot experiments.

    Ladda ner fulltext (pdf)
    fulltext
  • 40.
    Cruciani, Silvia
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Smith, Christian
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Integrating Path Planning and Pivoting2018Ingår i: 2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) / [ed] Maciejewski, AA Okamura, A Bicchi, A Stachniss, C Song, DZ Lee, DH Chaumette, F Ding, H Li, JS Wen, J Roberts, J Masamune, K Chong, NY Amato, N Tsagwarakis, N Rocco, P Asfour, T Chung, WK Yasuyoshi, Y Sun, Y Maciekeski, T Althoefer, K AndradeCetto, J Chung, WK Demircan, E Dias, J Fraisse, P Gross, R Harada, H Hasegawa, Y Hayashibe, M Kiguchi, K Kim, K Kroeger, T Li, Y Ma, S Mochiyama, H Monje, CA Rekleitis, I Roberts, R Stulp, F Tsai, CHD Zollo, L, IEEE , 2018, s. 6601-6608Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this work we propose a method for integrating motion planning and in-hand manipulation. Commonly addressed as a separate step from the final execution, in-hand manipulation allows the robot to reorient an object within the end-effector for the successful outcome of the goal task. A joint achievement of repositioning the object and moving the manipulator towards its desired final pose saves time in the execution and introduces more flexibility in the system. We address this problem using a pivoting strategy (i.e. in-hand rotation) for repositioning the object and we integrate this strategy with a path planner for the execution of a complex task. This method is applied on a Baxter robot and its efficacy is shown by experimental results.

  • 41.
    Cruciani, Silvia
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Smith, Christian
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Hang, Kaiyu
    Hong Kong Univ Sci & Technol, Dept Comp Sci & Engn, Hong Kong, Peoples R China.;Hong Kong Univ Sci & Technol, Inst Adv Study, Hong Kong, Peoples R China..
    Dexterous Manipulation Graphs2018Ingår i: 2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) / [ed] Maciejewski, AA Okamura, A Bicchi, A Stachniss, C Song, DZ Lee, DH Chaumette, F Ding, H Li, JS Wen, J Roberts, J Masamune, K Chong, NY Amato, N Tsagwarakis, N Rocco, P Asfour, T Chung, WK Yasuyoshi, Y Sun, Y Maciekeski, T Althoefer, K AndradeCetto, J Chung, WK Demircan, E Dias, J Fraisse, P Gross, R Harada, H Hasegawa, Y Hayashibe, M Kiguchi, K Kim, K Kroeger, T Li, Y Ma, S Mochiyama, H Monje, CA Rekleitis, I Roberts, R Stulp, F Tsai, CHD Zollo, L, IEEE , 2018, s. 2040-2047Konferensbidrag (Refereegranskat)
    Abstract [en]

    We propose the Dexterous Manipulation Graph as a tool to address in-hand manipulation and reposition an object inside a robot's end-effector. This graph is used to plan a sequence of manipulation primitives so to bring the object to the desired end pose. This sequence of primitives is translated into motions of the robot to move the object held by the end-effector. We use a dual arm robot with parallel grippers to test our method on a real system and show successful planning and execution of in-hand manipulation.

