Automatic sensor configuration for task-directed planning

We consider the problem of planning the configuration of a sensor within the context of a robotic task. In this paper, we focus on geometrically specified tasks in the plane, and give algorithms for computing the regions from which an idealized point-and-shoot sensor can detect a polygonal robot. Our main algorithm allows sensor configurations from which the robot may be partially obstructed, and computes the regions from which the robot can be detected as it translates through the goal at a known orientation. This algorithm runs in time O(kmn/sup 3/(n+m)) for an environment of complexity n, a robot of complexity m, and a goal of complexity k. The regions constructed can be used by an active sensing system to configure sensors that are guaranteed to observe the robot as it enters the goal.<
>