Exploiting visual constraints in robot motion planning

Abstract

A number of issues concerning the integration of visual and physical constraints for the synthesis and execution of error-tolerant motion strategies are addressed. Object features and their projections onto the image plane of a supervisory camera are used to define visual constraint surfaces. These surfaces can be directly used to enforce the following types of constrained motion: motion terminated on contact with a visual constraint surface, motion maintaining constant contact with a visual constraint surface, and motion that is simultaneously constrained by both visual and physical constraint surfaces. Preimage planning techniques are extended to the synthesis of motion strategies that exploit these types of motion.