Salvato in:
Dettagli Bibliografici
Autori principali: Jimenez, Jorge Ocampo, Suleiman, Wael
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2501.06639
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915099157987328
author Jimenez, Jorge Ocampo
Suleiman, Wael
author_facet Jimenez, Jorge Ocampo
Suleiman, Wael
contents This paper presents a novel method for accelerating path-planning tasks in unknown scenes with obstacles by utilizing Wasserstein Generative Adversarial Networks (WGANs) with Gradient Penalty (GP) to approximate the distribution of waypoints for a collision-free path using the Rapidly-exploring Random Tree algorithm. Our approach involves conditioning the WGAN-GP with a forward diffusion process in a continuous latent space to handle multimodal datasets effectively. We also propose encoding the waypoints of a collision-free path as a matrix, where the multidimensional ordering of the waypoints is naturally preserved. This method not only improves model learning but also enhances training convergence. Furthermore, we propose a method to assess whether the trained model fails to accurately capture the true waypoints. In such cases, we revert to uniform sampling to ensure the algorithm's probabilistic completeness; a process that traditionally involves manually determining an optimal ratio for each scenario in other machine learning-based methods. Our experiments demonstrate promising results in accelerating path-planning tasks under critical time constraints. The source code is openly available at https://bitbucket.org/joro3001/imagewgangpplanning/src/master/.
format Preprint
id arxiv_https___arxiv_org_abs_2501_06639
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Path Planning Performance through Image Representation Learning of High-Dimensional Configuration Spaces
Jimenez, Jorge Ocampo
Suleiman, Wael
Robotics
Artificial Intelligence
This paper presents a novel method for accelerating path-planning tasks in unknown scenes with obstacles by utilizing Wasserstein Generative Adversarial Networks (WGANs) with Gradient Penalty (GP) to approximate the distribution of waypoints for a collision-free path using the Rapidly-exploring Random Tree algorithm. Our approach involves conditioning the WGAN-GP with a forward diffusion process in a continuous latent space to handle multimodal datasets effectively. We also propose encoding the waypoints of a collision-free path as a matrix, where the multidimensional ordering of the waypoints is naturally preserved. This method not only improves model learning but also enhances training convergence. Furthermore, we propose a method to assess whether the trained model fails to accurately capture the true waypoints. In such cases, we revert to uniform sampling to ensure the algorithm's probabilistic completeness; a process that traditionally involves manually determining an optimal ratio for each scenario in other machine learning-based methods. Our experiments demonstrate promising results in accelerating path-planning tasks under critical time constraints. The source code is openly available at https://bitbucket.org/joro3001/imagewgangpplanning/src/master/.
title Enhancing Path Planning Performance through Image Representation Learning of High-Dimensional Configuration Spaces
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2501.06639