Maintaining Coherent Perceptual Information Using Anchoring

The purpose of this paper is to address the problem of maintaining coherent perceptual information in a mobile robotic system working over extended periods of time, interacting with a user and using multiple sensing modalities to gather information about the environment and specific objects. We present a system which is able to use spatial and olfactory sensors to patrol a corridor and execute user requested tasks. To cope with perceptual maintenance we present an extension of the anchoring framework capable of maintaining the correspondence between sensor data and the symbolic descriptions referring to objects. It is also capable of tracking and acquiring information from observations derived from sensor-data as well as information from a priori symbolic concepts. The general system is described and an experimental validation on a mobile robot is presented.

[1]  Lars Karlsson,et al.  Conditional progressive planning under uncertainty , 2001, IJCAI.

[2]  Silvia Coradeschi,et al.  Improving Odour Analysis Through Human-Robot Cooperation , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[3]  Lars Karlsson,et al.  Conditional Progressive Planning: A Preliminary Report , 2001, SCAI.

[4]  Alessandro Saffiotti,et al.  Anchoring Symbols to Sensor Data: Preliminary Report , 2000, AAAI/IAAI.

[5]  Silvia Coradeschi,et al.  Perceptual anchoring via conceptual spaces , 2004, AAAI 2004.

[6]  Wendi Heinzelman,et al.  Sensor management , 2004 .

[7]  M. Kleinehagenbrock,et al.  Person tracking with a mobile robot based on multi-modal anchoring , 2002, Proceedings. 11th IEEE International Workshop on Robot and Human Interactive Communication.

[8]  G. Palm,et al.  Associating words to visually recognized objects ∗ , 2004 .

[9]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[10]  Alessandro Saffiotti,et al.  A Multivalued Logic Approach to Integrating Planning and Control , 1995, Artif. Intell..

[11]  Ning Xiong,et al.  Perception management: an emerging concept for information fusion , 2003, Inf. Fusion.

[12]  Wolfram Burgard,et al.  People Tracking with Mobile Robots Using Sample-Based Joint Probabilistic Data Association Filters , 2003, Int. J. Robotics Res..

[13]  Silvia Coradeschi,et al.  Forming Odour Categories Using an Electronic Nose , 2004, ECAI.