Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913129505488896 |
|---|---|
| author | Lin, Tao Du, Yuxin Liu, Jiting Zhu, Nuobei Li, Yunhe Fu, Yuqian Chen, Yinxinyu Cai, Hongyi Ye, Zewei Cheng, Bing Ye, Kai Mao, Yiran Zhong, Yilei Dong, MingKang Yan, Junchi Li, Gen Zhao, Bo |
| author_facet | Lin, Tao Du, Yuxin Liu, Jiting Zhu, Nuobei Li, Yunhe Fu, Yuqian Chen, Yinxinyu Cai, Hongyi Ye, Zewei Cheng, Bing Ye, Kai Mao, Yiran Zhong, Yilei Dong, MingKang Yan, Junchi Li, Gen Zhao, Bo |
| contents | Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often struggle in scenarios requiring precise spatial understanding, as current VLA models primarily rely on 2D visual representations that lack depth information and detailed spatial relationships. While recent approaches incorporate explicit 3D inputs such as depth maps or point clouds to address this issue, they often increase system complexity, require additional sensors, and remain vulnerable to sensing noise and reconstruction errors. Another line of work explores implicit 3D-aware spatial modeling directly from RGB observations without extra sensors, but it often relies on large geometry foundation models, resulting in higher training and deployment costs. To address these challenges, we propose Evo-Depth, a lightweight depth-enhanced VLA framework that enhances spatially grounded manipulation without relying on additional sensing hardware or compromising deployment efficiency. Evo-Depth employs a lightweight Implicit Depth Encoding Module to extract compact depth features from multi-view RGB images. These features are incorporated into vision-language representations through a Spatial Enhancement Module via depth-aware modulation, enabling efficient spatial-semantic enhancement. A Progressive Alignment Training strategy is further introduced to align the resulting depth-enhanced representations with downstream action learning. With only 0.9B parameters, Evo-Depth achieves superior performance across four simulation benchmarks. In real-world experiments, Evo-Depth attains the highest average success rate while also exhibiting the smallest model size, lowest GPU memory usage, and highest inference frequency among compared methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14950 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model Lin, Tao Du, Yuxin Liu, Jiting Zhu, Nuobei Li, Yunhe Fu, Yuqian Chen, Yinxinyu Cai, Hongyi Ye, Zewei Cheng, Bing Ye, Kai Mao, Yiran Zhong, Yilei Dong, MingKang Yan, Junchi Li, Gen Zhao, Bo Computer Vision and Pattern Recognition Robotics Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often struggle in scenarios requiring precise spatial understanding, as current VLA models primarily rely on 2D visual representations that lack depth information and detailed spatial relationships. While recent approaches incorporate explicit 3D inputs such as depth maps or point clouds to address this issue, they often increase system complexity, require additional sensors, and remain vulnerable to sensing noise and reconstruction errors. Another line of work explores implicit 3D-aware spatial modeling directly from RGB observations without extra sensors, but it often relies on large geometry foundation models, resulting in higher training and deployment costs. To address these challenges, we propose Evo-Depth, a lightweight depth-enhanced VLA framework that enhances spatially grounded manipulation without relying on additional sensing hardware or compromising deployment efficiency. Evo-Depth employs a lightweight Implicit Depth Encoding Module to extract compact depth features from multi-view RGB images. These features are incorporated into vision-language representations through a Spatial Enhancement Module via depth-aware modulation, enabling efficient spatial-semantic enhancement. A Progressive Alignment Training strategy is further introduced to align the resulting depth-enhanced representations with downstream action learning. With only 0.9B parameters, Evo-Depth achieves superior performance across four simulation benchmarks. In real-world experiments, Evo-Depth attains the highest average success rate while also exhibiting the smallest model size, lowest GPU memory usage, and highest inference frequency among compared methods. |
| title | Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2605.14950 |