Salvato in:
Dettagli Bibliografici
Autori principali: Vatnsdal, Frederic, Camargo, Romina Garcia, Agarwal, Saurav, Ribeiro, Alejandro
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.17244
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918485521596416
author Vatnsdal, Frederic
Camargo, Romina Garcia
Agarwal, Saurav
Ribeiro, Alejandro
author_facet Vatnsdal, Frederic
Camargo, Romina Garcia
Agarwal, Saurav
Ribeiro, Alejandro
contents We propose MADP, a novel diffusion-model-based approach for collaboration in decentralized robot swarms. MADP leverages diffusion models to generate samples from complex and high-dimensional action distributions that capture the interdependencies between agents' actions. Each robot conditions policy sampling on a fused representation of its own observations and perceptual embeddings received from peers. To evaluate this approach, we task a team of holonomic robots piloted by MADP to address coverage control-a canonical multi agent navigation problem. The policy is trained via imitation learning from a clairvoyant expert on the coverage control problem, with the diffusion process parameterized by a spatial transformer architecture to enable decentralized inference. We evaluate the system under varying numbers, locations, and variances of importance density functions, capturing the robustness demands of real-world coverage tasks. Experiments demonstrate that our model inherits valuable properties from diffusion models, generalizing across agent densities and environments, and consistently outperforming state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17244
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalable Multi Agent Diffusion Policies for Coverage Control
Vatnsdal, Frederic
Camargo, Romina Garcia
Agarwal, Saurav
Ribeiro, Alejandro
Robotics
We propose MADP, a novel diffusion-model-based approach for collaboration in decentralized robot swarms. MADP leverages diffusion models to generate samples from complex and high-dimensional action distributions that capture the interdependencies between agents' actions. Each robot conditions policy sampling on a fused representation of its own observations and perceptual embeddings received from peers. To evaluate this approach, we task a team of holonomic robots piloted by MADP to address coverage control-a canonical multi agent navigation problem. The policy is trained via imitation learning from a clairvoyant expert on the coverage control problem, with the diffusion process parameterized by a spatial transformer architecture to enable decentralized inference. We evaluate the system under varying numbers, locations, and variances of importance density functions, capturing the robustness demands of real-world coverage tasks. Experiments demonstrate that our model inherits valuable properties from diffusion models, generalizing across agent densities and environments, and consistently outperforming state-of-the-art baselines.
title Scalable Multi Agent Diffusion Policies for Coverage Control
topic Robotics
url https://arxiv.org/abs/2509.17244