Robot competence development by constructive learning
Qinggang Meng
Mark H. Lee
Christopher Hinde
2134/26532
https://repository.lboro.ac.uk/articles/chapter/Robot_competence_development_by_constructive_learning/9400910
This paper presents a constructive learning approach for developing sensor-motor mapping in autonomous systems. The system's adaptation to environment changes is discussed and three methods are proposed to deal with long term and short term changes. The proposed constructive learning allows autonomous systems to develop network topology and adjust network parameters. The approach is supported by findings from psychology and neuroscience especially during infants cognitive development at early stages. A growing radial basis function network is introduced as a computational substrate for sensory-motor mapping learning. Experiments are conducted on a robot eye/hand coordination testbed and results show the incremental development of sensory-motor mapping and its adaptation to changes such as in tool-use.
2017-09-18 16:14:00
untagged
Information and Computing Sciences not elsewhere classified