Search and Rescue Robot Path Planning in Unknown Environment

Abstract:

For the path planning problem of search and rescue robot in unknown environment, a bionic learning algorithm was proposed. The GSOM (Growing Self-organizing Map) algorithm was used to build the environment cognitive map. The heuristic search A* algorithm was used to find the global optimal path from initial state to target state. When the local environment was changed, reinforcement learning algorithm based on sensor information was used to guide the search and rescue robot behavior of local path planning. Simulation results show the method effectiveness.

• Periodical: Applied Mechanics and Materials (Volumes 241-244)
• Pages: 1682-1687
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.241-244.1682
• Online since: December 2012
• Authors: Tao Pang, Xiao Gang Ruan, Er Shen Wang, Rui Yuan Fan
• Keywords: Autonomous Exploration, Cognitive Map, Path Planning, Search and Rescue Robot

References

[1] Perez, Automatic Planning of Manipulator Movements. IEEE trans on Sys Man and Cyb, Vol.11(11), (1981), pp.681-698.

DOI: 10.1109/tsmc.1981.4308589

[2] Yoram K, Johann B. Potential Field Methods and Their Inherent Limitations for Mobile Robot Navigation. Proc IEEE Int Conf Robot Automation, California, (1991), pp.1398-1404.

DOI: 10.1109/robot.1991.131810

[3] Weber H. Automation Planning and Execution System for Mobile Robots Driven by Stepping Motors. Robotics and Autonomous System. Vol. 33(4), (2000), pp.207-221.

DOI: 10.1016/s0921-8890(00)00097-x

[4] Quoy M, Gaussier P, Lepretre S, A planning map for mobile robots: Speed control and paths finding in a changing environment[C], Proceedings of 8th European Workshop on Learning Robots: Lausanne, SL: SPR, Vol. 1812. (2000), pp.103-119.

DOI: 10.1007/3-540-40044-3_7

[5] Cuperlier N, Quoy M, Gaussier P. Neurobiologically inspired mobile robot navigation and planning. Frontiers in NeuroRobotics, Vol. 1(1), (2007).

DOI: 10.3389/neuro.12.003.2007

[6] Kawewong A, Honda Y, Tsuboyama M. A Common-Neural-Pattern Based Reasoning for Mobile Robot Cognitive Mapping [C], Proceedings of the 15th International Conference on Neuro-Information, Auckland, NZ: IEEE,Vol. 5506, (2009), pp.32-39.

DOI: 10.1007/978-3-642-02490-0_4

[7] Fritzke B. Growing cell structures a self-organizing network for unsupervised and supervised learning[J]. Neural Networks, Vol 7(9), (1994), pp.1411-1460.

DOI: 10.1016/0893-6080(94)90091-4

[8] Quoy M, Gaussier P, Lepretre, S. A planning map for mobile robots: Speed control and paths finding in a changing environment. Proceedings of 8th European Workshop on Learning Robots, Lausanne, Switzerland, Vol 1812, (2000), pp.103-119.

DOI: 10.1007/3-540-40044-3_7

[9] Duguleana Mihai,Barbuceanu Florin Grigore, Teirelbar Ahmed. Obstacle Avoidance of Redundant Manipulators Using Neural Networks Based Reinforcement Learning[J]. Robotics and Computer Integrated Manufacturing, Vol. 28(2), (2012), pp.132-146.

DOI: 10.1016/j.rcim.2011.07.004

[10] Conforth M, Meng Y. Reinforcement Learning Using Swarm Intelligence-trained Neural Networks [J]. Journal of Experimental & Theoretical Artificial Intelligence, Vol. 22(3), (2012), pp.197-218.

DOI: 10.1080/09528130903065497

[11] Arleo A, Smeraldi F, Gerstner W. Cognitive navigation based on non-uniform gabor space sampling unsupervised growing networks and reinforcement learning[J]. IEEE Transactions on Neural Networks, Vol. 15(3), (2004), pp.639-652.

DOI: 10.1109/tnn.2004.826221