Place Learning in Dynamic Real-World Environments

In this paper, we present an approach for mobile robot localization designed for use in dynamic environments. Our approach integrates evidence grids within a topo-logical/metric network that can be used for navigation. Place learning consists of associating evidence grids with places in the topological network. Place recognition consists of building an evidence grid at the current location and using a registration procedure based on hill climbing to nd the best match between the current grid and the grids associated with places in the network. This approach has been implemented on a real mobile robot and has been tested in a real-world ooce environment containing multiple forms of dynamic change. In these experiments, this approach demonstrated robust localization in the presence of transient changes (such as moving people) and lasting changes (such as rearranged furniture) in the environment.

[1]  Randall D. Beer,et al.  Spatial learning for navigation in dynamic environments , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[2]  Hans P. Moravec,et al.  High resolution maps from wide angle sonar , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[3]  Brian Yamauchi.  Mobile robot localization in dynamic environments using dead reckoning and evidence grids , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[4]  Roland Siegwart,et al.  Mobile Robot Localization , 2011 .

[5]  Kurt Konolige.  A Refined Method for Occupancy Grid Interpretation , 1995, Reasoning with Uncertainty in Robotics.

[6]  Pat Langley,et al.  Case-Based Acquisition of Place Knowledge , 1995, ICML.

[7]  David Kortenkamp,et al.  Cognitive maps for mobile robots: A representation for mapping and navigation , 1993 .

[8]  Bernt Schiele,et al.  A comparison of position estimation techniques using occupancy grids , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

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

[10]  Benjamin Kuipers,et al.  A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations , 1991, Robotics Auton. Syst..

[11]  S. Engelson.  Passive map learning and visual place recognition , 1994 .

[12]  Alan C. Schultz,et al.  Continuous localization using evidence grids , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[13]  Russell Greiner,et al.  Learning to Select Useful Landmarks , 1994, AAAI.