Endre søk
Link to record
Permanent link

Direct link
BETA
Marzinotto, AlejandroORCID iD iconorcid.org/0000-0001-9362-0644
Publikasjoner (7 av 7) Visa alla publikasjoner
Almeida, D., Ambrus, R., Caccamo, S., Chen, X., Cruciani, S., Pinto Basto De Carvalho, J. F., . . . Kragic, D. (2017). Team KTH’s Picking Solution for the Amazon Picking Challenge 2016. In: Warehouse Picking Automation Workshop 2017: Solutions, Experience, Learnings and Outlook of the Amazon Robotics Challenge. Paper presented at ICRA 2017.
Åpne denne publikasjonen i ny fane eller vindu >>Team KTH’s Picking Solution for the Amazon Picking Challenge 2016
Vise andre…
2017 (engelsk)Inngår i: Warehouse Picking Automation Workshop 2017: Solutions, Experience, Learnings and Outlook of the Amazon Robotics Challenge, 2017Konferansepaper, Oral presentation only (Annet (populærvitenskap, 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.

HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
urn:nbn:se:kth:diva-215327 (URN)
Konferanse
ICRA 2017
Merknad

QC 20171009

Tilgjengelig fra: 2017-10-07 Laget: 2017-10-07 Sist oppdatert: 2018-05-24bibliografisk kontrollert
Marzinotto, A., Stork, J. A., Dimarogonas, D. V. & Kragic Jensfelt, D. (2015). Cooperative grasping through topological object representation. In: IEEE-RAS International Conference on Humanoid Robots: . Paper presented at 2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014, 18 November 2014 through 20 November 2014 (pp. 685-692). IEEE Computer Society
Åpne denne publikasjonen i ny fane eller vindu >>Cooperative grasping through topological object representation
2015 (engelsk)Inngår i: IEEE-RAS International Conference on Humanoid Robots, IEEE Computer Society, 2015, s. 685-692Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

We present a cooperative grasping approach based on a topological representation of objects. Using point cloud data we extract loops on objects suitable for generating entanglement. We use the Gauss Linking Integral to derive controllers for multi-agent systems that generate hooking grasps on such loops while minimizing the entanglement between robots. The approach copes well with noisy point cloud data, it is computationally simple and robust. We demonstrate the method for performing object grasping and transportation, through a hooking maneuver, with two coordinated NAO robots.

sted, utgiver, år, opplag, sider
IEEE Computer Society, 2015
Emneord
Anthropomorphic robots, Robots, Topology, Noisy point, Object grasping, Point cloud data, Topological objects, Topological representation, Multi agent systems
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-181529 (URN)10.1109/HUMANOIDS.2014.7041437 (DOI)2-s2.0-84945179216 (Scopus ID)9781479971749 (ISBN)
Konferanse
2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014, 18 November 2014 through 20 November 2014
Merknad

QC 20160318

Tilgjengelig fra: 2016-03-18 Laget: 2016-02-02 Sist oppdatert: 2018-01-10bibliografisk kontrollert
Benítez, G. E., Parra, V., Huerta, M., Marzinotto, A., Clotet, R., González, R., . . . Sanchez, L. E. (2015). Smartphone application for quantitative measurement of Parkinson tremors. In: IFMBE Proceedings: . Paper presented at 6th Latin American Congress on Biomedical Engineering, CLAIB 2014, 29 October 2014 through 31 October 2014 (pp. 785-788). Springer
Åpne denne publikasjonen i ny fane eller vindu >>Smartphone application for quantitative measurement of Parkinson tremors
Vise andre…
2015 (engelsk)Inngår i: IFMBE Proceedings, Springer, 2015, s. 785-788Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

One of the most common concerns in the atten-tion of patients with Parkinson's disease is an objectively eval-uation of the illness progress and the efficacy of treatments, in terms of the intensity and frequency of tremors. This symptom is produced by gradual degradation of the pigmented neurons located at the substantia nigra in the brain, in order to detect such movement levels. This paper proposes a Smartphone application for a quantitative detection, measurement and analysis of the Parkinson's tremor, due to the global use of Smartphones and the affordable cost of some Android plat-form devices. The subjects of this working project are those people who suffer from Parkinson's disease, who could down-load the application to their mobile phone in order to measure quantitatively the intensity and duration of their tremors, in any place, to send reports by email or to record them for a later use. The application enables the remote monitoring of the patients.

