MBHP: A memory-based method on robot planning under uncertainties

The current work environments for mobile robots tend to be complex and dynamic, which often causes difficulties in the execution of tasks due to incomplete and uncertain information. A number of experiments and applications have shown that it is an appropriate and efficient approach to handle this issue by integrating the AI method with plan-based robot control. In this paper, an HTN (Hierarchical Task Net) planner is integrated in the control architecture of a mobile robot as the deliberative planner, so that the tasks can be recursively decomposed into smaller subtasks, and the atomic actions sufficient for execution can be finally achieved. Simultaneously, by combining a robotics memory base and probability inference, the robot can exploit its experience, so that the lacking information for robot planning can be compensated. Finally, several experiments show that the robot can accomplish the task more efficiently in a dynamic environment by using this approach, which is called Memory-Based HTN Planning (MBHP).