MPTP: Motion-Planning-aware Task Planning for Navigation in Belief Space

TL;DR

This paper introduces a probabilistically complete task-motion planning framework for autonomous navigation in belief space, effectively integrating high-level task reasoning with low-level motion feasibility in complex, knowledge-rich environments.

Contribution

The paper presents a novel integrated framework that combines task and motion planning specifically for navigation in belief space, addressing the interaction between high-level reasoning and low-level motion feasibility.

Findings

Framework is validated in simulation and real environments.

Scalability demonstrated in large environments like Willow Garage world.

Approach is adaptable to building floor navigation.

Abstract

We present an integrated Task-Motion Planning (TMP) framework for navigation in large-scale environments. Of late, TMP for manipulation has attracted significant interest resulting in a proliferation of different approaches. In contrast, TMP for navigation has received considerably less attention. 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 objects to procure, the regions to navigate to in order to acquire them; 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. In this paper, we discuss a probabilistically complete approach that leverages this task-motion interaction for navigating in large knowledge-intensive domains, returning a plan that is optimal at the task-level. The framework is intended for motion planning under motion and sensing uncertainty, which is formally known as belief space planning. The underlying methodology is validated in simulation, in an office environment and its scalability is tested in the larger Willow Garage world. A reasonable comparison with a work that is closest to our approach is also provided. We also demonstrate the adaptability of our approach by considering a building floor navigation domain. Finally, we also discuss the limitations of our approach and put forward suggestions for improvements and future work.