RRT*former: Environment-Aware Sampling-Based Motion Planning using Transformer

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Mingyang, Li, Shaoyuan, Yin, Xiang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909913517654016
author Feng, Mingyang
Li, Shaoyuan
Yin, Xiang
author_facet Feng, Mingyang
Li, Shaoyuan
Yin, Xiang
contents We investigate the sampling-based optimal path planning problem for robotics in complex and dynamic environments. Most existing sampling-based algorithms neglect environmental information or the information from previous samples. Yet, these pieces of information are highly informative, as leveraging them can provide better heuristics when sampling the next state. In this paper, we propose a novel sampling-based planning algorithm, called \emph{RRT*former}, which integrates the standard RRT* algorithm with a Transformer network in a novel way. Specifically, the Transformer is used to extract features from the environment and leverage information from previous samples to better guide the sampling process. Our extensive experiments demonstrate that, compared to existing sampling-based approaches such as RRT*, Neural RRT*, and their variants, our algorithm achieves considerable improvements in both the optimality of the path and sampling efficiency. The code for our implementation is available on https://github.com/fengmingyang666/RRTformer.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15414
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RRT*former: Environment-Aware Sampling-Based Motion Planning using Transformer
Feng, Mingyang
Li, Shaoyuan
Yin, Xiang
Robotics
Artificial Intelligence
We investigate the sampling-based optimal path planning problem for robotics in complex and dynamic environments. Most existing sampling-based algorithms neglect environmental information or the information from previous samples. Yet, these pieces of information are highly informative, as leveraging them can provide better heuristics when sampling the next state. In this paper, we propose a novel sampling-based planning algorithm, called \emph{RRT*former}, which integrates the standard RRT* algorithm with a Transformer network in a novel way. Specifically, the Transformer is used to extract features from the environment and leverage information from previous samples to better guide the sampling process. Our extensive experiments demonstrate that, compared to existing sampling-based approaches such as RRT*, Neural RRT*, and their variants, our algorithm achieves considerable improvements in both the optimality of the path and sampling efficiency. The code for our implementation is available on https://github.com/fengmingyang666/RRTformer.
title RRT*former: Environment-Aware Sampling-Based Motion Planning using Transformer
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2511.15414