paper-with-me

홈 › Papers

Language-Grounded Decoupled Action Representation for Robotic Manipulation

2026-03-13 · Wuding Weng, Tongshu Wu, Liucheng Chen, Siyu Xie, Zheng Wang, Xing Xu, Jingkuan Song, Heng Tao Shen arxiv

The heterogeneity between high-level vision-language understanding and low-level action control remains a fundamental challenge in robotic manipulation. Although recent methods have advanced task-specific action alignment, they often struggle to generate robust and accurate actions for novel or semantically related tasks. To address this, we propose the Language-Grounded Decoupled Action Representation (LaDA) framework, which leverages natural language as a semantic bridge to connect perception and control. LaDA introduces a fine-grained intermediate layer of three interpretable action primitives--translation, rotation, and gripper control--providing explicit semantic structure for low-level actions. It further employs a semantic-guided soft-label contrastive learning objective to align similar action primitives across tasks, enhancing generalization and motion consistency. An adaptive weighting strategy, inspired by curriculum learning, dynamically balances contrastive and imitation objectives for stable and effective training. Extensive experiments on simulated benchmarks (LIBERO and MimicGen) and real-world demonstrations validate that LaDA achieves strong performance and generalizes effectively to unseen or related tasks.

📄 PDF Abstract BibTeX arXiv:2603.12967

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations

2025-12-09 · Yuchi Zhang, Churui Sun, Shiqi Liang, Diyuan Liu 외 arxiv

Recent end-to-end robotic manipulation research increasingly adopts architectures inspired by large language models to enable robust manipulation. However, a critical challenge arises from severe distribution shifts betw…

HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

2026-04-15 · Tianshuo Yang, Guanyu Chen, Yutian Chen, Zhixuan Liang 외 arxiv

While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their…

Visual Grounding

ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents

2026-04-11 · Dongjie Huo, Haoyun Liu, Guoqing Liu, Dekang Qi 외 arxiv

Current embodied intelligent systems still face a substantial gap between high-level reasoning and low-level physical execution in open-world environments. Although Vision-Language-Action (VLA) models provide strong perc…

OmniVLA: Physically-Grounded Multimodal VLA with Unified Multi-Sensor Perception for Robotic Manipulation

2025-11-03 · Heyu Guo, Shanmu Wang, Ruichun Ma, Shiqi Jiang 외 arxiv

Vision-language-action (VLA) models have shown strong generalization for robotic action prediction through large-scale vision-language pretraining. However, most existing models rely solely on RGB cameras, limiting their…

STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations

2026-04-11 · Yuhan Xie, Yuping Yan, Yunqi Zhao, Handing Wang 외 arxiv

Despite their strong performance in embodied tasks, recent Vision-Language-Action (VLA) models remain highly fragile under multimodal perturbations, where visual corruption and linguistic noise jointly induce distributio…