Robust controller design for active vision systems

Recent hardware developments have rendered controlled active vision a viable option for a broad range of problems, spanning applications as diverse as intelligent vehicle highway systems, MEMS microassembly and assisting individuals with disabilities. However, realizing this potential requires having a framework for synthesizing robust active vision systems, capable of moving beyond carefully controlled environments. In this paper we show how recently developed robust identification and control synthesis techniques can be brought to bear on the problem. These results are experimentally validated using a Bisight robotic head