Multiple paired forward and inverse models for motor control
Neural Networks - Special issue on neural control and robotics: biology and technology
MOSAIC Model for Sensorimotor Learning and Control
Neural Computation
| Hi-index | 0.00 |
In the spirit of the conference theme, the interplay between autonomy and intelligence, the general direction of this paper is to describe how autonomous robots could begin to autonomously develop intelligence. (For us a robot is always a constructed, embodied, situated system.) Most of the discussion will take place at the abstract level of system architecture and design principles. For the sake of discussion we assume that the robots under consideration have a reactive or behavior-based system as part of their architecture. This is reasonable since it is true of a high proportion of autonomous robots built today.