Closed-loop multi-step planning with innate physics knowledge
This addresses robot planning in dynamic environments, but it appears incremental as it builds on existing hierarchical and physics-based approaches.
The authors tackled robot planning by developing a hierarchical framework with a physics engine at its core to simulate task sequences, implementing it on a real robot for an overtaking scenario as proof-of-concept.
We present a hierarchical framework to solve robot planning as an input control problem. At the lowest level are temporary closed control loops, ("tasks"), each representing a behaviour, contingent on a specific sensory input and therefore temporary. At the highest level, a supervising "Configurator" directs task creation and termination. Here resides "core" knowledge as a physics engine, where sequences of tasks can be simulated. The Configurator encodes and interprets simulation results,based on which it can choose a sequence of tasks as a plan. We implement this framework on a real robot and test it in an overtaking scenario as proof-of-concept.