Learning dexterous in-hand manipulation
Learning dexterous in-hand manipulation
复制标题
DOI：
10.1177/0278364919887447
复制
发表时间：
2019-11-18
影响因子：
9.2
通讯作者：
Zaremba, Wojciech
中科院分区：
文献类型：
--
作者：
Andrychowicz, Marcin;Baker, Bowen;Zaremba, Wojciech
我们使用强化学习（RL）来学习灵巧的手操作策略，该策略可以在物理阴影灵巧的手上执行基于视觉的物体重新定向。训练是在模拟环境中进行的，在模拟环境中，我们随机化了系统的许多物理特性，如摩擦系数和物体的外观。我们的策略转移到物理机器人上，尽管完全是在模拟中训练的。我们的方法不依赖于任何人类的演示，但是在人类操作中发现的许多行为是自然出现的，包括手指绑带、多指协调和控制重力的使用。我们的结果是使用与OpenAI Five训练相同的分布式RL系统获得的。我们还提供了我们的结果的视频：。
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system such as friction coefficients and an object's appearance. Our policies transfer to the physical robot despite being trained entirely in simulation. Our method does not rely on any human demonstrations, but many behaviors found in human manipulation emerge naturally, including finger gaiting, multi-finger coordination, and the controlled use of gravity. Our results were obtained using the same distributed RL system that was used to train OpenAI Five. We also include a video of our results: .