DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation

原文：DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation

作者：Vincenzo Pomponi, Rocco Felici, Paolo Franceschi, Stefano Baraldo, Oliver Avram, Loris Roveda, Luca Maria Gambardella, Anna Valente

来源：arXiv cs.RO（机器人）

正文

Computer Science > Robotics

arXiv:2609.37348v1 (cs)

[Submitted on 29 Sep 2026]

Title:DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation

Authors:Vincenzo Pomponi, Rocco Felici, Paolo Franceschi, Stefano Baraldo, Oliver Avram, Loris Roveda, Luca Maria Gambardella, Anna Valente

View a PDF of the paper titled DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation, by Vincenzo Pomponi and 7 other authors

View PDF

HTML (experimental)

Abstract:Learning robust manipulation policies for diverse, long-horizon tasks from limited demonstrations remains a fundamental challenge in robotics. We present DROM, a language-guided diffusion framework that enables robots to learn, represent, and compose multiple manipulation skills within a single generative policy. DROM leverages Dynamic Movement Primitives (DMPs) to augment a small set of expert demonstrations into expressive multi-skill datasets, substantially reducing data collection while improving spatial generalization beyond the demonstrated workspace. Building upon Motion Planning Diffusion (MPD), we extend the diffusion architecture to support language-conditioned multi-skill trajectory generation through cross-attention, allowing a single model to generate skill-consistent motions for a diverse set of manipulation primitives, including orientation-sensitive behaviors that are difficult to design using conventional motion planning or hard-coded controllers. For long-horizon manipulation, a large language model decomposes high-level operator requests into executable sequences of skills, enabling natural language interaction and autonomous task execution. We validate DROM on a Franka Emika Panda robot, a FANUC CRX25ia robot, and in MuJoCo simulation across a wide range of manipulation tasks. Experimental results demonstrate that DROM outperforms Motion Planning Diffusion and Behavior Cloning baselines, achieves robust multi-skill generalization, and composes learned skills to reliably execute long-horizon manipulation tasks from natural language instructions using only a limited number of human demonstrations. Datasets, simulation environments, and more at this https URL.

Subjects:

Robotics (cs.RO)

Cite as:

arXiv:2609.37348 [cs.RO]

(or

arXiv:2609.37348v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.37348

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

机器人

由「前沿雷达」于 2026-09-29 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。