AURORA: Active Uncertainty-Driven Re-Orientation for In-Hand Reconstruction

2026-09-08

AI Summary

针对机器人手抓取物体时的视觉遮挡问题，提出AURORA框架，通过主动选择最佳视角和旋转策略来提高3D重建质量和效率。

Abstract

Observing objects grasped by a robot hand is challenging due to severe visual occlusions. Although in-hand manipulation can expose hidden surfaces, existing approaches often rely on predefined or open-loop reorientation strategies that do not explicitly target under-observed regions. We propose AURORA, an active 3D reconstruction framework that closes the loop between online object-centric reconstruction and in-hand reorientation. At its core, Ray-GPIS estimates direction-wise reconstruction uncertainty along candidate viewing rays and selects next-best-view targets using an uncertainty--novelty objective, which are realized through an axis-conditioned in-hand rotation policy. The resulting RGB-D observations are fused incrementally using CAD-free 6D pose tracking and lightweight geometric reconstruction. Experiments demonstrate that AURORA improves reconstruction quality and information-acquisition efficiency over non-active rotation strategies, while Ray-GPIS also outperforms active view-planning baselines in reconstruction performance, action-ranking quality, and planning efficiency. Targeted ablations further validate its robustness to hand occlusion and pose errors. The project webpage is available at https://aurorahand.github.io/

Problem

• visual occlusions
• in-hand manipulation
• reconstruction uncertainty

Innovation

• Active 3D Reconstruction
• Uncertainty-Driven Reorientation
• Ray-GPIS
• In-Hand Manipulation
• Next-Best-View