Heuristic Search Assisted Active Localization for Mobile Robot
LIU Yanli1,2, FAN Xiaoping1, ZHANG Heng2
1. School of Information Science and Engineering, Central South University, Changsha 410075, China;
2. School of Information Engineering, East China Jiaotong University, Nanchang 330013, China
A heuristic search assisted active localization method is proposed. The algorithm clusters the particles by using adaptive particle clustering algorithm. Then, path planning trees and solution space trees are constructed respectively. Priories of all the nodes in the solution space trees are calculated according to the priority evaluation function, and the problem of path search is solved by the priority queue-type branch-and-bound method. Finally, a localizing accuracy active enhancing method is presented to solve the particle divergence problem in a single particle cluster. Simulation experiments validate the feasibility of the methods.
[1] Burgard W, Fox D, Thrun S. Active mobile robot localization[C]//15th International Joint Conference on Artificial Intelligence: Vol.2. San Francisco, CA, USA: Morgan Kaufmann Publishers, 1997: 1346-1352.
[2] Fox D, Burgard W, Thrun S. Active Markov localization for mobile robots[J]. Robotics and Autonomous Systems, 1998, 25(3/4): 195-207.
[3] Jensfelt P, Kristensen S. Active global localization for a mobile robot using multiple hypothesis tracking[J]. IEEE Transactions on Robotics and Automation, 2001, 17(5): 748-760.
[4] Zhou H J, Sakane S. Sensor planning for mobile robot localization based on probabilistic inference using Bayesian network[C]//IEEE International Symposium on Assembly and Task Planning. Piscataway, NJ, USA: IEEE, 2001: 7-12.
[5] Zhou H J, Sakane S. Sensor planning for mobile robot localization: A hierarchical approach using Bayesian network and particle filter[J]. IEEE Transactions on Robotics, 2008, 24(2): 481-487.
[6] Porta J M, Terwijin B, Krose B J A. Efficient entropy-based action selection for appearance-based robot localization[C]//20th IEEE International Conference on Robotics and Automation. Piscataway, NJ, USA: IEEE, 2003: 2842-2847.
[7] Porta J M, Verbeek J J, Krose B J A. Active appearance-based robot localization using stereo vision[J]. Autonomous Robots, 2005, 18(1): 59-80.
[8] Petillot Y, Maurelli F. A tree-based planner for active localization: Applications to autonomous underwater vehicles[C]// Proceedings of ELMAR 2010. Piscataway, NJ, USA: IEEE, 2010: 479-483.
[9] 刘志斌,石宗英,赵明国,等.基于环境势场的移动机器人主动定位[J]. 控制与决策,2008,23(2): 187-194. Liu Z B, Shi Z Y, Zhao M G, et al. Environment potential field assisted active localization for mobile robot[J]. Control and Decision, 2008, 23(2): 187-194.
[10] 黄庆成,罗荣华.一种多移动机器人主动协同定位方法的研究[J]. 电子学报,2010,38(11): 2644-2648. Huang Q C, Luo R H. An active cooperative localization method for mobile robots[J]. Acta Electronica Sinica, 2010, 38(11): 2644-2648.
[11] 张恒,樊晓平,瞿志华.基于多假设跟踪的移动机器人自适应蒙特卡罗定位研究[J]. 自动化学报,2007,33(9): 941-946. Zhang H, Fan X P, Qu Z H. Mobile robot adaptive Monte Carlo localization based on multiple hypothesis tracking[J]. Acta Automatica Sinica, 2007, 33(9): 941-946.