Closed-loop multi-step planning with innate physics knowledge

TL;DR

This paper introduces a hierarchical planning framework for robots that integrates innate physics knowledge through a supervising Configurator, enabling multi-step planning and control based on simulated task sequences.

Contribution

The novel framework combines hierarchical control loops with a physics engine for planning, demonstrated on a real robot in an overtaking scenario.

Findings

Successful implementation on a real robot

Effective multi-step planning using physics simulation

Demonstrated capability in overtaking task

Abstract

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.