Learning Whole-Body Motor Skills for Humanoids
Learning Whole-Body Motor Skills for Humanoids
复制标题
DOI：
10.1109/humanoids.2018.8625045
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Chuanyu Yang;Kai Yuan;W. Merkt;T. Komura;S. Vijayakumar;Zhibin Li
中科院分区：
文献类型：
--
作者：
Chuanyu Yang;Kai Yuan;W. Merkt;T. Komura;S. Vijayakumar;Zhibin Li
本文提出了深度强化学习的分层框架，该框架获得各种推力恢复和平衡行为的运动技能，即脚踝、臀部、脚倾斜和迈步策略。该策略在物理模拟器中进行训练，具有机器人模型的真实设置和低级阻抗控制，可以轻松地将学到的技能转移到真实的机器人上。相对于传统方法的优点是将高级规划器和反馈控制集成在一个一致的策略网络中，该网络对于学习针对任意位置（例如腿、躯干）的未知扰动的多功能平衡和恢复运动是通用的。此外，所提出的框架允许通过许多最先进的学习算法快速学习策略。通过将我们的学习结果与文献中预编程的专用控制器的研究进行比较，自学技能在干扰抑制方面具有可比性，但具有产生广泛的自适应、多功能和鲁棒行为的额外优势。
This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained in a physics simulator with realistic setting of robot model and low-level impedance control that are easy to transfer the learned skills to real robots. The advantage over traditional methods is the integration of high-level planner and feedback control all in one single coherent policy network, which is generic for learning versatile balancing and recovery motions against unknown perturbations at arbitrary locations (e.g., legs, torso). Furthermore, the proposed framework allows the policy to be learned quickly by many state-of-the-art learning algorithms. By comparing our learned results to studies of preprogrammed, special-purpose controllers in the literature, self-learned skills are comparable in terms of disturbance rejection but with additional advantages of producing a wide range of adaptive, versatile and robust behaviors.