Robot Motion Planning with Dynamics as Hybrid Search

This paper presents a framework for motion planning with dynamics as hybrid search over the continuous space of feasible motions and the discrete space of a low-dimensional workspace decomposition. Each step of the hybrid search consists of expanding a frontier of regions in the discrete space using cost heuristics as guide followed by sampling-based motion planning to expand a tree of feasible motions in the continuous space to reach the frontier. The approach is geared towards robots with many degrees-of-freedom (DOFs), nonlinear dynamics, and nonholonomic constraints, which make it difficult to follow discrete-search paths to the goal, and hence require a tight coupling of motion planning and discrete search. Comparisons to related work show significant computational speedups.

[1]  Jean-Paul Laumond,et al.  Control of Probabilistic Diffusion in Motion Planning , 2008, WAFR.

[2]  Siddhartha S. Srinivasa,et al.  Manipulation planning with Workspace Goal Regions , 2009, 2009 IEEE International Conference on Robotics and Automation.

[3]  Anthony Stentz,et al.  R* Search , 2008, AAAI.

[4]  Matthew R. Walter,et al.  Reachability-guided sampling for planning under differential constraints , 2009, 2009 IEEE International Conference on Robotics and Automation.

[5]  Jonathan Richard Shewchuk,et al.  Delaunay refinement algorithms for triangular mesh generation , 2002, Comput. Geom..

[6]  John Langford,et al.  Cover trees for nearest neighbor , 2006, ICML.

[7]  Lydia E. Kavraki,et al.  A Sampling-Based Tree Planner for Systems With Complex Dynamics , 2012, IEEE Transactions on Robotics.

[8]  Steven M. LaValle,et al.  Motion Planning Part I: The Essentials , 2011 .

[9]  Lydia E. Kavraki,et al.  Motion Planning With Dynamics by a Synergistic Combination of Layers of Planning , 2010, IEEE Transactions on Robotics.

[10]  Maxim Likhachev,et al.  Planning with adaptive dimensionality for mobile manipulation , 2012, 2012 IEEE International Conference on Robotics and Automation.

[11]  Howie Choset,et al.  Principles of Robot Motion: Theory, Algorithms, and Implementation ERRATA!!!! 1 , 2007 .

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

[13]  Thierry Siméon,et al.  Transition-based RRT for path planning in continuous cost spaces , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Lydia E. Kavraki,et al.  Motion Planning in the Presence of Drift, Underactuation and Discrete System Changes , 2005, Robotics: Science and Systems.

[15]  Emilio Frazzoli,et al.  Optimal kinodynamic motion planning using incremental sampling-based methods , 2010, 49th IEEE Conference on Decision and Control (CDC).

[16]  Steven M. LaValle,et al.  Randomized Kinodynamic Planning , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[17]  Kostas E. Bekris,et al.  Learning approximate cost-to-go metrics to improve sampling-based motion planning , 2011, 2011 IEEE International Conference on Robotics and Automation.

[18]  Mark de Berg,et al.  Computational geometry: algorithms and applications , 1997 .

[19]  Steven M. LaValle,et al.  Motion Planning : The Essentials , 2011 .

[20]  Erion Plaku,et al.  Guiding Sampling-Based Motion Planning by Forward and Backward Discrete Search , 2012, ICIRA.

[21]  Wheeler Ruml,et al.  Abstraction-Guided Sampling for Motion Planning , 2012, SOCS.

[22]  Jean-Claude Latombe,et al.  Randomized Kinodynamic Motion Planning with Moving Obstacles , 2002, Int. J. Robotics Res..