Universal autonomous robot navigation using quasi optimal path generation

Autonomous robot navigation is an important research field because these robots can solve problems where the human presence is impossible, dangerous, expensive, or uncomfortable. In this paper, a new hybrid autonomous navigation method is introduced. The algorithm is composed of visibility graph based global navigation and simple potential field based local navigation parts. It applies a new automated graph generation method which may become necessary if, because of the observed new obstacles, a new path should be generated. The quasi optimal route is found by applying the well known A* algorithm on the graph. The presented technique offers a quasi optimal universal navigation technique which can successfully be used in all, known, unknown, and dynamically changing environments.

[1]  Peter Korondi,et al.  Virtual Training of Vector Function based Guiding Styles , 2001 .

[2]  F. Frances Yao,et al.  Optimal binary space partitions for orthogonal objects , 1990, SODA '90.

[3]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[4]  Jean-Claude Latombe,et al.  Robot motion planning , 1991, The Kluwer international series in engineering and computer science.

[5]  Annamária R. Várkonyi-Kóczy,et al.  3-Dimensional Potential Based Guiding , 2000 .

[6]  John Canny,et al.  The complexity of robot motion planning , 1988 .

[7]  Trent M. Hare,et al.  The Mars Pathfinder , 1998 .

[8]  Tomás Lozano-Pérez,et al.  An algorithm for planning collision-free paths among polyhedral obstacles , 1979, CACM.

[9]  Oussama Khatib,et al.  Real-Time Obstacle Avoidance for Manipulators and Mobile Robots , 1986 .

[10]  Ming C. Lin,et al.  An opportunistic global path planner , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[11]  Daniel E. Koditschek,et al.  Exact robot navigation using artificial potential functions , 1992, IEEE Trans. Robotics Autom..

[12]  Rina Dechter,et al.  Generalized best-first search strategies and the optimality of A* , 1985, JACM.

[13]  Yoram Koren,et al.  Potential field methods and their inherent limitations for mobile robot navigation , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[14]  Anthony Stentz,et al.  Optimal and efficient path planning for partially-known environments , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[15]  Paolo Fiorini,et al.  Motion Planning in Dynamic Environments Using Velocity Obstacles , 1998, Int. J. Robotics Res..