用视觉预测抓取成功率，让机器人在不确定时放弃尝试。
Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception
- 基于图像估计抓取姿态并预测置信度，避免盲目执行。
- 在真实图像与模拟抓取中训练，实现高成功率预判。
- 多类物体联合训练有效，适合实际场景的机器人系统。
深度目标位姿估计算法常过于自信。若抓取代理不仅能估计目标物体的6-DoF位姿，还能预测自身估计的不确定性，便可在高不确定性时选择不执行操作，从而避免任务失败。尽管目标位姿估计性能不断提升，且不确定性量化研究持续进步，但将二者与下游机器人抓取任务结合的研究仍较少。本文提出一种轻量级深度网络训练方法，可在实际抓取前预测基于图像位姿估计的抓取成功率。训练数据通过真实图像上的位姿估计与模拟抓取生成。我们还发现，尽管抓取实验中物体变化多样，但联合训练所有物体仍能提升性能，表明多样化物体有助于达成相同目标。
原文摘要 · Abstract (English)
Deep object pose estimators are notoriously overconfident. A grasping agent that both estimates the 6-DoF pose of a target object and predicts the uncertainty of its own estimate could avoid task failure by choosing not to act under high uncertainty. Even though object pose estimation improves and uncertainty quantification research continues to make strides, few studies have connected them to the downstream task of robotic grasping. We propose a method for training lightweight, deep networks to predict whether a grasp guided by an image-based pose estimate will succeed before that grasp is attempted. We generate training data for our networks via object pose estimation on real images and simulated grasping. We also find that, despite high object variability in grasping trials, networks benefit from training on all objects jointly, suggesting that a diverse variety of objects can nevertheless contribute to the same goal.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。