A model for visual observation under uncertainty

The problem of observing a moving agent is addressed. A modeling approach for the visual system and its observer is advocated in which a discrete-event dynamic system (DEDS) framework is developed and events are defined as ranges on parameter subsets. In particular, a system for observing a process in which a robot hand manipulates an object is proposed. A stabilizing observer is constructed, and low-level modules are developed for recognizing the events that cause state transitions within the dynamic manipulation system. The work examines closely the possibilities for errors and uncertainties in the manipulation system, observer construction process, and event identification mechanisms. The system utilizes different tracking techniques to observe and recognize the task in an active, adaptive, and goal-directed manner