Balancing state-space coverage in planning with dynamics

Sampling-based kinodynamic planners, such as the popular RRT algorithm, have been proposed as promising solutions to planning for systems with dynamics. Nevertheless, complex systems often raise significant challenges. In particular, the state-space exploration of sampling-based tree planners can be heavily biased towards a specific direction due to the presence of dynamics and underactuation. The premise of this paper is that it is possible to use statistical tools to learn quickly the effects of the constraints in the algorithm's state-space exploration during a training session. Then during the online operation of the algorithm, this information can be utilized so as to counter the undesirable bias due to the dynamics by appropriately adapting the control propagation step. The resulting method achieves a more balanced exploration of the state-space, resulting in faster solutions to planning challenges. The paper provides proof of concept experiments comparing against and improving upon the standard RRT using MATLAB simulations for (a) swinging up different versions of a 3-link Acrobot system with dynamics and (b) a second-order car-like system with significant drift.

[1]  Gilles Blanchard,et al.  On the Convergence of Eigenspaces in Kernel Principal Component Analysis , 2005, NIPS.

[2]  Timothy Bretl,et al.  Using Motion Primitives in Probabilistic Sample-Based Planning for Humanoid Robots , 2008, WAFR.

[3]  Russ Tedrake,et al.  High-dimensional underactuated motion planning via task space control , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Lydia E. Kavraki,et al.  Motion planning for physical simulation , 2007 .

[5]  Tamim Asfour,et al.  An integrated approach to inverse kinematics and path planning for redundant manipulators , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[6]  Russ Tedrake,et al.  Path planning in 1000+ dimensions using a task-space Voronoi bias , 2009, 2009 IEEE International Conference on Robotics and Automation.

[7]  Ahmad A. Masoud,et al.  Kinodynamic Motion Planning , 2010, IEEE Robotics & Automation Magazine.

[8]  Lydia E. Kavraki,et al.  A dimensionality reduction approach to modeling protein flexibility , 2002, RECOMB '02.

[9]  R. Murray,et al.  A Case Study in Approximate Linearization: The Acrobot Example , 2010 .

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

[11]  Mark W. Spong,et al.  Control of underactuated mechanical systems using switching and saturation , 1997 .

[12]  Mike Stilman,et al.  Task constrained motion planning in robot joint space , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[14]  Kamal K. Gupta,et al.  Path planning with general end-effector constraints: using task space to guide configuration space search , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Steven M. LaValle,et al.  Rapidly-Exploring Random Trees: Progress and Prospects , 2000 .

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

[17]  Siddhartha S. Srinivasa,et al.  BiSpace Planning: Concurrent Multi-Space Exploration , 2008, Robotics: Science and Systems.

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

[19]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[20]  Bruce Randall Donald,et al.  Provably good approximation algorithms for optimal kinodynamic planning for Cartesian robots and open-chain manipulators , 1995, Algorithmica.

[21]  John F. Canny,et al.  An exact algorithm for kinodynamic planning in the plane , 1990, SCG '90.

[22]  Florent Lamiraux,et al.  Kinodynamic motion planning: connecting exploration trees using trajectory optimization Methods , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[23]  Siddhartha S. Srinivasa,et al.  Manipulation planning on constraint manifolds , 2009, 2009 IEEE International Conference on Robotics and Automation.

[24]  Emilio Frazzoli,et al.  Improving the performance of sampling-based planners by using a symmetry-exploiting gap reduction algorithm , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[25]  J. Betts.  Survey of Numerical Methods for Trajectory Optimization , 1998 .

[26]  Mark W. Spong,et al.  Underactuated mechanical systems , 1998 .

[27]  Colm Ó'Dúnlaing,et al.  Motion planning with inertial constraints , 2015, Algorithmica.

[28]  Munther A. Dahleh,et al.  Maneuver-based motion planning for nonlinear systems with symmetries , 2005, IEEE Transactions on Robotics.

[29]  Lydia Tapia,et al.  Using Dimensionality Reduction to Better Capture RNA and Protein Folding Motions , 2008 .

[30]  John F. Canny,et al.  Time-optimal trajectories for a robot manipulator: a provably good approximation algorithm , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[31]  Steven Dubowsky,et al.  Global time optimal motions of robotic manipulators in the presence of obstacles , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[32]  John M. Hollerbach,et al.  Planning a minimum-time trajectories for robot arms , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[33]  Oliver Brock,et al.  Balancing exploration and exploitation in motion planning , 2008, 2008 IEEE International Conference on Robotics and Automation.

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

[35]  Frank L. Lewis,et al.  Optimal Control , 1986 .

[36]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[37]  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..

[38]  Lydia E. Kavraki,et al.  On the performance of random linear projections for sampling-based motion planning , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[39]  Siddhartha S. Srinivasa,et al.  Randomized path planning for redundant manipulators without inverse kinematics , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.