LASMP: Language Aided Subset Sampling Based Motion Planner

TL;DR

LASMP integrates natural language instructions with a modified RRT motion planner, significantly improving efficiency and safety in robot navigation by focusing sampling based on user commands.

Contribution

It introduces LASMP, a novel system combining language understanding with subset sampling in motion planning, reducing computational load and enhancing path safety.

Findings

Reduced node count by 55% compared to traditional RRT

Decreased random sample queries by 80%

Demonstrated improved performance in complex indoor environments

Abstract

This paper presents the Language Aided Subset Sampling Based Motion Planner (LASMP), a system that helps mobile robots plan their movements by using natural language instructions. LASMP uses a modified version of the Rapidly Exploring Random Tree (RRT) method, which is guided by user-provided commands processed through a language model (RoBERTa). The system improves efficiency by focusing on specific areas of the robot's workspace based on these instructions, making it faster and less resource-intensive. Compared to traditional RRT methods, LASMP reduces the number of nodes needed by 55% and cuts random sample queries by 80%, while still generating safe, collision-free paths. Tested in both simulated and real-world environments, LASMP has shown better performance in handling complex indoor scenarios. The results highlight the potential of combining language processing with motion planning to make robot navigation more efficient.