Self-Taught Visually-Guided Pointing for a Humanoid Robot

摘要

The authors implemented a system which performs a fundamental visuomotor coordination task on the humanoid robot Cog. Cog's task was to saccade its pair of two degree-of-freedom eyes to foveate on a target, and then to maneuver its six degree-of-freedom compliant arm to point at that target. This task requires systems for learning to saccade to visual targets, generating smooth arm trajectories, locating the arm in the visual field, and learning the map between gaze direction and correct pointing configuration of the arm. All learning was self-supervised solely by visual feedback. The task was accomplished by many parallel processes running on a seven processor, extensible architecture, MIMD computer.