An Infant Development-inspired Approach to Robot Hand-eye Coordination

This paper presents a novel developmental learning approach for hand-eye coordination in an autonomous robotic system. Robotic hand-eye coordination plays an important role in dealing with realtime environments. Under the approach, infant developmental patterns are introduced to build our robot’s learning system. The method works by first constructing a brain-like computational structure to control the robot, and then by using infant behavioural patterns to build a hand-eye coordination learning algorithm. This work is supported by an experimental evaluation, which shows that the control system is implemented simply, and that the learning approach provides fast and incremental learning of behavioural competence.