中文
相关论文

相关论文: Survey of Vision-Language-Action Models for Embodi…

200 篇论文

While the exploration for embodied AI has spanned multiple decades, it remains a persistent challenge to endow agents with human-level intelligence, including perception, learning, reasoning, decision-making, control, and generalization…

机器人学 · 计算机科学 2024-02-07 Zhiyuan Xu , Kun Wu , Junjie Wen , Jinming Li , Ning Liu , Zhengping Che , Jian Tang

The realization of Artificial General Intelligence (AGI) necessitates Embodied AI agents capable of robust spatial perception, effective task planning, and adaptive execution in physical environments. However, current large language models…

Embodied Artificial Intelligence (AI) is an intelligent system paradigm for achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications and driving the evolution from cyberspace to physical systems.…

人工智能 · 计算机科学 2025-09-25 Tongtong Feng , Xin Wang , Yu-Gang Jiang , Wenwu Zhu

Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of…

机器学习 · 计算机科学 2026-03-20 Zhuofan Li , Hongkun Yang , Zhenyang Chen , Yangxuan Chen , Yingyan , Lin , Chaojian Li

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

机器人学 · 计算机科学 2025-12-17 Zechen Bai , Chen Gao , Mike Zheng Shou

Embodied scene understanding serves as the cornerstone for autonomous agents to perceive, interpret, and respond to open driving scenarios. Such understanding is typically founded upon Vision-Language Models (VLMs). Nevertheless, existing…

计算机视觉与模式识别 · 计算机科学 2024-03-08 Yunsong Zhou , Linyan Huang , Qingwen Bu , Jia Zeng , Tianyu Li , Hang Qiu , Hongzi Zhu , Minyi Guo , Yu Qiao , Hongyang Li

Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are…

Vision-language-action models (VLAs) have become increasingly popular in robot manipulation for their end-to-end design and remarkable performance. However, existing VLAs rely heavily on vision-language models (VLMs) that only support…

机器人学 · 计算机科学 2025-02-24 Wei Zhao , Pengxiang Ding , Min Zhang , Zhefei Gong , Shuanghao Bai , Han Zhao , Donglin Wang

This paper describes our research on AI agents embodied in visual, virtual or physical forms, enabling them to interact with both users and their environments. These agents, which include virtual avatars, wearable devices, and robots, are…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, enabling robots to perform tasks based on natural language instructions and current visual input. However, existing VLA models struggle with…

Vision-Language Models (VLMs) have emerged as a promising approach to address the data scarcity challenge in robotics, enabling the development of generalizable visuomotor control policies. While models like OpenVLA showcase the potential…

Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D…

机器人学 · 计算机科学 2025-12-16 Yicheng Feng , Wanpeng Zhang , Ye Wang , Hao Luo , Haoqi Yuan , Sipeng Zheng , Zongqing Lu

Vision-Language-Action (VLA) models widely adopt pretrained Vision-Language Models (VLMs) as policy backbones, yet it remains unclear what kind of pretrained VLM representation is useful as a VLA initialization. In this paper, we study VLA…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Weifeng Lin , Siyuan Huang , Hao Li , Tingwei Chen , Ruichuan An , Xinyu Wei , Jianbo Liu , Hongsheng Li

Understanding how Vision-Language-Action (VLA) models transform multimodal knowledge into embodied control remains an open challenge. We present VLA-Trace, a progressive diagnostic framework that analyzes VLA models through a unified…

Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language…

计算机视觉与模式识别 · 计算机科学 2025-06-25 Yuqi Wang , Xinghang Li , Wenxuan Wang , Junbo Zhang , Yingyan Li , Yuntao Chen , Xinlong Wang , Zhaoxiang Zhang

Embodied Artificial Intelligence (Embodied AI) is crucial for achieving Artificial General Intelligence (AGI) and serves as a foundation for various applications (e.g., intelligent mechatronics systems, smart manufacturing) that bridge…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Yang Liu , Weixing Chen , Yongjie Bai , Xiaodan Liang , Guanbin Li , Wen Gao , Liang Lin

Vision-language-action (VLA) models perform well on training-seen robotic tasks but struggle to generalize to unseen scenes and objects. A key limitation lies in their implicit visual representations, which entangle object appearance,…

计算机视觉与模式识别 · 计算机科学 2026-05-08 Hanyu Zhou , Chuanhao Ma , Gim Hee Lee

We introduce iFlyBot-VLA, a large-scale Vision-Language-Action (VLA) model trained under a novel framework. The main contributions are listed as follows: (1) a latent action model thoroughly trained on large-scale human and robotic…

计算机视觉与模式识别 · 计算机科学 2025-11-05 Yuan Zhang , Chenyu Xue , Wenjie Xu , Chao Ji , Jiajia wu , Jia Pan

Vision-language-action (VLA) models provide a powerful approach to training control policies for physical systems, such as robots, by combining end-to-end learning with transfer of semantic knowledge from web-scale vision-language model…

Vision-Language-Action (VLA) models aim to control robots for manipulation from visual observations and natural-language instructions. However, existing hierarchical and autoregressive paradigms often introduce architectural overhead,…