Intelligence without representation
Artificial Intelligence
Imitation Learning of an Intelligent Navigation System for Mobile Robots Using Reservoir Computing
SBRN '08 Proceedings of the 2008 10th Brazilian Symposium on Neural Networks
Robust Singular Spectrum Transform
IEA/AIE '09 Proceedings of the 22nd International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems: Next-Generation Applied Intelligence
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Correspondence Mapping Induced State and Action Metrics for Robotic Imitation
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
Internal representation is an important design decision in any imitation learning system. Actions and perceptual spaces were separate in classical AI due to the standard sense-process-act loop. Recently another representation that combines the two spaces into what we call a common sensorimotor space was inspired by the discovery of mirror neurons in animals and humans. The justification of this move is usually biological plausibility. This paper reports on a series of experiments comparing these two alternatives for self-initiated imitation tasks. The results of these experiments show that using a common sensorimotor representation allows the system to achieve higher accuracy and sensitivity. This is shown to be true (for our scenarios) even when the dimensionality of the common sensorimotor representation is higher than the dimensionality of the separate perceptual space. It also allows for an easier behavior generation mechanism and ensures reproducibility of learned behavior by the learner.