  • 42.
    Cruciani, Silvia
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL. KTH Royal Inst Technol, Div Robot Percept & Learning, EECS, S-11428 Stockholm, Sweden..
    Sundaralingam, Balakumar
    Univ Utah, Robot Ctr, Salt Lake City, UT 84112 USA.;Univ Utah, Sch Comp, Salt Lake City, UT 84112 USA..
    Hang, Kaiyu
    Yale Univ, Dept Mech Engn & Mat Sci, New Haven, CT 06520 USA..
    Kumar, Vikash
    Google AI, San Francisco, CA 94110 USA..
    Hermans, Tucker
    Univ Utah, Robot Ctr, Salt Lake City, UT 84112 USA.;Univ Utah, Sch Comp, Salt Lake City, UT 84112 USA.;NVIDIA Res, Santa Clara, CA USA..
    Kragic, Danica
    KTH, Tidigare Institutioner (före 2005), Numerisk analys och datalogi, NADA. KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL. KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Centrum för autonoma system, CAS. KTH Royal Inst Technol, Div Robot Percept & Learning, EECS, S-11428 Stockholm, Sweden..
    Benchmarking In-Hand Manipulation2020Ingår i: IEEE Robotics and Automation Letters, ISSN 2377-3766, E-ISSN 1949-3045, Vol. 5, nr 2, s. 588-595Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The purpose of this benchmark is to evaluate the planning and control aspects of robotic in-hand manipulation systems. The goal is to assess the systems ability to change the pose of a hand-held object by either using the fingers, environment or a combination of both. Given an object surface mesh from the YCB data-set, we provide examples of initial and goal states (i.e. static object poses and fingertip locations) for various in-hand manipulation tasks. We further propose metrics that measure the error in reaching the goal state from a specific initial state, which, when aggregated across all tasks, also serves as a measure of the systems in-hand manipulation capability. We provide supporting software, task examples, and evaluation results associated with the benchmark.

  • 43.
    Cruciani, Silvia
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Yin, Hang
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Kragic, Danica
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    In-Hand Manipulation of Objects with Unknown ShapesManuskript (preprint) (Övrigt vetenskapligt)
    Abstract [en]

    This work addresses the problem of changing grasp configurations on objects with an unknown shape through in-hand manipulation. Our approach leverages shape priors,learned as deep generative models, to infer novel object shapesfrom partial visual sensing. The Dexterous Manipulation Graph method is extended to build upon incremental data and account for estimation uncertainty in searching a sequence of manipulation actions. We show that our approach successfully solves in-hand manipulation tasks with unknown objects, and demonstrate the validity of these solutions with robot experiments.

    Ladda ner fulltext (pdf)
    fulltext
  • 44. Dembrower, K.
    et al.
    Liu, Yue
    KTH, Centra, Science for Life Laboratory, SciLifeLab.
    Azizpour, Hossein
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Eklund, M.
    Smith, Kevin
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Datavetenskap, Beräkningsvetenskap och beräkningsteknik (CST). KTH, Centra, Science for Life Laboratory, SciLifeLab.
    Lindholm, P.
    Strand, F.
    Comparison of a deep learning risk score and standard mammographic density score for breast cancer risk prediction2020Ingår i: Radiology, ISSN 0033-8419, E-ISSN 1527-1315, Vol. 294, nr 2, s. 265-272Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Background: Most risk prediction models for breast cancer are based on questionnaires and mammographic density assessments. By training a deep neural network, further information in the mammographic images can be considered. Purpose: To develop a risk score that is associated with future breast cancer and compare it with density-based models. Materials and Methods: In this retrospective study, all women aged 40-74 years within the Karolinska University Hospital uptake area in whom breast cancer was diagnosed in 2013-2014 were included along with healthy control subjects. Network development was based on cases diagnosed from 2008 to 2012. The deep learning (DL) risk score, dense area, and percentage density were calculated for the earliest available digital mammographic examination for each woman. Logistic regression models were fitted to determine the association with subsequent breast cancer. False-negative rates were obtained for the DL risk score, age-adjusted dense area, and age-adjusted percentage density. Results: A total of 2283 women, 278 of whom were later diagnosed with breast cancer, were evaluated. The age at mammography (mean, 55.7 years vs 54.6 years; P< .001), the dense area (mean, 38.2 cm2 vs 34.2 cm2; P< .001), and the percentage density (mean, 25.6% vs 24.0%; P< .001) were higher among women diagnosed with breast cancer than in those without a breast cancer diagnosis. The odds ratios and areas under the receiver operating characteristic curve (AUCs) were higher for age-adjusted DL risk score than for dense area and percentage density: 1.56 (95% confidence interval [CI]: 1.48, 1.64; AUC, 0.65), 1.31 (95% CI: 1.24, 1.38; AUC, 0.60), and 1.18 (95% CI: 1.11, 1.25; AUC, 0.57), respectively (P< .001 for AUC). The false-negative rate was lower: 31% (95% CI: 29%, 34%), 36% (95% CI: 33%, 39%; P = .006), and 39% (95% CI: 37%, 42%; P< .001); this difference was most pronounced for more aggressive cancers. Conclusion: Compared with density-based models, a deep neural network can more accurately predict which women are at risk for future breast cancer, with a lower false-negative rate for more aggressive cancers.

