Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation

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.

[1]  B. Faverjon,et al.  On computing three-finger force-closure grasps of polygonal objects , 1991 .

[2]  Jean-Daniel Boissonnat,et al.  On Computing Four-Finger Equilibrium and Force-Closure Grasps of Polyhedral Objects , 1997, Int. J. Robotics Res..

[3]  Yunhui Liu Computing n-Finger Form-Closure Grasps on Polygonal Objects , 2000, Int. J. Robotics Res..

[4]  Dan Ding,et al.  Computation of 3-D form-closure grasps , 2001, IEEE Trans. Robotics Autom..

[5]  Il Hong Suh,et al.  Optimal grasping based on non-dimensionalized performance indices , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[6]  Ying Li,et al.  An analytical grasp planning on given object with multifingered hand , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[7]  Robert B. Fisher,et al.  Visual quality measures for Characterizing Planar robot grasps , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[8]  Christopher K. I. Williams,et al.  Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[9]  Raúl Suárez,et al.  Fast and Flexible Determination of Force-Closure Independent Regions to Grasp Polygonal Objects , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[10]  James J. Kuffner,et al.  OpenRAVE: A Planning Architecture for Autonomous Robotics , 2008 .

[11]  Oliver Kroemer,et al.  Combining active learning and reactive control for robot grasping , 2010, Robotics Auton. Syst..

[12]  Carl E. Rasmussen,et al.  Gaussian Processes for Machine Learning (GPML) Toolbox , 2010, J. Mach. Learn. Res..

[13]  Manuel Lopes,et al.  Active learning of visual descriptors for grasping using non-parametric smoothed beta distributions , 2012, Robotics Auton. Syst..

[14]  Luc De Raedt,et al.  High-level Reasoning and Low-level Learning for Grasping: A Probabilistic Logic Pipeline , 2014, ArXiv.

[15]  Matt J. Kusner,et al.  Bayesian Optimization with Inequality Constraints , 2014, ICML.

[16]  Antoine Cully,et al.  Robots that can adapt like animals , 2014, Nature.

[17]  Honglak Lee,et al.  Deep learning for detecting robotic grasps , 2013, Int. J. Robotics Res..

[18]  Danica Kragic,et al.  Task-Based Robot Grasp Planning Using Probabilistic Inference , 2015, IEEE Transactions on Robotics.

[19]  Stefanie Tellex,et al.  Autonomously Acquiring Instance-Based Object Models from Experience , 2015, ISRR.

[20]  Jianxiong Xiao,et al.  3D ShapeNets: A deep representation for volumetric shapes , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Leonidas J. Guibas,et al.  ShapeNet: An Information-Rich 3D Model Repository , 2015, ArXiv.

[22]  Nando de Freitas,et al.  Taking the Human Out of the Loop: A Review of Bayesian Optimization , 2016, Proceedings of the IEEE.

[23]  Mathieu Aubry,et al.  Dex-Net 1.0: A cloud-based network of 3D objects for robust grasp planning using a Multi-Armed Bandit model with correlated rewards , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[24]  Chad DeChant,et al.  Shape completion enabled robotic grasping , 2016, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[25]  Danica Kragic,et al.  Affordance detection for task-specific grasping using deep learning , 2017, 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids).

[26]  Xinyu Liu,et al.  Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics , 2017, Robotics: Science and Systems.

[27]  Christopher G. Atkeson,et al.  Deep Kernels for Optimizing Locomotion Controllers , 2017, CoRL.

[28]  L. Matthies,et al.  Semantic and Geometric Scene Understanding for Task-oriented Grasping of Novel Objects from a Single View , 2017 .

[29]  Stefan Schaal,et al.  On the design of LQR kernels for efficient controller learning , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[30]  Stefan Schaal,et al.  On the relevance of grasp metrics for predicting grasp success , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[31]  Christopher G. Atkeson,et al.  Bayesian Optimization Using Domain Knowledge on the ATRIAS Biped , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[32]  Mirko Wächter,et al.  Grasping of Unknown Objects Using Deep Convolutional Neural Networks Based on Depth Images , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[33]  Franziska Meier,et al.  Using Simulation to Improve Sample-Efficiency of Bayesian Optimization for Bipedal Robots , 2018, J. Mach. Learn. Res..

[34]  Silvio Savarese,et al.  Learning task-oriented grasping for tool manipulation from simulated self-supervision , 2020, Int. J. Robotics Res..