LEGO: Leveraging Experience in Roadmap Generation for Sampling-Based Planning

We consider the problem of leveraging prior experience to generate roadmaps in sampling-based motion planning. A desirable roadmap is one that is sparse, allowing for fast search, with nodes spread out at key locations such that a low- cost feasible path exists. An increasingly popular approach is to learn a distribution of nodes that would produce such a roadmap. State-of-the-art is to train a conditional variational auto-encoder (CVAE) on the prior dataset with the shortest paths as target input. While this is quite effective on many problems, we show it can fail in the face of complex obstacle configurations or mismatch between training and testing. We present an algorithm LEGO that addresses these issues by training the CVAE with target samples that satisfy two important criteria. Firstly, these samples belong only to bottleneck regions along near-optimal paths that are otherwise difficult- to-sample with a uniform sampler. Secondly, these samples are spread out across diverse regions to maximize the likelihood of a feasible path existing. We formally define these properties and prove performance guarantees for LEGO. We extensively evaluate LEGO on a range of planning problems, including robot arm planning, and report significant gains over heuristics as well as learned baselines.

[1]  David Hsu,et al.  Workspace-Based Connectivity Oracle: An Adaptive Sampling Strategy for PRM Planning , 2006, WAFR.

[2]  B. Faverjon,et al.  Probabilistic Roadmaps for Path Planning in High-Dimensional Con(cid:12)guration Spaces , 1996 .

[3]  Daniel Vallejo,et al.  OBPRM: an obstacle-based PRM for 3D workspaces , 1998 .

[4]  David Hsu,et al.  Workspace importance sampling for probabilistic roadmap planning , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[5]  Daniel D. Lee,et al.  Learning Implicit Sampling Distributions for Motion Planning , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[6]  Boris Katz,et al.  Deep Sequential Models for Sampling-Based Planning , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  James J. Kuffner,et al.  Randomized statistical path planning , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Maximilian Karl,et al.  Dynamic movement primitives in latent space of time-dependent variational autoencoders , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[9]  Yisong Yue,et al.  Generating Long-term Trajectories Using Deep Hierarchical Networks , 2016, NIPS.

[10]  Oliver Brock,et al.  Toward Optimal Configuration Space Sampling , 2005, Robotics: Science and Systems.

[11]  Oliver Brock,et al.  Sampling-Based Motion Planning Using Predictive Models , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[12]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[13]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[14]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

[15]  Jean-Claude Latombe,et al.  On the Probabilistic Foundations of Probabilistic Roadmap Planning , 2006, Int. J. Robotics Res..

[16]  David Hsu,et al.  The bridge test for sampling narrow passages with probabilistic roadmap planners , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[17]  J. Halton On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integrals , 1960 .

[18]  Steven M. LaValle,et al.  Planning algorithms , 2006 .

[19]  Mark H. Overmars,et al.  The Gaussian sampling strategy for probabilistic roadmap planners , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[20]  Gildardo Sánchez-Ante,et al.  Hybrid PRM Sampling with a Cost-Sensitive Adaptive Strategy , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[21]  Lydia Tapia,et al.  A Machine Learning Approach for Feature-Sensitive Motion Planning , 2004, WAFR.

[22]  Lydia E. Kavraki,et al.  A framework for using the workspace medial axis in PRM planners , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[23]  Siddhartha S. Srinivasa,et al.  Informed RRT*: Optimal Incremental Path Planning Focused through an Admissible Ellipsoidal Heuristic , 2014, ArXiv.

[24]  Daniel D. Lee,et al.  Learning Dimensional Descent for Optimal Motion Planning in High-dimensional Spaces , 2011, AAAI.

[25]  Marco Pavone,et al.  Robot Motion Planning in Learned Latent Spaces , 2018, IEEE Robotics and Automation Letters.

[26]  Jean-Paul Laumond,et al.  Linear dimensionality reduction in random motion planning , 2011, Int. J. Robotics Res..

[27]  Marco Pavone,et al.  Deterministic sampling-based motion planning: Optimality, complexity, and performance , 2015, ISRR.

[28]  Han-Lim Choi,et al.  Approximate Inference-Based Motion Planning by Learning and Exploiting Low-Dimensional Latent Variable Models , 2018, IEEE Robotics and Automation Letters.

[29]  Michael C. Yip,et al.  Deeply Informed Neural Sampling for Robot Motion Planning , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[30]  Siddhartha S. Srinivasa,et al.  Pareto-optimal search over configuration space beliefs for anytime motion planning , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[31]  Marco Pavone,et al.  Learning Sampling Distributions for Robot Motion Planning , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[32]  Rajeev Motwani,et al.  Path Planning in Expansive Configuration Spaces , 1999, Int. J. Comput. Geom. Appl..

[33]  James J. Kuffner,et al.  Adaptive workspace biasing for sampling-based planners , 2008, 2008 IEEE International Conference on Robotics and Automation.

[34]  Dinesh Manocha,et al.  Faster Sample-Based Motion Planning Using Instance-Based Learning , 2012, WAFR.

[35]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[36]  Nancy M. Amato,et al.  An obstacle-based rapidly-exploring random tree , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[37]  Wojciech Zaremba,et al.  Domain randomization for transferring deep neural networks from simulation to the real world , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[38]  Ross A. Knepper,et al.  Herb 2.0: Lessons Learned From Developing a Mobile Manipulator for the Home , 2012, Proceedings of the IEEE.

[39]  Lydia E. Kavraki,et al.  Using Local Experiences for Global Motion Planning , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[40]  Nancy M. Amato,et al.  MAPRM: a probabilistic roadmap planner with sampling on the medial axis of the free space , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[41]  Mark H. Overmars,et al.  Using Workspace Information as a Guide to Non-uniform Sampling in Probabilistic Roadmap Planners , 2005, Int. J. Robotics Res..

[42]  Marco Pavone,et al.  Deterministic Sampling-Based Motion Planning: Optimality, Complexity, and Performance , 2015, ISRR.

[43]  Nancy M. Amato,et al.  RESAMPL: A Region-Sensitive Adaptive Motion Planner , 2008, WAFR.