Transformational planning for mobile manipulation based on action-related places

Opportunities for interleaving or parallelizing actions are abundant in everyday activities. Being able to perceive, predict and exploit such opportunities leads to more efficient and robust behavior. In this paper, we present a mobile manipulation platform that exploits such opportunities to optimize its behavior, e.g. grasping two objects from one location simultaneously, rather than navigating to two different locations. To do so, it uses a general least-commitment representation of place, called ARPLACE, from which manipulation is predicted to be successful. Models for ARPLACEs are learned from experience using Support Vector Machines and Point Distribution Models, and take into account the robot's morphology and skill repertoire. We present a transformational planner that reasons about ARPLACEs, and applies transformation rules to its plans if more robust and efficient behavior is predicted.

[1]  Charles C. Kemp,et al.  Challenges for robot manipulation in human environments [Grand Challenges of Robotics] , 2007, IEEE Robotics & Automation Magazine.

[2]  Lydia E. Kavraki,et al.  Path planning using lazy PRM , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[3]  Chapter 5 Sampling-Based Motion Planning , 2006 .

[4]  Stephen Hart,et al.  A Framework for Learning Declarative Structure , 2006 .

[5]  Drew McDermott,et al.  A reactive plan language , 1991 .

[6]  E. Torres-Jara,et al.  Challenges for Robot Manipulation in Human Environments , 2006 .

[7]  Dmitry Berenson,et al.  An optimization approach to planning for mobile manipulation , 2008, 2008 IEEE International Conference on Robotics and Automation.

[8]  Michael Beetz,et al.  3D model selection from an internet database for robotic vision , 2009, 2009 IEEE International Conference on Robotics and Automation.

[9]  Marc Friedman,et al.  Least-Commitment Action Selection , 1996, AIPS.

[10]  Gunnar Rätsch,et al.  Large Scale Multiple Kernel Learning , 2006, J. Mach. Learn. Res..

[11]  Richard T. Vaughan,et al.  The Player/Stage Project: Tools for Multi-Robot and Distributed Sensor Systems , 2003 .

[12]  Michael Beetz,et al.  Refining the Execution of Abstract Actions with Learned Action Models , 2008, J. Artif. Intell. Res..

[13]  Michael Beetz,et al.  Positioning mobile manipulators to perform constrained linear trajectories , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Alcherio Martinoli,et al.  A quantitative method for comparing trajectories of mobile robots using point distribution models , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Michael Beetz,et al.  Transformational Planning for Everyday Activity , 2007, ICAPS.

[16]  Michael Beetz,et al.  Declarative goals in reactive plans , 1992 .

[17]  Michael Beetz.  Structured Reactive Controllers , 2004, Autonomous Agents and Multi-Agent Systems.

[18]  Jun Nakanishi,et al.  Movement imitation with nonlinear dynamical systems in humanoid robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[19]  Gerald J. Sussman,et al.  A Computational Model of Skill Acquisition , 1973 .

[20]  Drew McDermott,et al.  An Algorithm for Probabilistic, Totally-Ordered Temporal Projection , 1994 .