Abstract：A new data fusion method to extract features from the local environment for mobile robot has been developed and implemented. This method, named the group of obstacles, compresses data in a series of levels in order to reduce data quantity for communication between modules in distributed single-robot system, or between all the robots and the central station in multi-robot system. This method based on gird map and active window has strong adaptability and real-time in crowded environment. Enormous simulative and physical experiments are carried out to cope with dynamic environments. Experimental results demonstrate that robot can successfully avoid collision and plan path by using this method in perception of robot.
[1] Cho D W. Certainty grid representation for robot navigation by Bayesian method[J].Robotica, 1990,8:159-165. [2] Weigl M, Siemiatkowska B, Sikorski K A, Borkowski A. grid-based mapping for autonomous mobile robot[J].Robotics and Autonomous Systems,1993,11:13-21. [3] Daniel Pagac, Eduardo M Nebot, Hugh Durrant-Whyte. An evidential approach to map-building for autonomous vehicles[J].IEEE trans on Robotics and Automation, 1998,14(4):623-629. [4] Ram A, Arkin R C, Moorman K, Clark R J. Case-based reactive navigation:A method for on-line selection and adaptation of reactive robotic control parameters[J].IEEE trans on SMC-PART B:CYBERNETICS, 1997,27(3):376-393. [5] Borenstein J, Koren Y. Histogramtic in-motion mapping for mobile robot obstacle avoidance[J].IEEE trans. on Robotics and Automation, 1991,7(4):535-539. [6] Borenstein J, Koren Y. The vector field histogram-fast obstacle avoidance for mobile Robots[J].IEEE trans on Robotics and Automation, 1991,7(3):278-288. [7] Borenstein J, Koren Y. Real-time obstacle avoidance for fast mobile robots[J].IEEE trans on SMC, 1989,19(5):1179-1187
