Chris Bowen
Skip Abstract Section
Skip Supplemental Material SectionAbstract
We present a robot motion planning approach for performing a learned task while reacting to the movement of obstacles and task-relevant objects. We employ a closed-loop, sampling-based motion planner operating multiple times a second that senses obstacles and task-relevant objects and generates collision-free motion plans based on a learned-task model. The task model is learned from expert demonstrations prior to task execution and is represented as a hidden Markov model. During task execution, our motion planner quickly searches in the Cartesian product of the task model and a probabilistic roadmap for a collision-free plan with features most similar to the demonstrations given the current locations of the task-relevant objects. We accelerate replanning using a fast bidirectional search and by biasing the sampling distribution using information from the learned-task model. We show the efficacy of our approach with the Baxter robot performing two tasks.
Supplemental Material
Available for Download
zip
bowen.zip (9.2 MB)
Supplemental movie and image files for, Closed-Loop Global Motion Planning for Reactive, Collision-Free Execution of Learned Tasks
- Ron Alterovitz, Sachin Patil, and Anna Derbakova. 2011. Rapidly-exploring roadmaps: Weighing exploration vs. refinement in optimal motion planning. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’11). 3706--3712.Google Scholar
Cross Ref
- Scott Benson. 1995. Inductive learning of reactive action models. In Proceedings of the International Conference on Machine Learning (ICML’95). 47--54. Google ScholarDigital Library
- Dmitry Berenson, Thierry Siméon, and Siddhartha S. Srinivasa. 2011. Addressing cost-space chasms in manipulation planning. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’11). 4561--4568.Google Scholar
- Dmitry Berenson, Siddhartha S. Srinivasa, Dave Ferguson, and James J. Kuffner. 2009. Manipulation planning on constraint manifolds. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’09). 625--632. Google ScholarDigital Library
- Julien Bidot, Lars Karlsson, Fabien Lagriffoul, and Alessandro Saffiotti. 2017. Geometric backtracking for combined task and motion planning in robotic systems. Artificial Intelligence 247, 229--265.Google ScholarCross Ref
- Chris Bowen and Ron Alterovitz. 2014. Closed-loop global motion planning for reactive execution of learned tasks. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’14). 1754--1760.Google ScholarCross Ref
- Chris Bowen, Gu Ye, and Ron Alterovitz. 2015. Asymptotically-optimal motion planning for learned tasks using time-dependent cost maps. IEEE Transactions on Automation Science and Engineering 12, 1, 171--182.Google ScholarCross Ref
- Felix Burget, Maren Bennewitz, and Wolfram Burgard. 2016. BI2RRT*: An efficient sampling-based path planning framework for task-constrained mobile manipulation. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’16). IEEE, 3714--3721.Google ScholarCross Ref
- Sylvain Calinon, Florent D’halluin, Darwin G. Caldwell, and Aude G. Billard. 2009. Handling of multiple constraints and motion alternatives in a robot programming by demonstration framework. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots. 582--588.Google Scholar
- Howie Choset, Kevin M. Lynch, Seth A. Hutchinson, George A. Kantor, Wolfram Burgard, Lydia E. Kavraki, and Sebastian Thrun. 2005. Principles of Robot Motion: Theory, Algorithms, and Implementations. MIT Press, Cambridge, MA.Google Scholar
- Jonathan Claassens. 2010. An RRT-based path planner for use in trajectory imitation. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’10). 3090--3095.Google ScholarCross Ref
- Jonathan Claassens and Yiannis Demiris. 2012. Exploiting affordance symmetries for task reproduction planning. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots (Humanoids). IEEE, 653--659.Google ScholarCross Ref
- Ioan A. Şucan and Sachin Chitta. 2012. Motion planning with constraints using configuration space approximations. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’12). 1904--1910.Google Scholar
