xperception——让机器人抓取更轻松
xperception -- Making Robotic Grasping Easier
- Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
研究针对高混合低产量制造中机器人操作灵活性问题，提出零样本6D姿态估计技术xperception，利用CAD模型和基础模型语义特征，基于FreeZe算法实现毫米级精确估计，为相关行业机器人自动化提供了可扩展方案。
中文摘要 AI 辅助
向高混合低产量制造的转变需要机器人操作具备灵活性。然而，传统视觉系统仍是瓶颈，每当生产线引入新物体时都需大量数据收集和模型再训练。为克服这一局限性，我们提出了xperception，一种零样本6D姿态估计技术，无需特定物体微调及费力的数据标注。通过直接利用典型CAD模型并整合基础模型（如DINOv2、GeDi）的丰富语义特征，xperception实现了毫米级精确的6D姿态估计。xperception在诸如料箱抓取等工业任务中对严重遮挡具有鲁棒性，且专为部署在工业边缘硬件（如NVIDIA Jetson Thor）而设计。经6级技术就绪水平验证，xperception的核心方法基于赢得2024年国际BOP挑战赛的FreeZe算法，为非结构化高混合低产量制造行业中可扩展、即插即用的机器人自动化铺平了道路。
英文摘要
The transition toward high-mix low-volume manufacturing demands flexibility in robotic manipulation. However, conventional vision systems remain a bottleneck, requiring extensive data collection and model retraining whenever a new object is introduced to the production line. To overcome this rigidity, we present xperception, a zero-shot 6D pose estimation technology that eliminates the need for object-specific fine-tuning and laborious data annotation. By directly utilizing typical CAD models and integrating the rich semantic features of foundation models (e.g. DINOv2, GeDi), xperception achieves millimeter-accurate 6D pose estimation. xperception showed robustness against severe occlusions in industrial tasks like bin picking and is engineered for deployment on industrial edge hardware, such as NVIDIA Jetson Thor. Validated at a TRL of 6, the core methodology behind xperception is based on the FreeZe algorithm, which won the international BOP Challenge 2024, paving the way for scalable, plug-and-play robotic automation in unstructured high-mix low-volume manufacturing industries.
