A Robot-Task Planner for Mobile Robots

Abstract To be both realistic and efficient a planning method must take into account several aspects of robotics applications such as sensory and command uncertainties, relationship between planning and execution control and complexity of the robot control. The planner described in this paper deals with these aspects and proposes solutions based on efficient concepts such as the Robot-Task and Task Function concepts. It also aims at introducing the new concept of Local Map that allows to both simplify the matching phasis of the robot localization and to enhance the robustness of the tracking. Special effort is made to provide results so that execution control can be simple at observation level and safe at action level.

[1]  Claude Samson,et al.  Robot Control: The Task Function Approach , 1991 .

[2]  I. Collin,et al.  Local map design and task function planning for mobile robots , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[3]  Jean-Claude Latombe,et al.  Robot motion planning , 1970, The Kluwer international series in engineering and computer science.

[4]  Gérard Govaert,et al.  Binary clustering with missing data , 1993 .

[5]  Fumio Miyazaki,et al.  A stable tracking control method for a non-holonomic mobile robot , 1991, Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91.

[6]  Éric Rutten,et al.  A task-level robot programming language and its reactive execution , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[7]  Russell H. Taylor,et al.  Automatic Synthesis of Fine-Motion Strategies for Robots , 1984 .

[8]  S. N. Gottschlich,et al.  AMP-CAD: an assembly motion planning system , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.