Change search
Refine search result
1 - 6 of 6
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Antonova, Rika
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Kokic, Mia
    KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Stork, Johannes A.
    KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Kragic, Danica
    KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation2018Conference paper (Refereed)
    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.

  • 2.
    Antonova, Rika
    et al.
    KTH, School of Computer Science and Communication (CSC), Robotics, perception and learning, RPL.
    Rai, Akshara
    Robotics Institute, School of Computer Science, Carnegie Mellon University, USA.
    Atkeson, Christopher G.
    Robotics Institute, School of Computer Science, Carnegie Mellon University, USA.
    Deep kernels for optimizing locomotion controllers2017In: Proceedings of the 1st Annual Conference on Robot Learning, PMLR , 2017Conference paper (Refereed)
    Abstract [en]

    Sample efciency is important when optimizing parameters of locomotion controllers, since hardware experiments are time consuming and expensive. Bayesian Optimization, a sample-efcient optimization framework, has recently been widely applied to address this problem, but further improvements in sample efciency are needed for practical applicability to real-world robots and highdimensional controllers. To address this, prior work has proposed using domain expertise for constructing custom distance metrics for locomotion. In this work we show how to learn such a distance metric automatically. We use a neural network to learn an informed distance metric from data obtained in high-delity simulations. We conduct experiments on two different controllers and robot architectures. First, we demonstrate improvement in sample efciency when optimizing a 5-dimensional controller on the ATRIAS robot hardware. We then conduct simulation experiments to optimize a 16-dimensional controller for a 7-link robot model and obtain signicant improvements even when optimizing in perturbed environments. This demonstrates that our approach is able to enhance sample efciency for two different controllers, hence is a tting candidate for further experiments on hardware in the future. Keywor

  • 3.
    Antonova, Rika
    et al.
    Robotics Institute, School of Computer Science, Carnegie Mellon University, USA.
    Rai, Akshara
    Robotics Institute, School of Computer Science, Carnegie Mellon University, USA.
    Atkeson, Christopher G.
    Robotics Institute, School of Computer Science, Carnegie Mellon University, USA.
    Sample efficient optimization for learning controllers for bipedal locomotion2016In: IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 2016, IEEE conference proceedings, 2016Conference paper (Refereed)
    Abstract [en]

    Learning policies for bipedal locomotion can be difficult, as experiments are expensive and simulation does not usually transfer well to hardware. To counter this, we need algorithms that are sample efficient and inherently safe. Bayesian Optimization is a powerful sample-efficient tool for optimizing non-convex black-box functions. However, its performance can degrade in higher dimensions. We develop a distance metric for bipedal locomotion that enhances the sample-efficiency of Bayesian Optimization and use it to train a 16 dimensional neuromuscular model for planar walking. This distance metric reflects some basic gait features of healthy walking and helps us quickly eliminate a majority of unstable controllers. With our approach we can learn policies for walking in less than 100 trials for a range of challenging settings. In simulation, we show results on two different costs and on various terrains including rough ground and ramps, sloping upwards and downwards. We also perturb our models with unknown inertial disturbances analogous with differences between simulation and hardware. These results are promising, as they indicate that this method can potentially be used to learn control policies on hardware.

  • 4.
    Kokic, Mia
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for Autonomous Systems, CAS. KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Antonova, Rika
    KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for Autonomous Systems, CAS. KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Stork, Johannes A.
    KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for Autonomous Systems, CAS. KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Kragic, Danica
    KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for Autonomous Systems, CAS. KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation2018In: Proceedings of The 2nd Conference on Robot Learning, PMLR 87, 2018, p. 641-650Conference paper (Refereed)
    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.

