2025/10/16 by Li, Yixuan, Chen, Yuhui, Zhou, Mingcai +3 · 3 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO)
paper · doi:10.48550/arxiv.2510.14836
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.