Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.19859 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910004048560128 |
|---|---|
| author | Ma, Xiangkai Xing, Lekai Zhang, Han Li, Wenzhong Lu, Sanglu |
| author_facet | Ma, Xiangkai Xing, Lekai Zhang, Han Li, Wenzhong Lu, Sanglu |
| contents | Vision-Language-Action (VLA) models built upon Chain-of-Thought (CoT) have achieved remarkable success in advancing general-purpose robotic agents, owing to its significant perceptual comprehension. Recently, since text-only CoT struggles to adequately capture scene details in complex spatial environments, a highly promising strategy involves leveraging visual priors to guide robotic action generation. Nevertheless, these strategies face two inherent challenges: (i) a modality gap between visual observations and low-level actions, and (ii) unstable training due to competing objectives between visual prediction and action generation. To address these challenges, we propose a Vision-Integrated Trajectory Alignment (VITA) framework that learns a shared discrete latent space for vision and action, enabling joint modeling of perception and motor control. VITA introduces a implicit visual CoT: autoregressively generated tokens is simultaneously decoded into future frames predictions and robot actions, thereby internalizing visual dynamics as an inductive bias for motion planning. Extensive experiments on simulated and real-world environments demonstrate state-of-the-art performance. VITA improves 14.5\%, 9.6\% and 12.1\% over existing baselines on CALVIN, LIBERO and SimplerEnv. Furthermore, VITA attains an average success rate of 80.5\% across six real-world tasks, demonstrating its potential as a generalist robotic manipulation model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19859 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation Ma, Xiangkai Xing, Lekai Zhang, Han Li, Wenzhong Lu, Sanglu Robotics Vision-Language-Action (VLA) models built upon Chain-of-Thought (CoT) have achieved remarkable success in advancing general-purpose robotic agents, owing to its significant perceptual comprehension. Recently, since text-only CoT struggles to adequately capture scene details in complex spatial environments, a highly promising strategy involves leveraging visual priors to guide robotic action generation. Nevertheless, these strategies face two inherent challenges: (i) a modality gap between visual observations and low-level actions, and (ii) unstable training due to competing objectives between visual prediction and action generation. To address these challenges, we propose a Vision-Integrated Trajectory Alignment (VITA) framework that learns a shared discrete latent space for vision and action, enabling joint modeling of perception and motor control. VITA introduces a implicit visual CoT: autoregressively generated tokens is simultaneously decoded into future frames predictions and robot actions, thereby internalizing visual dynamics as an inductive bias for motion planning. Extensive experiments on simulated and real-world environments demonstrate state-of-the-art performance. VITA improves 14.5\%, 9.6\% and 12.1\% over existing baselines on CALVIN, LIBERO and SimplerEnv. Furthermore, VITA attains an average success rate of 80.5\% across six real-world tasks, demonstrating its potential as a generalist robotic manipulation model. |
| title | Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation |
| topic | Robotics |
| url | https://arxiv.org/abs/2511.19859 |