Saved in:
Bibliographic Details
Main Authors: Wu, You, Chen, Zixuan, Ou, Cunxu, Wang, Wenxuan, Huang, Wenbo, Cao, Lin, Chen, Yangtao, Qiu, Weichao, Quan, Xingyue, Shi, Jieqi, Huo, Jing, Gao, Yang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.13788
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910052833558528
author Wu, You
Chen, Zixuan
Ou, Cunxu
Wang, Wenxuan
Huang, Wenbo
Cao, Lin
Chen, Yangtao
Qiu, Weichao
Quan, Xingyue
Shi, Jieqi
Huo, Jing
Gao, Yang
author_facet Wu, You
Chen, Zixuan
Ou, Cunxu
Wang, Wenxuan
Huang, Wenbo
Cao, Lin
Chen, Yangtao
Qiu, Weichao
Quan, Xingyue
Shi, Jieqi
Huo, Jing
Gao, Yang
contents Robotic manipulation in open-world environments requires reasoning across semantics, geometry, and long-horizon action dynamics. Existing hierarchical Vision-Language-Action (VLA) frameworks typically use 2D representations to connect high-level reasoning with low-level control, but lack depth awareness and temporal consistency, limiting robustness in complex 3D scenes. We propose ST-VLA, a hierarchical VLA framework using a unified 3D-4D representation to bridge perception and action. ST-VLA converts 2D guidance into 3D trajectories and generates smooth spatial masks that capture 4D spatio-temporal context, providing a stable interface between semantic reasoning and continuous control. To enable effective learning of such representations, we introduce ST-Human, a large-scale human manipulation dataset with 14 tasks and 300k episodes, annotated with 2D, 3D, and 4D supervision via a semi-automated pipeline. Using ST-Human, we train ST-VLM, a spatio-temporal vision-language model that generates spatially grounded and temporally coherent 3D representations to guide policy execution. The smooth spatial masks focus on task-relevant geometry and stabilize latent representations, enabling online replanning and long-horizon reasoning. Experiments on RLBench and real-world manipulation tasks show that \method significantly outperforms state-of-the-art baselines, improving zero-shot success rates by 44.6% and 30.3%. These results demonstrate that offloading spatio-temporal reasoning to VLMs with unified 3D-4D representations substantially improves robustness and generalization for open-world robotic manipulation. Project website: https://oucx117.github.io/ST-VLA/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13788
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation
Wu, You
Chen, Zixuan
Ou, Cunxu
Wang, Wenxuan
Huang, Wenbo
Cao, Lin
Chen, Yangtao
Qiu, Weichao
Quan, Xingyue
Shi, Jieqi
Huo, Jing
Gao, Yang
Robotics
Robotic manipulation in open-world environments requires reasoning across semantics, geometry, and long-horizon action dynamics. Existing hierarchical Vision-Language-Action (VLA) frameworks typically use 2D representations to connect high-level reasoning with low-level control, but lack depth awareness and temporal consistency, limiting robustness in complex 3D scenes. We propose ST-VLA, a hierarchical VLA framework using a unified 3D-4D representation to bridge perception and action. ST-VLA converts 2D guidance into 3D trajectories and generates smooth spatial masks that capture 4D spatio-temporal context, providing a stable interface between semantic reasoning and continuous control. To enable effective learning of such representations, we introduce ST-Human, a large-scale human manipulation dataset with 14 tasks and 300k episodes, annotated with 2D, 3D, and 4D supervision via a semi-automated pipeline. Using ST-Human, we train ST-VLM, a spatio-temporal vision-language model that generates spatially grounded and temporally coherent 3D representations to guide policy execution. The smooth spatial masks focus on task-relevant geometry and stabilize latent representations, enabling online replanning and long-horizon reasoning. Experiments on RLBench and real-world manipulation tasks show that \method significantly outperforms state-of-the-art baselines, improving zero-shot success rates by 44.6% and 30.3%. These results demonstrate that offloading spatio-temporal reasoning to VLMs with unified 3D-4D representations substantially improves robustness and generalization for open-world robotic manipulation. Project website: https://oucx117.github.io/ST-VLA/.
title ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation
topic Robotics
url https://arxiv.org/abs/2603.13788