sted, utgiver, år, opplag, sider
Springer, 2015
Serie
IFMBE Proceedings, ISSN 1680-0737 ; 49
Emneord
Accelerometers sensors, Parkinson’s disease, Smartphone, Tremor detec-tion, Biomedical engineering, Neurodegenerative diseases, Remote patient monitoring, Signal encoding, Smartphones, Gradual degradation, Measurement and analysis, Parkinson's disease, Quantitative detection, Quantitative measurement, Remote monitoring, Smart-phone applications, Diseases
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-167411 (URN)10.1007/978-3-319-13117-7_200 (DOI)000363767200199 ()2-s2.0-84925235609 (Scopus ID)9783319131160 (ISBN)
Konferanse
6th Latin American Congress on Biomedical Engineering, CLAIB 2014, 29 October 2014 through 31 October 2014
Merknad

QC 20150522

Tilgjengelig fra: 2015-05-22 Laget: 2015-05-22 Sist oppdatert: 2018-01-11bibliografisk kontrollert
Wang, Y., Ögren, P., Colledanchise, M. & Marzinotto, A. (2014). A Distributed Convergent Solution to the Ambulance Positioning Problem on a Streetmap Graph. In: Boje, Edward, Xia, Xiaohua (Ed.), : . Paper presented at The 19th IFAC world congress, Cape Town, August 24-29, 2014 (pp. 9190-9196). IFAC Papers Online, 19
Åpne denne publikasjonen i ny fane eller vindu >>A Distributed Convergent Solution to the Ambulance Positioning Problem on a Streetmap Graph
2014 (engelsk)Inngår i: / [ed] Boje, Edward, Xia, Xiaohua, IFAC Papers Online, 2014, Vol. 19, s. 9190-9196Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

In this paper, we combine ideas from multi-agent cooperative coverage control, with problem formulations from the resource allocation field, to create a distributed convergent approach to the ambulance positioning problem. Inspired by coverage control we use the graph version of so-called Voronoi regions, making the solution distributed and reactive, thereby freeing computational resources. The solution is distributed in the sense that each vehicle only needs to know the positions of its neighbors, and the computations of each vehicle only depend on the size of its Voronoi region/set. This implies that considering a problem of twice the size, using twice the number of vehicles will leave the computational load per vehicle unchanged. The freed resources are used to capture the allocation problem in more detail: maximizing an estimate of the victim survival probability instead of more coarse measures of ambulance availability. Using real city street map data from OpenStreetMap (OSM), we provide simulation results illustrating the applicability of our approach. Finally, we prove that the proposed distributed algorithm is convergent in the sense that it finds a local optimum in finite time.

sted, utgiver, år, opplag, sider
IFAC Papers Online, 2014
Emneord
Coordination of multiple vehicle systems; Multi-agent systems; Distributed control and estimation
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
urn:nbn:se:kth:diva-165678 (URN)10.3182/20140824-6-ZA-1003.00115 (DOI)
Konferanse
The 19th IFAC world congress, Cape Town, August 24-29, 2014
Prosjekter
European Union FP7 project Robo- How.Cog
Forskningsfinansiär
EU, FP7, Seventh Framework Programme, FP7-ICT-288533Swedish Research CouncilSwedish Foundation for Strategic Research
Merknad

QC 20150507

Tilgjengelig fra: 2015-04-29 Laget: 2015-04-29 Sist oppdatert: 2016-02-24bibliografisk kontrollert
Tumova, J., Marzinotto, A., Dimarogonas, D. V. & Kragic, D. (2014). Maximally Satisfying LTL Action Planning. In: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS 2014): . Paper presented at 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014, Palmer House Hilton Hotel Chicago, United States, 14 September 2014 through 18 September 2014 (pp. 1503-1510). IEEE
Åpne denne publikasjonen i ny fane eller vindu >>Maximally Satisfying LTL Action Planning
2014 (engelsk)Inngår i: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS 2014), IEEE , 2014, s. 1503-1510Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

We focus on autonomous robot action planning problem from Linear Temporal Logic (LTL) specifications, where the action refers to a "simple" motion or manipulation task, such as "go from A to B" or "grasp a ball". At the high-level planning layer, we propose an algorithm to synthesize a maximally satisfying discrete control strategy while taking into account that the robot's action executions may fail. Furthermore, we interface the high-level plan with the robot's low-level controller through a reactive middle-layer formalism called Behavior Trees (BTs). We demonstrate the proposed framework using a NAO robot capable of walking, ball grasping and ball dropping actions.

