Saved in:
Bibliographic Details
Main Authors: Bhattacharjee, Saswati, Sinha, Anirban, Ekenna, Chinwe
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.00649
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916418076803072
author Bhattacharjee, Saswati
Sinha, Anirban
Ekenna, Chinwe
author_facet Bhattacharjee, Saswati
Sinha, Anirban
Ekenna, Chinwe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00649
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LASMP: Language Aided Subset Sampling Based Motion Planner
Bhattacharjee, Saswati
Sinha, Anirban
Ekenna, Chinwe
Robotics
Artificial Intelligence
Human-Computer Interaction
Machine Learning
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.
title LASMP: Language Aided Subset Sampling Based Motion Planner
topic Robotics
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2410.00649