No abstract

No abstract

Our robot ping-pong system attains good performance in a complex non-linear environment subject t o tight temporal constraints. We will show how the expert controller combines approximate estimates and feedback t o arrive a t a suitable task plan, emphasizing feasibility rather than strict optimality. We will discuss the characteristics of the expert controller t h a t cause it t o work, and their relationship t o other tasks.

A system for performing visual processing on gray-scale images in real time (60 Hz) has been constructed. The custom VLSI moment generator chip computes area, center of gravity, orientation, and size. An image preprocessor allows separate moments to be computed for separate regions. A standard set of buses allows new processing elements to be easily added. The system is expected to find application in real-time sensor-based electronic assembly and in automated inspection and registration tasks. A simple application to a real-time visually servoed robot task is summarized.

No abstract