Parallel plan execution and re-planning on a mobile robot using state machines with HTN planning systems

This work presents parallel plan execution, an intermediate layer for mobile robot systems using high-level planners such as Hierarchical Task Network planning to execute a series of actions. Sequential plans generated by high-level planners leave system resources unused while unnecessarily increasing execution time of generated plans. This increases delay of development cycles and also increases the actual cost, regarding time, energy, and resources, of running mobile service robots in real environments. In this paper, a parallelization layer is presented using an execution based state machine. An extension to this state machine is proposed, which is capable of low-level re-planning if the desired action could not be executed correctly. The achievements are evaluated on a mobile service robot using an HTN planner and future integration into a learning system is presented.