- Neil T. Dantam, Zachary K. Kingston, Swarat Chaudhuri, and Lydia E. Kavraki. 2016. Incremental task and motion planning: A constraint-based approach. In Robotics: Science and Systems (RSS’16). Robotics: Science and Systems Foundation.Google Scholar
- Richard I. A. Davis and Brian C. Lovell. 2004. Comparing and evaluating HMM ensemble training algorithms using train and test and condition number criteria. Formal Pattern Analysis 8 Applications 6, 4, 327--335. Google ScholarDigital Library
- Dennis de Champeaux. 1983. Bidirectional heuristic search again. Journal of the ACM 30, 1, 22--32. Google ScholarDigital Library
- A. Dobson and Kostas E. Bekris. 2013. A study on the finite-time near-optimality properties of sampling-based motion planners. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’13). 1236--1241.Google Scholar
- Staffan Ekvall and Danica Kragic. 2008. Robot learning from demonstration: A task-level planning approach. International Journal of Advanced Robotic Systems 5, 3, 33.Google ScholarCross Ref
- Dave Ferguson, Nidhi Kalra, and Anthony Stentz. 2006. Replanning with RRTs. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’06). IEEE, 1243--1248.Google ScholarCross Ref
- Perttu Hämäläinen, Joose Rajamäki, and C. Karen Liu. 2015. Online control of simulated humanoids using particle belief propagation. ACM Transactions on Graphics 34, 4, 81. Google ScholarDigital Library
- Kris Hauser. 2012. On responsiveness, safety, and completeness in real-time motion planning. Autonomous Robots 32, 1, 35--48. Google ScholarDigital Library
- Micha Hersch, Florent Guenter, Sylvain Calinon, and Aude Billard. 2008. Dynamical system modulation for robot learning via kinesthetic demonstrations. IEEE Transactions on Robotics 24, 6, 1463--1467. Google ScholarDigital Library
- Leonard Jaillet, Juan Cortes, and Thierry Simeon. 2010. Sampling-based path planning on configuration-space costmaps. IEEE Transactions on Robotics 26, 4, 635--646. Google ScholarDigital Library
- Leonard Jaillet and Josep Porta. 2012. Asymptotically-optimal path planning on manifolds. In Proceedings of Robotics: Science and Systems (RSS’12). Robotics: Science and Systems Foundation, Sydney, Australia.Google ScholarCross Ref
- Rainer Jakel, Sven R. Schmidt-Rohr, Martin Losch, and Rudiger Dillmann. 2010. Representation and constrained planning of manipulation strategies in the context of programming by demonstration. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’10). 162--169.Google ScholarCross Ref
- Sertac Karaman and Emilio Frazzoli. 2011. Sampling-based algorithms for optimal motion planning. International Journal of Robotics Research 30, 7, 846--894. Google ScholarDigital Library
- L. E. Kavraki, P. Svestka, J.-C. Latombe, and M. Overmars. 1996. Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transactions on Robotics and Automation 12, 4, 566--580.Google ScholarCross Ref
- Seyed Mohammad Khansari-Zadeh and Aude Billard. 2012. A dynamical system approach to realtime obstacle avoidance. Autonomous Robots 32, 4, 433--454. Google ScholarDigital Library
- Beobkyoon Kim, Terry Taewoong Um, Chansu Suh, and Frank C. Park. 2016. Tangent bundle RRT: A randomized algorithm for constrained motion planning. Robotica 34, 1, 202--225.Google ScholarCross Ref
- D. Kulic, W. Takano, and Y. Nakamura. 2008. Incremental learning, clustering and hierarchy formation of whole body motion patterns using adaptive hidden Markov chains. International Journal of Robotics Research 27, 7, 761--784. Google ScholarDigital Library
- Fabien Lagriffoul, Dimitar Dimitrov, Julien Bidot, Alessandro Saffiotti, and Lars Karlsson. 2014. Efficiently combining task and motion planning using geometric constraints. International Journal of Robotics Research 33, 14, 1726--1747. Google ScholarDigital Library
- Steven M. LaValle. 2006. Planning Algorithms. Cambridge University Press, Cambridge, UK. Google ScholarDigital Library
- Ryan Luna, Ioan A. Şucan, Mark Moll, and Lydia E. Kavraki. 2013. Anytime solution optimization for sampling-based motion planning. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’13). 5068--5074.Google Scholar
