Self-adaptive Pose-tracking Algorithm for Mobile Robots in Dynamic and Highly-occluded Environments
WANG Yong1,2, CHEN Weidong1,2, WANG Jingchuan1,2, XIAO Peng3
1. Key Laboratory of System Control and Information Processing, Ministry of Education of China, Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China;
2. State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, China;
3. Electric Power Research Institute, State Grid Shandong Electric Power Company, Jinan 250002, China
In dynamic and highly-occluded environments such as a cafeteria, metro station etc. the pose-tracking accuracy of mobile robots will be greatly influenced since the occlusion degree and map features are different. To solve this problem, a self-adaptive pose-tracking algorithm is proposed. The main idea is to ensure the accurate and robust robot localization through correcting the odometer-based proposal distribution function (PDF) in particle filter (PF) based on the localizability, which is defined to evaluate the influences of both the dynamic obstacles and prior-map (different structures and uncertainty) on localization. Furthermore, to guarantee the robustness in different dynamic and highly-occluded environments, the reliability parameter between the observations of laser range-finder (LRF) and the measurements of odometer in fusion process is improved. The simulation and experimental results demonstrate that the improved reliability parameter is valid, and the proposed algorithm is accurate and robust for pose-tracking in dynamic and highly-occluded environments.
 Wang Y, Chen W D. Hybrid map-based navigation for intelligent wheelchair[C]//IEEE International Conference on Robot- ics and Automation. Piscataway, USA: IEEE, 2011: 637-642. Weiss G, Wetzler C, von Puttkamer E. Keeping track of position and orientation of moving indoor systems by correlation of range-finder scans[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 1994: 595-601. Gutmann J S, Burgard W, Fox D, et al. An experimental comparison of localization methods[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 1998: 736-743. Fox D, Burgard W, Dellaert F, et al. Monte Carlo localization: Efficient position estimation for mobile robots[C]//16th National Conference on Artificial Intelligence. Menlo Park,USA: AAAI, 1999: 343-349. Thrun S, Burgard W, Fox D. Probabilistic robotics[M]. Cambridge, USA: MIT Press, 2005. Lee J S, Chung W K. Robust mobile robot localization in highly non-static environments[J]. Autonomous Robots, 2010, 29(1): 1-16.  Simmons R, Goldberg D, Goode A, et al. Grace: An autonomous robot for the AAAI robot challenge[J]. AI Magazine, 2003, 24(2): 51-72. Sun Z L, van de Ven D, Ramos F, et al. Inferring laser-scan matching uncertainty with conditional random fields[J]. Robotics and Autonomous Systems, 2012, 60(1): 83-94.  Holz D, Behnke S. Sancta Simplicitas-On the efficiency and achievable results of SLAM using ICP-based incremental registration[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2010: 1380-1387. Roumeliotis S I, Bekey G A. Bayesian estimation and Kalman filtering: A unified framework for mobile robot localization[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2000: 2985-2992. van der Merwe R, Doucet A, de Freitas N, et al. The unscented particle filter[C]//13th Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 2000: 584-590. Jochmann G, Kerner S, Tasse S, et al. Efficient multi-hypotheses unscented Kalman filtering for robust localization[C]//RoboCup 2011: Robot Soccer World Cup XV. Berlin, Germany: Springer-Verlag, 2012: 222-233. Ko S I, Choi J S. Indoor mobile localization system using UKF and pre-filtering[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2007: 2865-2870. 王炜,陈卫东,王勇.基于概率栅格地图的移动机器人可定位性估计[J].机器人,2012,34(4):485-491,512.Wang W, Chen W D, Wang Y. Probabilistic grid map based localizability estimation for mobile robots[J]. Robot, 2012, 34(4): 485-491,512. Wang Y, Chen W D, Wang J C, et al. Action selection based on localizability for active global localization of mobile robots[C]//IEEE International Conference on Mechatronics and Automation. Piscataway, USA: IEEE, 2012: 2071-2076. 王勇,陈卫东,王景川,等.面向拥挤环境的移动机器人改进粒子滤波定位[J].机器人,2012,34(5):596-603.Wang Y, Chen W D, Wang J C, et al. Improved particle filter localization in crowded environments for mobile robots[J]. Robot, 2012, 34(5): 596-603. Roy N, Burgard W, Fox D, et al. Coastal navigation-Robot motion with uncertainty[C]//AAAI Fall Symposium Series-Planning with Partially Observable Markov Decision Processes (POMDPs): Working Notes. Menlo Park, USA: AAAI, 1998: 135-140. 王卫华,陈卫东,席裕庚.移动机器人地图创建中的不确定传感信息处理[J].自动化学报,2003,29(2):267-274.Wang W H, Chen W D, Xi Y G. Uncertainty sensor information processing in map building of mobile robot[J]. Acta Automatica Sinica, 2003, 29(2): 267-274. Censi A. On achievable accuracy for range-finder localization[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2007: 4170-4175. Antonelli G, Chiaverini S, Fusco G. A calibration method for odometry of mobile robots based on the least-squares technique: Theory and experimental validation[J]. IEEE Transactions on Robotics, 2005, 21(5): 994-1004.  Willner D, Chang C B, Dunn K P. Kalman filter algorithms for a multi-sensor system[C]//IEEE Conference on Decision and Control. Piscataway, USA: IEEE, 1976: 570-574. Kleeman L. Advanced sonar and odometry error modeling for simultaneous localisation and map building[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2003: 699-704. Wolf J, Burgard W, Burkhardt H. Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization[J]. IEEE Transactions on Robotics, 2005, 21(2): 208-216.  He T, Hirose S. Observation-driven Bayesian filtering for global location estimation in the field area[J]. Journal of Field Robot- ics, 2013, 30(4): 489-518.