A method of planning movement and observation for a mobile robot considering uncertainties of movement, visual sensing, and a map

We present a method of route selection for a vision guided mobile robot wit h an odometry system, given an uncertain map. The robot first generates can didates of the routes, which are expanded to possible loci in consideration of the map uncertainty. It then makes an observation and movement plan alo ng each locus and computes the minimum traveling time. Uncertainties of mov ement and visual sensing are considered in this step. Finally, for each can didate route, the robot computes its expected traveling time from probabili ties of loci. It selects the route with the least expected traveling time a s the optimal route. The advantage of the planning method is that the obser vation and movement planning are incorporated in path planning to obtain th e optimal plan. The three sources of uncertainty are considered in a unifie d manner in our method. The method has been implemented and tested to valid ate our claim.