Extended Monte Carlo algorithm to collaborate distributed sensors for mobile robot localization

This paper presents a probabilistic algorithm to collaborate distributed sensors for mobile robot localization. During robot localization given a known environment model, Monte Carlo method is extended to integrate the detection information coming from environmental sensors to localize robot as long as the sensors do detect the robot. Meanwhile, we present an implementation that uses color environmental cameras for robot detection. All the parameters of each environmental camera are unknown in advance and can be calibrated by robot. Once cameras' calibrated, their detection models can be trained using sensor data according to their parameters. As a result, the robot's belief can reduce its uncertainty in response to the detection effectively. A further experiment, obtained with the real robot in an indoor office environment, illustrates that drastic improvement in localization speed and accuracy when compared to conventional robot localization.

[1]  Simon J. Godsill,et al.  On sequential simulation-based methods for Bayesian filtering , 1998 .

[2]  Wolfram Burgard,et al.  Monte Carlo Localization: Efficient Position Estimation for Mobile Robots , 1999, AAAI/IAAI.

[3]  Reid G. Simmons,et al.  Probabilistic Robot Navigation in Partially Observable Environments , 1995, IJCAI.

[4]  Leslie Pack Kaelbling,et al.  Acting under uncertainty: discrete Bayesian models for mobile-robot navigation , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[5]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[6]  R. Y. Tsai,et al.  An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision , 1986, CVPR 1986.

[7]  Daphne Koller,et al.  Using Learning for Approximation in Stochastic Processes , 1998, ICML.

[8]  Wolfram Burgard,et al.  Coastal navigation-mobile robot navigation with uncertainty in dynamic environments , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[9]  W. Burgard,et al.  Markov Localization for Mobile Robots in Dynamic Environments , 1999, J. Artif. Intell. Res..

[10]  D. Rubin.  Using the SIR algorithm to simulate posterior distributions , 1988 .

[11]  Wolfram Burgard,et al.  Robust Monte Carlo localization for mobile robots , 2001, Artif. Intell..

[12]  Wolfram Burgard,et al.  Estimating the Absolute Position of a Mobile Robot Using Position Probability Grids , 1996, AAAI/IAAI, Vol. 2.

[13]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[14]  Shigeyuki Sakane,et al.  Sensor planning for mobile robot localization using Bayesian network representation and inference , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Jun Ota,et al.  Self-calibration of environmental camera for mobile robot navigation , 2007, Robotics Auton. Syst..

[16]  Stuart J. Russell,et al.  Stochastic simulation algorithms for dynamic probabilistic networks , 1995, UAI.

[17]  Gaurav S. Sukhatme,et al.  Localization for mobile robot teams using maximum likelihood estimation , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  Eric P. Fox.  Bayesian Statistics 3 , 1991 .

[19]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[20]  Alan E. Gelfand,et al.  Bayesian statistics without tears: A sampling-resampling perspective , 1992 .