engleski

Autonomous robot learning model based on visual interpretation of spatial structures

The main concept of the presented research is an autonomous robot learning model for which a novel ARTgrid neural network architecture for classification of spatial structures is utilized. The motivation scenario includes incremental unsupervised learning which is mainly based on discrete spatial structure changes recognized by the robot vision system. The learning policy problem is represented as a classification problem for which the adaptive resonance theory (ART) concept is implemented. Main methodology and architecture of the autonomous robot learning model with preliminary results is presented. A computer simulation was performed with four input sets set containing 22, 45, 73 and 111 random spatial structures. ARTgrid shows a fairly high (>85%) match score when applied with already learned patterns after the first learning cycle, and a score >95% after the second cycle. Regarding category proliferation the results are compared with a more predictive modified cluster centre seeking algorithm.

Autonomous systems; Machine learning; Adaptive Resonance Theory

nije evidentirano