NNgTL: Neural Network Guided Optimal Temporal Logic Task Planning for Mobile Robots

TL;DR

This paper introduces a neural network-guided sampling strategy for temporal logic task planning in mobile robots, significantly improving efficiency by directing sampling toward promising regions in continuous workspaces.

Contribution

The work presents a novel multi-modal neural network that guides sampling in LTL planning, enhancing the efficiency of sampling-based methods for mobile robot navigation.

Findings

Achieves less than 15% of the time of existing methods to find feasible solutions.

Demonstrates superior efficiency in numerical experiments.

Guided sampling improves the success rate of planning in continuous workspaces.

Abstract

In this work, we investigate task planning for mobile robots under linear temporal logic (LTL) specifications. This problem is particularly challenging when robots navigate in continuous workspaces due to the high computational complexity involved. Sampling-based methods have emerged as a promising avenue for addressing this challenge by incrementally constructing random trees, thereby sidestepping the need to explicitly explore the entire state-space. However, the performance of this sampling-based approach hinges crucially on the chosen sampling strategy, and a well-informed heuristic can notably enhance sample efficiency. In this work, we propose a novel neural-network guided (NN-guided) sampling strategy tailored for LTL planning. Specifically, we employ a multi-modal neural network capable of extracting features concurrently from both the workspace and the B\"{u}chi automaton. This neural network generates predictions that serve as guidance for random tree construction, directing the sampling process toward more optimal directions. Through numerical experiments, we compare our approach with existing methods and demonstrate its superior efficiency, requiring less than 15% of the time of the existing methods to find a feasible solution.