  • 45.
    Djikic, Addi
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Segmentation and Depth Estimation of Urban Road Using Monocular Camera and Convolutional Neural Networks2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Deep learning för säkra autonoma transportsystem framträder mer och mer inom forskning och utveckling. Snabb och robust uppfattning om miljön för autonoma fordon kommer att vara avgörande för framtida navigering inom stadsområden med stor trafiksampel.

    I denna avhandling härleder vi en ny form av ett neuralt nätverk som vi kallar AutoNet. Där nätverket är designat som en autoencoder för pixelvis djupskattning av den fria körbara vägytan för stadsområden, där nätverket endast använder sig av en monokulär kamera och dess bilder. Det föreslagna nätverket för djupskattning hanteras som ett regressions problem. AutoNet är även konstruerad som ett klassificeringsnätverk som endast ska klassificera och segmentera den körbara vägytan i realtid med monokulärt seende. Där detta är hanterat som ett övervakande klassificerings problem, som även visar sig vara en mer simpel och mer robust lösning för att hitta vägyta i stadsområden.

    Vi implementerar även ett av de främsta neurala nätverken ENet för jämförelse. ENet är utformat för snabb semantisk segmentering i realtid, med hög prediktions- hastighet. Evalueringen av nätverken visar att AutoNet utklassar ENet i varje prestandamätning för noggrannhet, men visar sig vara långsammare med avseende på antal bilder per sekund. Olika optimeringslösningar föreslås för framtida arbete, för hur man ökar nätverk-modelens bildhastighet samtidigt som man behåller robustheten.All träning och utvärdering görs på Cityscapes dataset. Ny data för träning samt evaluering för djupskattningen för väg skapas med ett nytt tillvägagångssätt, genom att kombinera förberäknade djupkartor med semantiska etiketter för väg. Datainsamling med ett Scania-fordon utförs även, monterad med en monoculär kamera för att testa den slutgiltiga härleda modellen.

    Det föreslagna nätverket AutoNet visar sig vara en lovande topp-presterande modell i fråga om djupuppskattning för väg samt vägklassificering för stadsområden.

    Ladda ner fulltext (pdf)
    fulltext
  • 46.
    Englesson, Erik
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Azizpour, Hossein
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation2019Konferensbidrag (Refereegranskat)
    Ladda ner fulltext (pdf)
    fulltext
  • 47.
    Ericson, Ludvig
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Flying High: Deep Imitation Learning of Optimal Control for Unmanned Aerial Vehicles2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Optimal kontroll för multikoptrar är ett svårt problem delvis på grund av den vanligtvis låga processorkraft som styrdatorn har, samt att multikoptrar är synnerligen instabila system. Djup imitationsinlärning är en metod där en beräkningstung expert approximeras med ett neuralt nätverk, och gör det därigenom möjligt att köra dessa tunga experter som realtidskontroll för multikoptrar. I detta arbete undersöks prestandan och pålitligheten hos djup imitationsinlärning med banoptimering som expert genom att först definiera en dynamisk modell för multikoptrar, sedan applicera en välkänd banoptimeringsmetod på denna modell, och till sist approximera denna expert med imitationsinlärning. Vår undersökning visar att nätverksarkitekturen spelar en avgörande roll för karakteristiken hos både inlärningsprocessens konvergenstid, såväl som den resulterande kontrollpolicyn, och att särskilt banoptimering kan nyttjas för att förbättra konvergenstiden hos imitationsinlärningen. Till sist påpekar vi några begränsningar hos metoden och identifierar särskilt intressanta områden för framtida studier.