  • 5.
    Rai, Akshara
    et al.
    Carnegie Mellon Univ, Sch Comp Sci, Robot Inst, Pittsburgh, PA 15213 USA..
    Antonova, Rika
    KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
    Meier, Franziska
    Univ Washington, Paul G Allen Sch Comp Sci Engn, Seattle, WA 98195 USA..
    Atkeson, Christopher G.
    Carnegie Mellon Univ, Sch Comp Sci, Robot Inst, Pittsburgh, PA 15213 USA..
    Using Simulation to Improve Sample-Efficiency of Bayesian Optimization for Bipedal Robots2019In: Journal of machine learning research, ISSN 1532-4435, E-ISSN 1533-7928, Vol. 20, article id 49Article in journal (Refereed)
    Abstract [en]

    Learning for control can acquire controllers for novel robotic tasks, paving the path for autonomous agents. Such controllers can be expert-designed policies, which typically require tuning of parameters for each task scenario. In this context, Bayesian optimization (BO) has emerged as a promising approach for automatically tuning controllers. However, sample-efficiency can still be an issue for high-dimensional policies on hardware. Here, we develop an approach that utilizes simulation to learn structured feature transforms that map the original parameter space into a domain-informed space. During BO, similarity between controllers is now calculated in this transformed space. Experiments on the ATRIAS robot hardware and simulation show that our approach succeeds at sample-efficiently learning controllers for multiple robots. Another question arises: What if the simulation significantly differs from hardware? To answer this, we create increasingly approximate simulators and study the effect of increasing simulation-hardware mismatch on the performance of Bayesian optimization. We also compare our approach to other approaches from literature, and find it to be more reliable, especially in cases of high mismatch. Our experiments show that our approach succeeds across different controller types, bipedal robot models and simulator fidelity levels, making it applicable to a wide range of bipedal locomotion problems.

  • 6.
    Rai, Akshara
    et al.
    Carnegie Mellon Univ, Sch Comp Sci, Robot Inst, Pittsburgh, PA 15213 USA..
    Antonova, Rika
    KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL. KTH Royal Inst Technol, CSC, Robot Percept & Learning, Stockholm, Sweden..
    Song, Seungmoon
    Carnegie Mellon Univ, Sch Comp Sci, Robot Inst, Pittsburgh, PA 15213 USA..
    Martin, William
    Carnegie Mellon Univ, Sch Comp Sci, Robot Inst, Pittsburgh, PA 15213 USA..
    Geyer, Hartmut
    Carnegie Mellon Univ, Sch Comp Sci, Robot Inst, Pittsburgh, PA 15213 USA..
    Atkeson, Christopher
    Carnegie Mellon Univ, Sch Comp Sci, Robot Inst, Pittsburgh, PA 15213 USA..
    Bayesian Optimization Using Domain Knowledge on the ATRIAS Biped2018In: 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), IEEE, 2018, p. 1771-1778Conference paper (Refereed)
    Abstract [en]

    Robotics controllers often consist of expert-designed heuristics, which can be hard to tune in higher dimensions. Simulation can aid in optimizing these controllers if parameters learned in simulation transfer to hardware. Unfortunately, this is often not the case in legged locomotion, necessitating learning directly on hardware. This motivates using data-efficient learning techniques like Bayesian Optimization (BO) to minimize collecting expensive data samples. BO is a black-box data-efficient optimization scheme, though its performance typically degrades in higher dimensions. We aim to overcome this problem by incorporating domain knowledge, with a focus on bipedal locomotion. In our previous work, we proposed a feature transformation that projected a 16-dimensional locomotion controller to a 1-dimensional space using knowledge of human walking. When optimizing a human-inspired neuromuscular controller in simulation, this feature transformation enhanced sample efficiency of BO over traditional BO with a Squared Exponential kernel. In this paper, we present a generalized feature transform applicable to non-humanoid robot morphologies and evaluate it on the ATRIAS bipedal robot, in both simulation and hardware. We present three different walking controllers and two are evaluated on the real robot. Our results show that this feature transform captures important aspects of walking and accelerates learning on hardware and simulation, as compared to traditional BO.

1 - 6 of 6
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf