Abstract
This chapter discusses the adaptive sensory-motor coordination through self-consistency. The human brain develops accurate sensory-motor coordination in the face of many unforeseen changes in the dimensions of the body, strength of the muscles, and placements of the sensory organs. This is accomplished for the most part without a teacher. The autonomous robots of the future will have to confront similar constraints if they are to be effective in uncertain environments. They will have to locate, reach, and pick up novel payloads all in real time and be expandable to accommodate many joints and sensors. They will have to learn and maintain accurate performance even after unpredictable changes are made in either the geometrical, mechanical, or sensing parameters or from internal parameter changes or damage. The chapter presents a theory and implementation that suggest how three types of adaptive sensory-motor co-ordinations might be learned and maintained by animals as well as robot controllers. They are (1) Locating stationary targets with movable sensors, (2) reaching arbitrarily positioned and oriented targets in 3D space with multi-joint arms, And (3) positioning an unforeseen payload with accurate and stable movements despite unknown sensor feedback delay. These three abilities can be tied together by focusing on the overall problem that a human faces in grabbing an object.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have