Saved in:
Bibliographic Details
Main Authors: Ma, Xiangkai, Xing, Lekai, Zhang, Han, Li, Wenzhong, Lu, Sanglu
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