Unified framework for path-planning and task-planning for autonomous robots

Most of the robotic systems are designed to move and perform tasks in a variety of environments. Some of these environments are controllable and well-defined, and the tasks to be performed are generally everyday ones. However, exploration missions also enclose hard constraints such as driving vehicles to many locations in a surface of several kilometres to collect and/or analyse interesting samples. Therefore, a critical aspect for the mission is to optimally (or sub-optimally) plan the path that a robot should follow while performing scientific tasks. In this paper, we present up2ta, a new AI planner that interleaves path-planning and task-planning for mobile robotics applications. The planner is the result of integrating a modified PDDL planner with a path-planning algorithm, combining domain-independent heuristics and a domain-specific heuristic for path-planning. Then, up2ta can exploit capabilities of both planners to generate shorter paths while performing scientific tasks in an efficient ordered way. The planner has been tested in two domains: an exploration mission consisting of pictures acquisition, and a more challenging one that includes samples delivering. Also, up2ta has been integrated and tested in a real robotic platform for both domains. •A planner for mobile robotics applications is proposed.•Integrating task-planning and path-planning provides several advantages.•Using specific and domain independent heuristics improves the solutions generated.