ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
Zhenyang Liu1,2, Yongchong Gu1, Yikai Wang3,
Xiangyang Xue1,†, Yanwei Fu1,2,†
1Fudan University, 2Shanghai Innovation Institute, 3Nanyang Technological University
†Corresponding Authors
📢 News & Roadmap
This repository is the official implementation of ActiveVLA. We are currently preparing the code and data for release. Please stay tuned!
📖 Abstract
Most existing Vision-Language-Action (VLA) models rely on static, wrist-mounted cameras that provide a fixed, end-effector-centric viewpoint. This setup limits perceptual flexibility: the agent cannot adaptively adjust its viewpoint or camera resolution according to the task context, leading to failures in long-horizon tasks or fine-grained manipulation due to occlusion and lack of detail.
We propose ActiveVLA, a novel vision-language-action framework that explicitly integrates active perception into robotic manipulation. Unlike passive perception methods, ActiveVLA empowers robots to:
- Actively Select Viewpoints: Autonomously determine optimal camera perspectives to maximize visibility and task relevance while minimizing occlusions.
- Active 3D Zoom-in: Selectively enhance high-resolution views of task-critical regions within the 3D scene.
By dynamically refining its perceptual input, ActiveVLA achieves superior adaptability and performance in complex scenarios. Experiments show that ActiveVLA outperforms state-of-the-art baselines on RLBench, COLOSSEUM, and GemBench, and transfers seamlessly to real-world robots.
🚀 Method: ActiveVLA
We propose a coarse-to-fine active perception framework that integrates 3D spatial reasoning with vision-language understanding.
The pipeline consists of two main stages:
- Critical Region Localization (Coarse Stage): Projects 3D inputs onto multi-view 2D projections to identify critical 3D regions via heatmaps.
- Active Perception Optimization (Fine Stage):
- Active Viewpoint Selection: Uses a hypothesis testing strategy to choose optimal viewpoints that maximize amodal relevance and diversity.
- Active 3D Zoom-in: Applies a virtual optical zoom effect to improve resolution in key areas for precise manipulation.
Note: For more visualizations and real-world robot demos, please visit our
Project Page.
📊 Results
ActiveVLA achieves state-of-the-art performance across multiple benchmarks:
- RLBench: Achieves an average success rate of 91.8%, ranking 1st in 10 tasks.
- COLOSSEUM: Demonstrates superior robustness with a 65.9% success rate in challenging generalization scenarios.
- GemBench: Outperforms all baselines with strong adaptability across diverse tasks.
- Real World: High success rates in occlusion-heavy tasks (e.g., retrieving items from drawers, handling occluded objects).
📝 Citation
If you find our work useful in your research, please consider citing:
1@misc{liu2026activevlainjectingactiveperception,
2 title={ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation},
3 author={Zhenyang Liu and Yongchong Gu and Yikai Wang and Xiangyang Xue and Yanwei Fu},
4 year={2026},
5 eprint={2601.08325},
6 archivePrefix={arXiv},
7 primaryClass={cs.RO},
8 url={https://arxiv.org/abs/2601.08325},
9}