    Ladda ner fulltext (pdf)
    OptimQuadControl
  • 48.
    Eriksson, Sara
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Medieteknik och interaktionsdesign, MID.
    Unander-Scharin, Åsa
    Luleå University of Technology.
    Trichon, Vincent
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Medieteknik och interaktionsdesign, MID.
    Unander-Scharin, Carl
    Karlstad University.
    Kjellström, Hedvig
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Höök, Kristina
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Medieteknik och interaktionsdesign, MID.
    Dancing with Drones: Crafting Novel Artistic Expressions through Intercorporeality2019Ingår i: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, New York, NY USA, 2019, s. 617:1-617:12Konferensbidrag (Refereegranskat)
    Ladda ner fulltext (pdf)
    fulltext
  • 49. Feng, Di
    et al.
    Wei, Xiao
    KTH, Skolan för elektroteknik och datavetenskap (EECS).
    Rosenbaum, Lars
    Maki, Atsuto
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Dietmayer, Klaus
    Ulm Univ, Inst Measurement Control & Microtechnol, D-89081 Ulm, Germany..
    Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector2019Ingår i: 2019 30TH IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV19), IEEE , 2019, s. 667-674Konferensbidrag (Refereegranskat)
    Abstract [en]

    Training a deep object detector for autonomous driving requires a huge amount of labeled data. While recording data via on-board sensors such as camera or LiDAR is relatively easy, annotating data is very tedious and time-consuming, especially when dealing with 3D LiDAR points or radar data. Active learning has the potential to minimize human annotation efforts while maximizing the object detector's performance. In this work, we propose an active learning method to train a LiDAR 3D object detector with the least amount of labeled training data necessary. The detector leverages 2D region proposals generated from the RGB images to reduce the search space of objects and speed up the learning process. Experiments show that our proposed method works under different uncertainty estimations and query functions, and can save up to 60% of the labeling efforts while reaching the same network performance. 

  • 50.
    Gandler, Gabriela Zarzar
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL. Peltarion, Hollandargatan 17, S-11160 Stockholm, Sweden.;ABB Corp Res, Vasteras, Sweden..
    Ek, Carl Henrik
    Univ Bristol, Beacon House,Queens Rd, Bristol BS8 1QU, Avon, England..
    Björkman, Mårten
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.
    Stolkin, Rustam
    Univ Birmingham, Birmingham B15 2TT, W Midlands, England..
    Bekiroglu, Yasemin
    Univ Birmingham, Birmingham B15 2TT, W Midlands, England.;ABB Corp Res, Vasteras, Sweden..
    Object shape estimation and modeling, based on sparse Gaussian process implicit surfaces, combining visual data and tactile exploration2020Ingår i: Robotics and Autonomous Systems, ISSN 0921-8890, E-ISSN 1872-793X, Vol. 126, artikel-id 103433Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Inferring and representing three-dimensional shapes is an important part of robotic perception. However, it is challenging to build accurate models of novel objects based on real sensory data, because observed data is typically incomplete and noisy. Furthermore, imperfect sensory data suggests that uncertainty about shapes should be explicitly modeled during shape estimation. Such uncertainty models can usefully enable exploratory action planning for maximum information gain and efficient use of data. This paper presents a probabilistic approach for acquiring object models, based on visual and tactile data. We study Gaussian Process Implicit Surface (GPIS) representation. GPIS enables a non-parametric probabilistic reconstruction of object surfaces from 3D data points, while also providing a principled approach to encode the uncertainty associated with each region of the reconstruction. We investigate different configurations for GPIS, and interpret an object surface as the level-set of an underlying sparse GP. Experiments are performed on both synthetic data, and also real data sets obtained from two different robots physically interacting with objects. We evaluate performance by assessing how close the reconstructed surfaces are to ground-truth object models. We also evaluate how well objects from different categories are clustered, based on the reconstructed surface shapes. Results show that sparse GPs enable a reliable approximation to the full GP solution, and the proposed method yields adequate surface representations to distinguish objects. Additionally the presented approach is shown to provide computational efficiency, and also efficient use of the robot's exploratory actions.

1234 1 - 50 av 183
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf