Task-Motion Planning for Navigation in Belief Space

TL;DR

This paper introduces an integrated task-motion planning framework for autonomous robot navigation in complex, large-scale environments, emphasizing probabilistic completeness and belief space considerations for improved decision-making.

Contribution

It presents a novel task-motion planning approach that accounts for uncertainty and interaction between task and motion levels in indoor navigation.

Findings

Framework is probabilistically complete.

Plan is optimal at the task level.

Validated in simulated office environment.

Abstract

We present an integrated Task-Motion Planning (TMP) framework for navigation in large-scale environment. Autonomous robots operating in real world complex scenarios require planning in the discrete (task) space and the continuous (motion) space. In knowledge intensive domains, on the one hand, a robot has to reason at the highest-level, for example the regions to navigate to; on the other hand, the feasibility of the respective navigation tasks have to be checked at the execution level. This presents a need for motion-planning-aware task planners. We discuss a probabilistically complete approach that leverages this task-motion interaction for navigating in indoor domains, returning a plan that is optimal at the task-level. Furthermore, our framework is intended for motion planning under motion and sensing uncertainty, which is formally known as belief space planning. The underlying methodology is validated with a simulated office environment in Gazebo. In addition, we discuss the limitations and provide suggestions for improvements and future work.