Planning with SiMBA: Motion Planning under Uncertainty for Temporal Goals using Simplified Belief Guides

TL;DR

This paper introduces SiMBA, a multi-layered motion planning algorithm that efficiently handles uncertainty and complex temporal goals by guiding sampling-based searches with simplified belief models, improving computational speed.

Contribution

It presents a novel approach that guides sampling-based motion planning under uncertainty using simplified belief space trajectories, avoiding complex finite abstractions.

Findings

Significant speed-up in planning for complex temporal specifications.

Proven correctness and probabilistic completeness of the algorithm.

Effective handling of motion and sensing uncertainties in temporal logic planning.

Abstract

This paper presents a new multi-layered algorithm for motion planning under motion and sensing uncertainties for Linear Temporal Logic specifications. We propose a technique to guide a sampling-based search tree in the combined task and belief space using trajectories from a simplified model of the system, to make the problem computationally tractable. Our method eliminates the need to construct fine and accurate finite abstractions. We prove correctness and probabilistic completeness of our algorithm, and illustrate the benefits of our approach on several case studies. Our results show that guidance with a simplified belief space model allows for significant speed-up in planning for complex specifications.