An approach to restaurant service robot SLAM

Recently service robots are becoming a part of our daily life. There is a huge market for robot since many human friendly service robots are designed. In this paper we describe a system of Simultaneous Localization and Mapping(SLAM) on restaurant service robot using a depth camera and a move base with odometry and gyro. We create a virtual laser scan from the depth camera, which provides depth image to be converted into 2D laser scan. Meanwhile, the color image provided by the depth camera could be used to extract feature descriptions which will be used in the loop closure process. The depth camera act as a low cost laser scanner and a RGB camera in this case. Our method is under particle filter frame. The robot builds map incrementally when exploring new environment. This make it can accurately locate itself in the working environment and complete routine navigation tasks autonomously. We will introduce the fundamental mathematical model and conduct experiments to show it.

[1]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[2]  Kevin P. Murphy,et al.  Bayesian Map Learning in Dynamic Environments , 1999, NIPS.

[3]  Wolfram Burgard,et al.  An efficient fastSLAM algorithm for generating maps of large-scale cyclic environments from raw laser range measurements , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[4]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[5]  Peter Cheeseman,et al.  On the Representation and Estimation of Spatial Uncertainty , 1986 .

[6]  Sebastian Thrun,et al.  FastSLAM 2.0: An Improved Particle Filtering Algorithm for Simultaneous Localization and Mapping that Provably Converges , 2003, IJCAI.

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

[8]  Kurt Konolige,et al.  Incremental mapping of large cyclic environments , 1999, Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375).

[9]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[10]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[11]  Nando de Freitas,et al.  Real-Time Monitoring of Complex Industrial Processes with Particle Filters , 2002, NIPS.

[12]  P. Moral.  Nonlinear filtering : Interacting particle resolution , 1997 .

[13]  Hugh F. Durrant-Whyte,et al.  A computationally efficient solution to the simultaneous localisation and map building (SLAM) problem , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[14]  Timothy J. Robinson,et al.  Sequential Monte Carlo Methods in Practice , 2003 .

[15]  R. E. Kalman,et al.  New Results in Linear Filtering and Prediction Theory , 1961 .

[16]  R. E. Kalman,et al.  Contributions to the Theory of Optimal Control , 1960 .

[17]  Hans P. Moravec.  Sensor Fusion in Certainty Grids for Mobile Robots , 1988, AI Mag..

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

[19]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[20]  Eric Moulines,et al.  Comparison of resampling schemes for particle filtering , 2005, ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005..