A study of autonomous robot behavior using the LAPART neural architecture

Presents an experimental study on the effects of sensorial representations, sensor fusion, control arbitration, and environmental configurations on the learning of a coupled simulated/physical robotic system using the LAPART-2 neural architecture.

[1]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[2]  Thomas P. Caudell,et al.  Acquiring rule sets as a product of learning in a logical neural architecture , 1997, IEEE Trans. Neural Networks.

[3]  Thomas P. Caudell,et al.  Architecture as it controls a simulated autonomous vehicle , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[4]  T. P. Caudell,et al.  Studies of inference rule creation using LAPART , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[5]  Thomas P. Caudell,et al.  A neural architecture for pattern sequence verification through inferencing , 1993, IEEE Trans. Neural Networks.

[6]  Michael J. Healy.  A Topological Semantics for Rule Extraction with Neural Networks , 1999, Connect. Sci..

[7]  Thomas P. Caudell,et al.  Studies of generalization for the LAPART-2 architecture , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[8]  Thomas P. Caudell,et al.  Guaranteed two-pass convergence for supervised and inferential learning , 1998, IEEE Trans. Neural Networks.