sted, utgiver, år, opplag, sider
IEEE, 2014
Serie
IEEE International Conference on Intelligent Robots and Systems, ISSN 2153-0858
Emneord
Intelligent robots, Robots, Temporal logic, Action execution, Action planning, Behavior trees, Discrete control strategies, Linear temporal logic specifications, Low-level controllers, Manipulation task, Robot actions
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-163507 (URN)10.1109/IROS.2014.6942755 (DOI)000349834601089 ()2-s2.0-84911499807 (Scopus ID)978-1-4799-6934-0 (ISBN)
Konferanse
2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014, Palmer House Hilton Hotel Chicago, United States, 14 September 2014 through 18 September 2014
Merknad

QC 20150407

Tilgjengelig fra: 2015-04-07 Laget: 2015-04-07 Sist oppdatert: 2018-01-11bibliografisk kontrollert
Colledanchise, M., Marzinotto, A. & Ögren, P. (2014). Performance Analysis of Stochastic Behavior Trees. In: ICRA 2014: . Paper presented at IEEE International Conference on Robotics and Automation (ICRA), 2014, Hong Kong, PEOPLES R CHINA, MAY 31-JUN 07, 2014.
Åpne denne publikasjonen i ny fane eller vindu >>Performance Analysis of Stochastic Behavior Trees
2014 (engelsk)Inngår i: ICRA 2014, 2014Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

This paper presents a mathematical framework for performance analysis of Behavior Trees (BTs). BTs are a recent alternative to Finite State Machines (FSMs), for doing modular task switching in robot control architectures. By encoding the switching logic in a tree structure, instead of distributing it in the states of a FSM, modularity and reusability are improved.

In this paper, we compute performance measures, such as success/failure probabilities and execution times, for plans encoded and executed by BTs. To do this, we first introduce Stochastic Behavior Trees (SBT), where we assume that the probabilistic performance measures of the basic action controllers are given. We then show how Discrete Time Markov Chains (DTMC) can be used to aggregate these measures from one level of the tree to the next. The recursive structure of the tree then enables us to step by step propagate such estimates from the leaves (basic action controllers) to the root (complete task execution). Finally, we verify our analytical results using massive Monte Carlo simulations, and provide an illustrative example of the results for a complex robotic task.

HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-147012 (URN)10.1109/ICRA.2014.6907328 (DOI)000377221103040 ()2-s2.0-84929207712 (Scopus ID)
Konferanse
IEEE International Conference on Robotics and Automation (ICRA), 2014, Hong Kong, PEOPLES R CHINA, MAY 31-JUN 07, 2014
Forskningsfinansiär
EU, FP7, Seventh Framework Programme
Merknad

QC 20150209

Tilgjengelig fra: 2014-06-21 Laget: 2014-06-21 Sist oppdatert: 2020-02-21bibliografisk kontrollert
Marzinotto, A., Colledanchise, M., Smith, C. & Ögren, P. (2014). Towards a Unified Behavior Trees Framework for Robot Control. In: Robotics and Automation (ICRA), 2014 IEEE International Conference on : . Paper presented at IEEE International Conference on Robots and Automation,Hong Kong,May 31 2014-June 7 2014 (pp. 5420-5427). IEEE Robotics and Automation Society
Åpne denne publikasjonen i ny fane eller vindu >>Towards a Unified Behavior Trees Framework for Robot Control
2014 (engelsk)Inngår i: Robotics and Automation (ICRA), 2014 IEEE International Conference on , IEEE Robotics and Automation Society, 2014, s. 5420-5427Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

This paper presents a unified framework for Behavior Trees (BTs), a plan representation and execution tool. The available literature lacks the consistency and mathematical rigor required for robotic and control applications. Therefore, we approach this problem in two steps: first, reviewing the most popular BT literature exposing the aforementioned issues; second, describing our unified BT framework along with equivalence notions between BTs and Controlled Hybrid Dynamical Systems (CHDSs). This paper improves on the existing state of the art as it describes BTs in a more accurate and compact way, while providing insight about their actual representation capabilities. Lastly, we demonstrate the applicability of our framework to real systems scheduling open-loop actions in a grasping mission that involves a NAO robot and our BT library.

sted, utgiver, år, opplag, sider
IEEE Robotics and Automation Society, 2014
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-165676 (URN)10.1109/ICRA.2014.6907656 (DOI)2-s2.0-84911492157 (Scopus ID)
Konferanse
IEEE International Conference on Robots and Automation,Hong Kong,May 31 2014-June 7 2014
Merknad

QC 20150507

Tilgjengelig fra: 2015-04-29 Laget: 2015-04-29 Sist oppdatert: 2020-03-10bibliografisk kontrollert
Organisasjoner
Identifikatorer
ORCID-id: ORCID iD iconorcid.org/0000-0001-9362-0644