An ASSOM Neural Network to Represent Actions Performed by an Autonomous Agent

An ASSOM neural network to describe the action performed by an autonomous reactive agent is proposed. The neural network receives in input the sequences of data acquired by the agent internal sensors and it classifies them by generating the corresponding symbolic assertions. Experimental results performed on a RWI B12 autonomous robot are reported.

[1]  David Chapman,et al.  What are plans for? , 1990, Robotics Auton. Syst..

[2]  A. Chella,et al.  DAISY: a distributed architecture for intelligent system , 1997, Proceedings Fourth IEEE International Workshop on Computer Architecture for Machine Perception. CAMP'97.

[3]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[4]  Pattie Maes,et al.  Designing autonomous agents: Theory and practice from biology to engineering and back , 1990, Robotics Auton. Syst..

[5]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[6]  Salvatore Gaglio,et al.  A Cognitive Architecture for Artificial Vision , 1997, Artif. Intell..

[7]  C. Balkenius Natural intelligence in artificial creatures , 1995 .