- J. Mainprice, E. A. Sisbot, L. Jaillet, J. Cortés, R. Alami, and T. Siméon. 2011. Planning human-aware motions using a sampling-based costmap planner. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’11). 5012--5017.Google Scholar
- James D. Marble and Kostas E. Bekris. 2013. Asymptotically near-optimal planning with probabilistic roadmap spanners. IEEE Transactions on Robotics 29, 2, 432--444. Google ScholarDigital Library
- Anahita Mohseni-Kabir, Charles Rich, Sonia Chernova, Candace L. Sidner, and Daniel Miller. 2015. Interactive hierarchical task learning from a single demonstration. In Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction (HRI’15). ACM Press, New York, New York, USA, 205--212. Google ScholarDigital Library
- P. Pastor, L. Righetti, M. Kalakrishnan, and S. Schaal. 2011. Online movement adaptation based on previous sensor experiences. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’11). 365--371.Google Scholar
- Rethink Robotics. 2013. Baxter Research Robot. Retrieved April 26, 2018 from www.rethinkrobotics.com/baxter-research-robot.Google Scholar
- Jonathan Scholz and Mike Stilman. 2010. Combining motion planning and optimization for flexible robot manipulation. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots. 80--85.Google ScholarCross Ref
- Ashwini Shukla and Aude Billard. 2012. Coupled dynamical system based arm-hand grasping model for learning fast adaptation strategies. Robotics and Autonomous Systems 60, 3, 424--440. Google ScholarDigital Library
- Siddharth Srivastava, Eugene Fang, Lorenzo Riano, Rohan Chitnis, Stuart Russell, and Pieter Abbeel. 2014. Combined task and motion planning through an extensible planner-independent interface layer. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). IEEE, 639--646.Google ScholarCross Ref
- Mike Stilman. 2010. Global manipulation planning in robot joint space with task constraints. IEEE Transactions on Robotics 26, 3, 576--584. Google ScholarDigital Library
- Yuandong Yang and Oliver Brock. 2009. Elastic roadmaps—Motion generation for autonomous mobile manipulation. Autonomous Robots 28, 1, 113. Google ScholarDigital Library
- Gu Ye and Ron Alterovitz. 2011. Demonstration-guided motion planning. In Proceedings of the International Symposium on Robotics Research (ISRR’11), Springer Tracts in Advanced Robotics, Vol. 100. 291--307.Google Scholar
- Matt Zucker, James Kuffner, and Michael Branicky. 2007. Multipartite RRTs for rapid replanning in dynamic environments. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’07). 1603--1609.Google ScholarCross Ref
- Matt Zucker, Nathan Ratliff, Anca D. Dragan, Mihail Pivtoraiko, Matthew Klingensmith, Christopher M. Dellin, J. Andrew Bagnell, and Siddhartha S. Srinivasa. 2013. CHOMP: Covariant Hamiltonian optimization for motion planning. International Journal of Robotics Research 32, 9--10, 1164--1193. Google ScholarDigital Library
Index Terms
- Closed-Loop Global Motion Planning for Reactive, Collision-Free Execution of Learned Tasks
Recommendations
Action observation in collision-free motion planning for mobile robots
IROS '95: Proceedings of the International Conference on Intelligent Robots and Systems-Volume 2 - Volume 2This paper addresses the problem of mutual collision avoidance of mobile robots in a narrow and uncertain environment. The minimal application of inter-robot communication is required to develop an autonomous and flexible mobile robot in such an ...
Comparative analysis of collision-free path-planning methods for multi-manipulator systems
Motion planning for manipulators with many degrees of freedom is a complex task. The research in this area has been mostly restricted to static environments. This paper presents a comparative analysis of three reactive on-line path-planning methods for ...
Dynamic Motion Planning Algorithm in Human-Robot Collision Avoidance
Intelligent Robotics and ApplicationsAbstractThe collision-free robotic motion planning algorithm in a dynamic environment is an effective method for the prevention of collision in a human-robot interaction scenario. In this paper, an improvement of the Rapidly-exploring Random Tree (RRT) ...
Comments