DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Xukun, Sun, Yu, Zhang, Lei, Huang, Bosheng, Peng, Yibo, Meng, Yuan, Jiang, Haojun, Xie, Shaoxuan, Yao, Guocai, Knoll, Alois, Bing, Zhenshan, Wang, Xinlong, Sun, Zhenguo
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917298328043520
author Li, Xukun
Sun, Yu
Zhang, Lei
Huang, Bosheng
Peng, Yibo
Meng, Yuan
Jiang, Haojun
Xie, Shaoxuan
Yao, Guocai
Knoll, Alois
Bing, Zhenshan
Wang, Xinlong
Sun, Zhenguo
author_facet Li, Xukun
Sun, Yu
Zhang, Lei
Huang, Bosheng
Peng, Yibo
Meng, Yuan
Jiang, Haojun
Xie, Shaoxuan
Yao, Guocai
Knoll, Alois
Bing, Zhenshan
Wang, Xinlong
Sun, Zhenguo
contents Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal diffusion transformer that disentangles vision, proprioception, and tactile signals through specialized conditioning pathways, enabling structured and controllable integration of multimodal inputs, with a lightweight adapter for parameter-efficient injection of additional signals. Alongside DECO, we release DECO-50 dataset for bimanual dexterous manipulation with tactile sensing, consisting of 50 hours of data and over 5M frames, collected via teleoperation on real dual-arm robots. We train DECO on DECO-50 and conduct extensive real-world evaluation with over 2,000 robot rollouts. Experimental results show that DECO achieves the best performance across all tasks, with a 72.25% average success rate and a 21% improvement over the baseline. Moreover, the tactile adapter brings an additional 10.25% average success rate across all tasks and a 20% gain on complex contact-rich tasks while tuning less than 10% of the model parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05513
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter
Li, Xukun
Sun, Yu
Zhang, Lei
Huang, Bosheng
Peng, Yibo
Meng, Yuan
Jiang, Haojun
Xie, Shaoxuan
Yao, Guocai
Knoll, Alois
Bing, Zhenshan
Wang, Xinlong
Sun, Zhenguo
Robotics
Artificial Intelligence
Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal diffusion transformer that disentangles vision, proprioception, and tactile signals through specialized conditioning pathways, enabling structured and controllable integration of multimodal inputs, with a lightweight adapter for parameter-efficient injection of additional signals. Alongside DECO, we release DECO-50 dataset for bimanual dexterous manipulation with tactile sensing, consisting of 50 hours of data and over 5M frames, collected via teleoperation on real dual-arm robots. We train DECO on DECO-50 and conduct extensive real-world evaluation with over 2,000 robot rollouts. Experimental results show that DECO achieves the best performance across all tasks, with a 72.25% average success rate and a 21% improvement over the baseline. Moreover, the tactile adapter brings an additional 10.25% average success rate across all tasks and a 20% gain on complex contact-rich tasks while tuning less than 10% of the model parameters.
title DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2602.05513