Stereo cameras closely mimic human binocular vision, providing rich spatial cues critical for precise robotic manipulation. Despite their advantage, the adoption of stereo vision in vision-language-action models (VLAs) remains underexplored. In this work, we present StereoVLA, a VLA model that leverages rich geometric cues from stereo vision. We propose a novel Geometric-Semantic Feature Extraction module that utilizes vision foundation models to extract and fuse two key features: 1) geometric features from subtle stereo-view differences for spatial perception; 2) semantic-rich features from the monocular view for instruction following. Additionally, we propose an auxiliary Interaction-Region Depth Estimation task to further enhance spatial perception and accelerate model convergence. Extensive experiments show that our approach outperforms baselines by a large margin in diverse tasks under the stereo setting and demonstrates strong robustness to camera pose variations.
@article{arxiv.2512.21970,
title = {StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision},
author = {Shengliang Deng and Mi Yan and Yixin Zheng and Jiayi Su and Wenhao Zhang and Xiaoguang Zhao and Heming Cui and Zhizheng Zhang and He Wang},
journal= {arXiv preprint arXiv:2512.21970},
year = {2025}
}