Experiments and Results in Multimodal, Distributed, Robotic Perception

Distributed architecture for cooperative perception processes is described. This is called henceforth a perception net (PN). The case of multiple, autonomous, mobile robots navigating with reference to the multi-form world-model is considered. Information sharing and communication issues are pointed out. Description of the experimental implementation made of two mobile platforms is accompanied with the demonstration of results, namely the maps, which have been obtained by fusing the measurements with the a priori knowledge within the logical framework of the PN. The application have been based on the QNX network with Ethernet links.

[1]  Piotr Skrzypczynski,et al.  Cooperative Perception and World-Model Maintenance in Mobile Navigation Tasks , 1998, DARS.

[2]  Sebastian Thrun,et al.  Learning Metric-Topological Maps for Indoor Mobile Robot Navigation , 1998, Artif. Intell..

[3]  Tom Henderson,et al.  Logical sensor systems , 1984, J. Field Robotics.

[4]  Tim C. Lueth,et al.  Decentralized control of distributed intelligent robots and subsystems , 1994 .

[5]  Ramesh C. Jain,et al.  Evidential reasoning for building environment maps , 1995, IEEE Trans. Syst. Man Cybern..

[6]  Alberto Elfes,et al.  Sonar-based real-world mapping and navigation , 1987, IEEE J. Robotics Autom..

[7]  Randall Davis,et al.  Frameworks for Cooperation in Distributed Problem Solving , 1988, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Ren C. Luo,et al.  Multisensor integration and fusion in intelligent systems , 1989, IEEE Trans. Syst. Man Cybern..

[9]  Sukhan Lee,et al.  Perception-net based geometric data fusion for state estimation and system self-calibration , 1997, Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97.