arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.06282cs.ROcs.AI
收藏

随机化对机器人操作任务中仿真到现实转移的影响分析

Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks

Department of Informatics, Technical University of Munich(慕尼黑技术大学信息学院);Rosenheim University of Applied Sciences(罗森海姆应用技术大学)

Josip Josifovski, Mohammadhossein Malmir, Noah Klarmann, Bare Luka Žagar, Nicolás Navarro-Guerrero, Alois Knoll

AI总结:

本文提出一个可复现的实验框架,比较四种随机化策略在仿真和现实中的表现,发现更多随机化有助于仿真到现实转移,但可能影响仿真中策略的学习能力。

摘要:

随机化目前是仿真到现实转移中用于数据驱动学习算法的常用方法。然而,大多数仿真到现实研究仅针对特定随机化技术并在高度定制的机器人系统上报告结果,这使得系统评估不同随机化方法变得困难。为了解决这个问题,我们定义了一个易于复现的实验设置,用于机器人抓取和平衡操作任务,可作为比较基准。我们比较了四种随机化策略与三种随机参数在仿真和真实机器人上的表现。我们的结果表明,更多的随机化有助于仿真到现实转移,但可能也会损害算法在仿真中找到良好策略的能力。完全随机化的仿真和微调显示了不同的结果,并且比其他测试的方法在真实机器人上表现更好。

英文摘要:

Randomization is currently a widely used approach in Sim2Real transfer for data-driven learning algorithms in robotics. Still, most Sim2Real studies report results for a specific randomization technique and often on a highly customized robotic system, making it difficult to evaluate different randomization approaches systematically. To address this problem, we define an easy-to-reproduce experimental setup for a robotic reach-and-balance manipulator task, which can serve as a benchmark for comparison. We compare four randomization strategies with three randomized parameters both in simulation and on a real robot. Our results show that more randomization helps in Sim2Real transfer, yet it can also harm the ability of the algorithm to find a good policy in simulation. Fully randomized simulations and fine-tuning show differentiated results and translate better to the real robot than the other approaches tested.

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。

↑