arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.01048cs.RO
收藏

面向自适应机器人应用的Sim2Real抓取位姿估计

Sim2Real Grasp Pose Estimation for Adaptive Robotic Applications

Institute for Computer Science and Control, Eötvös Loránd Research Network(厄特沃什·罗兰研究网络计算机科学与控制研究所);Eötvös Loránd University(厄特沃什·罗兰大学);Budapest University of Technology and Economics(布达佩斯技术与经济大学)

Dániel Horváth, Kristóf Bocsi, Gábor Erdős, Zoltán Istenes

AI总结:

针对机器人操作中抓取位姿估计的数据短缺问题,提出两种基于视觉的多目标抓取位姿估计模型(MOGPE)及基于域随机化的sim2real方法,在真实实验中取得80%和96.67%的成功率,为工业应用提供高效数据生成与训练框架。

摘要:

自适应机器人在实现真正共创的网络物理系统中发挥着重要作用。在机器人操作任务中,最大的挑战之一是估计给定工件的位姿。尽管最近基于深度学习的模型显示出良好的效果,但它们需要庞大的数据集进行训练。本文提出了两种基于视觉的多目标抓取位姿估计模型(MOGPE),即MOGPE Real-Time和MOGPE High-Precision。此外,提出了一种基于域随机化的sim2real方法,以缩小现实差距并克服数据短缺问题。在真实的机器人抓取与放置实验中,我们的方法分别使用MOGPE Real-Time和MOGPE High-Precision模型取得了80%和96.67%的成功率。我们的框架为快速数据生成和模型训练提供了工业工具,且仅需最少的特定领域数据。

英文摘要:

Adaptive robotics plays an essential role in achieving truly co-creative cyber physical systems. In robotic manipulation tasks, one of the biggest challenges is to estimate the pose of given workpieces. Even though the recent deep-learning-based models show promising results, they require an immense dataset for training. In this paper, two vision-based, multi-object grasp pose estimation models (MOGPE), the MOGPE Real-Time and the MOGPE High-Precision are proposed. Furthermore, a sim2real method based on domain randomization to diminish the reality gap and overcome the data shortage. Our methods yielded an 80% and a 96.67% success rate in a real-world robotic pick-and-place experiment, with the MOGPE Real-Time and the MOGPE High-Precision model respectively. Our framework provides an industrial tool for fast data generation and model training and requires minimal domain-specific data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