QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912781534494720 |
|---|---|
| author | Li, Yixuan Chen, Yuhui Zhou, Mingcai Li, Haoran Zhang, Zhengtao Zhao, Dongbin |
| author_facet | Li, Yixuan Chen, Yuhui Zhou, Mingcai Li, Haoran Zhang, Zhengtao Zhao, Dongbin |
| contents | Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D structures necessary for precise control. To address this limitation, we propose QDepth-VLA, a general framework that augments VLA models with an auxiliary depth prediction task. A dedicated depth expert is designed to predict quantized latent tokens of depth maps obtained from a VQ-VAE encoder, enabling the model to learn depth-aware representations that capture critical geometric cues. Experimental results on the simulation benchmarks and real-world tasks demonstrate that QDepth-VLA yields strong spatial reasoning and competitive performance on manipulation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14836 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models Li, Yixuan Chen, Yuhui Zhou, Mingcai Li, Haoran Zhang, Zhengtao Zhao, Dongbin Computer Vision and Pattern Recognition Robotics Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D structures necessary for precise control. To address this limitation, we propose QDepth-VLA, a general framework that augments VLA models with an auxiliary depth prediction task. A dedicated depth expert is designed to predict quantized latent tokens of depth maps obtained from a VQ-VAE encoder, enabling the model to learn depth-aware representations that capture critical geometric cues. Experimental results on the simulation benchmarks and real-world tasks demonstrate that QDepth-VLA yields strong spatial reasoning and competitive performance on manipulation tasks. |
| title | QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2510.14836 |