恢复视野：面向机器人操作中遮挡恢复的物理主动视觉基准测试
Recovering the View: Benchmarking Physical Active Vision for Occlusion Recovery in Robotic Manipulation
浏览论文内容
中文总结 AI 辅助
针对机器人操作中遮挡导致观测不可靠的问题，本文提出双臂主动视觉基准BAVO-Bench和主动视觉策略A-FAR，通过统一3D表示和预训练4D模型提供未来感知指导，显著提升对结构性和时间偏移遮挡的鲁棒性。
中文摘要 AI 辅助
物理主动视觉使机器人能够在任务相关观测变得不可靠时改变其视角，然而现有的操作基准对研究策略在执行过程中如何从遮挡中恢复的支持有限。我们引入了BAVO-Bench（遮挡下的双臂主动视觉），这是一个双臂主动视觉基准，通过干净、阶段遮挡和随机时间遮挡条件系统地控制外部可见性，从而能够评估操作性能和主动视觉恢复。基于这一设置，我们提出了A-FAR（主动未来感知恢复），一种用于联合视角和操作控制的主动视觉策略。A-FAR将移动相机观测统一表示在机器人中心的3D框架中，并从预训练的4D模型中提取关系结构及其未来演化，为策略提供未来感知的几何指导，而无需在部署时提供未来观测。跨多个操作任务的实验表明，A-FAR在保持干净观测下强性能的同时，提高了对结构性和时间偏移遮挡的鲁棒性。
英文摘要
Physical active vision allows robots to change their viewpoint when task-relevant observations become unreliable, yet existing manipulation benchmarks provide limited support for studying how policies recover from occlusion during execution. We introduce BAVO-Bench (Bimanual Active Vision under Occlusion), a bimanual active-vision benchmark that systematically controls external visibility through Clean, Stage Occlusion, and Random-time Occlusion conditions, enabling evaluation of both manipulation performance and active visual recovery. Building on this setting, we present A-FAR (Active Future-Aware Recovery), an active-vision policy for joint viewpoint and manipulation control. A-FAR represents moving-camera observations in a unified robot-centric 3D frame and distills relational structure together with its future evolution from a pretrained 4D model, providing the policy with future-aware geometric guidance without requiring future observations at deployment. Experiments across multiple manipulation tasks show that A-FAR improves robustness to both structured and temporally shifted occlusions while maintaining strong performance under clean observations.
发表机构
- Sun Yat-sen University（中山大学）
- University of Electronic Science and Technology of China（电子科技大学）
- Pengcheng Laboratory（鹏城实验室）
- X-Era AI Lab（X-Era AI实验室）
机构由 AI 辅助整理，请以论文原文为准。
