ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
This addresses a bottleneck in robotic perception for more accurate manipulation tasks, though it appears incremental as it builds on existing VLA frameworks.
The paper tackled the problem of current Vision-Language-Action models struggling to allocate visual attention to target regions by proposing ReconVLA, a reconstructive model that uses a diffusion transformer to reconstruct gaze regions, resulting in improved precise manipulation and generalization in experiments.
Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the target manipulated objects. This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention, thus effectively leveraging task-specific visual information and conducting precise manipulation. Moreover, we curate a large-scale pretraining dataset comprising over 100k trajectories and 2 million data samples from open-source robotic datasets, further boosting the model's generalization in visual reconstruction. Extensive experiments in simulation and the real world demonstrate the superiority of our implicit grounding method, showcasing its capabilities of precise manipulation and generalization. Our project page is https://zionchow.github.io/ReconVLA/.