Large-Scale Multi-Object Rearrangement

This paper describes a new robotic tabletop rearrangement system, and presents experimental results. The tasks involve rearranging as many as 30 to 100 blocks, sometimes packed with a density of up to 40%. The high packing factor forces the system to push several objects at a time, making accurate simulation difficult, if not impossible. Nonetheless, the system achieves goals specifying the pose of every object, with an average precision of ± 1 mm and ± 2°. The system searches through policy rollouts of simulated pushing actions, using an Iterated Local Search technique to escape local minima. In real world execution, the system executes just one action from a policy, then uses a vision system to update the estimated task state, and replans. The system accepts a fully general description of task goals, which means it can solve the singulation and separation problems addressed in prior work, but can also solve sorting problems and spell out words, among other things. The paper includes examples of several solved problems, statistical analysis of the system’s behavior on different types of problems, and some discussion of limitations, insights, and future work.

[1]  Dieter Fox,et al.  Interactive singulation of objects from a pile , 2012, 2012 IEEE International Conference on Robotics and Automation.

[2]  Manfred K. Warmuth,et al.  Finding a Shortest Solution for the N × N Extension of the 15-PUZZLE Is Intractable , 1986, AAAI.

[3]  Mark Moll,et al.  Randomized Physics-Based Motion Planning for Grasping in Cluttered and Uncertain Environments , 2017, IEEE Robotics and Automation Letters.

[4]  Siddhartha S. Srinivasa,et al.  Rearrangement planning using object-centric and robot-centric action spaces , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[5]  S. LaValle.  Rapidly-exploring random trees : a new tool for path planning , 1998 .

[6]  Siddhartha S. Srinivasa,et al.  A Framework for Push-Grasping in Clutter , 2011, Robotics: Science and Systems.

[7]  Mehmet Remzi Dogar,et al.  Real-Time Online Re-Planning for Grasping Under Clutter and Uncertainty , 2018, 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids).

[8]  Siddhartha S. Srinivasa,et al.  Unobservable Monte Carlo planning for nonprehensile rearrangement tasks , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Anca D. Dragan,et al.  Robot grasping in clutter: Using a hierarchy of supervisors for learning from demonstrations , 2016, 2016 IEEE International Conference on Automation Science and Engineering (CASE).

[10]  Danica Kragic,et al.  Rearrangement with Nonprehensile Manipulation Using Deep Reinforcement Learning , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Siddhartha S. Srinivasa,et al.  Nonprehensile whole arm rearrangement planning on physics manifolds , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Kevin M. Lynch,et al.  Stable Pushing: Mechanics, Controllability, and Planning , 1995, Int. J. Robotics Res..

[13]  Mehmet Remzi Dogar,et al.  Planning with a Receding Horizon for Manipulation in Clutter Using a Learned Value Function , 2018, 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids).

[14]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[15]  James M. Rehg,et al.  Guided pushing for object singulation , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Kostas E. Bekris,et al.  High-Quality Tabletop Rearrangement with Overhand Grasps: Hardness Results and Fast Methods , 2017, Robotics: Science and Systems.

[17]  Gordon T. Wilfong.  Motion planning in the presence of movable obstacles , 1988, SCG '88.

[18]  Kostas E. Bekris,et al.  Dealing with Difficult Instances of Object Rearrangement , 2015, Robotics: Science and Systems.

[19]  Kenneth Y. Goldberg,et al.  Linear Push Policies to Increase Grasp Access for Robot Bin Picking , 2018, 2018 IEEE 14th International Conference on Automation Science and Engineering (CASE).

[20]  Helena Ramalhinho Dias Lourenço,et al.  Iterated Local Search , 2001, Handbook of Metaheuristics.

[21]  Edwin Olson,et al.  AprilTag 2: Efficient and robust fiducial detection , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[22]  Alberto Rodriguez,et al.  Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[23]  A. Volgenant,et al.  A shortest augmenting path algorithm for dense and sparse linear assignment problems , 1987, Computing.

[24]  James J. Kuffner,et al.  Navigation among movable obstacles: real-time reasoning in complex environments , 2004, 4th IEEE/RAS International Conference on Humanoid Robots, 2004..

[25]  Leslie Pack Kaelbling,et al.  Reliably Arranging Objects in Uncertain Domains , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[26]  Matthew T. Mason,et al.  Mechanics of Robotic Manipulation , 2001 .

[27]  Wolfram Burgard,et al.  Learning to Singulate Objects using a Push Proposal Network , 2017, ISRR.

[28]  Erik D. Demaine,et al.  Push-Pull Block Puzzles are Hard , 2017, ArXiv.

[29]  Siddhartha S. Srinivasa,et al.  Kinodynamic randomized rearrangement planning via dynamic transitions between statically stable states , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).