A fuzzy evaluation based approach was proposed to solve the exploring problem for autonomous robotic mapping in unknown environment to deal with the fuzziness and uncertainty of unknown environmental information. The approach classified the frontiers which were between the known and unknown areas of grid map according to their distance and feasibility, and then chose the points with higher priority as candidates. Distances between the candidate points and current position, information gains and localizability were evaluated in fuzzy rules. The selection of the next observing pose or a series of next poses in path was achieved in low computational cost with the fuzzy evaluation. Then the exploration was finished, and the grid map and the feature map were accurately constructed. Experimental results demonstrate that the approach can improve the efficiency of exploring and achieve high performance in real-time planning.
［1］ THRUN S. Robotic mapping: a survey. exploring artificial intelligence in the new millenium［M］. San Francisco: Morgan Kaufmann, 2002: 1-35.
［2］ ISIER V, KANNAN S, DANIILIDIS K. Local exploration: online algorithms and a probabilistic framework［C］//Proceedings of the 2003 IEEE International Conference on Roboticsand Automation. USA:IEEE, 2003:1913-1920.
［3］ YAMAUCHI B. A frontier-based approach for autonomous exploration［C］//Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and Automation. Monterey, CA: IEEE, 1997: 146-151.
［4］ TOVAR B, MURRIETA-CID R, ESTEVES C. Robot motion planning for map building［C］//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.Lausanne, Switzerland: IEEE, 2002:673-680.
［5］ FREDA L, ORIOLO G. Frontier-based probabilistic strategies for sensor-based exploration［C］//Proceedings of the 2005 IEEE International Conference on Robotics and Automation. Barcelona, Spain: IEEE, 2005: 2892-3898.
［6］ GONZLEZ-BAOS H, EFRAT A, LATOMBE J C, et al. Planning robot motion strategies for efficient model construction ［C］// The 9th International Symposium on RoboticsResearch. Salt Lake City, UT: Springer-Verlag, 1999: 345-352.
［7］ GONZLEZ-BAOS H H, LATOMBE J C. Navigation strategies for exploring indoor environments ［J］. International Journal of Robotics Research, 2002, 21(10): 829-848.
［8］ MAKARENKO A A, WILLIAMS S B, BOURGAULT F, et al. An experiment in integrated exploration［C］//Proceedings of IEEE/RSJ International Conference on Intelligent Robots andSystems. Lausanne, Switzerland: IEEE, 2002: 534-539.
［9］ 张恒,樊晓平.移动机器人同步定位与地图构建过程中的轨迹规划研究［J］.机器人,2006,28(3):285-290.
ZHANG Heng, FAN Xiao-ping. Mobile robot trajectory planning in simultaneous localization and mapping problem ［J］.Robot, 2006, 28(3): 285-290.
［10］ MACKAY D. Bayesian methods for adaptive models ［D］. Pasadena: California Institute of Technology, 1991.
［11］ 周光明,贾梦雷,陈宗海.移动机器人未知环境自主探测的一种高效算法［J］.上海交通大学学报,2005,39(6): 936-940.
ZHOU Guang-ming, JIA Meng-lei, CHEN Zong-hai. An efficient algorithm for mobile robot’s autonomous exploration in unknown environments ［J］.Journal of Shanghai JiaotongUniversity, 2005, 39(6): 936-940.
［12］ STACHNISS C, GRISETTI G, BURGARD W. Information gain-based exploration using rao-blackwellized particle filters［C］// Proceedings of Robotics: Science and Systems.Cambridge, UK: ［s.n.］,2005: 65-72.
［13］ 熊蓉,褚健,吴俊.基于点线相合的机器人增量式地图构建［J］.控制理论与应用,2007,24(2):170-176.
XIONG Rong, CHU Jian, WU Jun. Incremental mapping based on dot-line congruence for robot［J］.Control Theory and Applications, 2007,24(2):170-176.
［14］ DECHTER R, PEARL J. Generalized best-first search strategies and the optimality of A*［J］. Journal of the ACM, 1985, 32(3): 505-536.
