arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.01360cs.RO
收藏

基于深度强化学习与最优控制的可扩展视觉伺服研究

Toward Scalable Visual Servoing Using Deep Reinforcement Learning and Optimal Control

Simon Fraser University(西蒙弗雷泽大学);University of Regina(里贾纳大学)

Salar Asayesh, Hossein Sheikhi Darani, Mo chen, Mehran Mehrandezh, Kamal Gupta

AI总结:

针对传统视觉伺服收敛区域有限、深度学习方法可扩展性不足的问题,提出结合深度强化学习与最优控制的混合策略,在7自由度机械臂上实现高收敛精度,且可跨千余场景扩展、泛化未知数据集,适配真实噪声遮挡环境。

摘要:

经典基于像素的视觉伺服(VS)方法精度高,但受优化非线性限制,收敛区域有限。现代基于深度学习的视觉伺服方法克服了传统视觉问题,但缺乏可扩展性,仅能在有限场景下训练。本文提出一种结合深度强化学习(DRL)与最优控制的混合视觉伺服策略,同时提升收敛区域与可扩展性。该方法的DRL模块分别处理表征学习与策略学习,以增强可扩展性、泛化性、学习效率并简化域适应;最优控制部分则保证了高终点精度。我们在7自由度机械臂上验证了方法的性能,实现了高收敛率与极低的末端定位误差。值得注意的是,该方法在超过1000个不同场景中展现出可扩展性,还能泛化到未见过的数据集。最后,我们验证了方法的实际应用价值,通过单次域迁移学习在含噪声与遮挡的环境中展现出适应性。真实机器人实验可查看:https://sites.google.com/view/vsls。

英文摘要:

Classical pixel-based Visual Servoing (VS) approaches offer high accuracy but suffer from a limited convergence area due to optimization nonlinearity. Modern deep learning-based VS methods overcome traditional vision issues but lack scalability, requiring training on limited scenes. This paper proposes a hybrid VS strategy utilizing Deep Reinforcement Learning (DRL) and optimal control to enhance both convergence area and scalability. The DRL component of our approach separately handles representation and policy learning to enhance scalability, generalizability, learning efficiency and ease domain adaptation. Moreover, the optimal control part ensures high end-point accuracy. Our method showcases remarkable achievements in terms of high convergence rates and minimal end-positioning errors using a 7-DOF manipulator. Importantly, it exhibits scalability across more than 1000 distinct scenes. Furthermore, we demonstrate its capacity for generalization to previously unseen datasets. Lastly, we illustrate the real-world applicability of our approach, highlighting its adaptability through single-shot domain transfer learning in environments with noise and occlusions. Real-robot experiments can be found at \url{https://sites.google.com/view/vsls}.

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。

↑