Path planning with target finding by single camera under map uncertainty

This paper presents a method of path planning for a mobile robot with a pan-tilt camera to find target objects under spatial uncertainties. The uncertainties of object poses are represented by probability distributions on both a geometric map and a grid map. A passability measure and a target visibility measure are defined based on these uncertainties in order to evaluate a path. Given an initial path, the proposed method optimizes it with respect to travel time, collision avoidance, and target finding using these measures. Experiments show the method has successfully refined the initial paths using these measures.