Task-assisted Motion Planning in Partially Observable Domains
This addresses navigation challenges for autonomous robots in complex real-world scenarios, but it appears incremental as it builds on existing PDDL+ and heuristic methods.
The paper tackles robot navigation in partially observable environments by integrating belief space reasoning into a hybrid task-motion planning framework, validating it in simulation.
We present an integrated Task-Motion Planning framework for robot navigation in belief space. Autonomous robots operating in real world complex scenarios require planning in the discrete (task) space and the continuous (motion) space. To this end, we propose a framework for integrating belief space reasoning within a hybrid task planner. The expressive power of PDDL+ combined with heuristic-driven semantic attachments performs the propagated and posterior belief estimates while planning. The underlying methodology for the development of the combined hybrid planner is discussed, providing suggestions for improvements and future work. Furthermore we validate key aspects of our approach using a realistic scenario in simulation.