D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised Deformations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yuhao, Okumura, Keisuke, Woo, Heedo, Shankar, Ajay, Prorok, Amanda
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915373005144064
author Zhang, Yuhao
Okumura, Keisuke
Woo, Heedo
Shankar, Ajay
Prorok, Amanda
author_facet Zhang, Yuhao
Okumura, Keisuke
Woo, Heedo
Shankar, Ajay
Prorok, Amanda
contents This work presents an optimization method for generating kinodynamically feasible and collision-free multi-robot trajectories that exploits an incremental denoising scheme in diffusion models. Our key insight is that high-quality trajectories can be discovered merely by denoising noisy trajectories sampled from a distribution. This approach has no learning component, relying instead on only two ingredients: a dynamical model of the robots to obtain feasible trajectories via rollout, and a fitness function to guide denoising with Monte Carlo gradient approximation. The proposed framework iteratively optimizes a deformation for the previous trajectory with the current denoising process, allows anytime refinement as time permits, supports different dynamics, and benefits from GPU acceleration. Our evaluations for differential-drive and holonomic teams with up to 16 robots in 2D and 3D worlds show its ability to discover high-quality solutions faster than other black-box optimization methods such as MPPI. In a 2D holonomic case with 16 robots, it is almost twice as fast. As evidence for feasibility, we demonstrate zero-shot deployment of the planned trajectories on eight multirotors.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12204
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised Deformations
Zhang, Yuhao
Okumura, Keisuke
Woo, Heedo
Shankar, Ajay
Prorok, Amanda
Robotics
Systems and Control
This work presents an optimization method for generating kinodynamically feasible and collision-free multi-robot trajectories that exploits an incremental denoising scheme in diffusion models. Our key insight is that high-quality trajectories can be discovered merely by denoising noisy trajectories sampled from a distribution. This approach has no learning component, relying instead on only two ingredients: a dynamical model of the robots to obtain feasible trajectories via rollout, and a fitness function to guide denoising with Monte Carlo gradient approximation. The proposed framework iteratively optimizes a deformation for the previous trajectory with the current denoising process, allows anytime refinement as time permits, supports different dynamics, and benefits from GPU acceleration. Our evaluations for differential-drive and holonomic teams with up to 16 robots in 2D and 3D worlds show its ability to discover high-quality solutions faster than other black-box optimization methods such as MPPI. In a 2D holonomic case with 16 robots, it is almost twice as fast. As evidence for feasibility, we demonstrate zero-shot deployment of the planned trajectories on eight multirotors.
title D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised Deformations
topic Robotics
Systems and Control
url https://arxiv.org/abs/2503.12204