利用人类知识学习仿人机器人的自然运动行为（CS R）---用户7305506

本文提出了一个新的学习框架，该框架利用了模仿学习，深度强化学习和控制理论中的知识，以实现对类人动物而言自然，动态和强大的人性化运动。我们提出了新颖的方法来引入人为偏见，即运动捕获数据和特殊的Multi-Expert网络结构。我们使用Multi-Expert网络结构来平滑地融合行为特征，并使用增强的奖励设计来完成任务和模仿奖励。通过使用常规人形机器人控制的基本概念，我们的奖励设计是可组合的，可调的和可解释的。我们严格地验证和基准化了学习框架，该框架在各种测试场景中始终产生强大的运动行为。此外，我们展示了在存在干扰（例如地形不规则和外部推动）的情况下学习强大而通用的策略的能力。

原文标题：Learning natural locomotion behaviors for humanoid robots using human knowledge

原文：This paper presents a new learning framework that leverages the knowledge from imitation learning, deep reinforcement learning, and control theories to achieve human-style locomotion that is natural, dynamic, and robust for humanoids. We proposed novel approaches to introduce human bias, i.e. motion capture data and a special Multi-Expert network structure. We used the Multi-Expert network structure to smoothly blend behavioral features, and used the augmented reward design for the task and imitation rewards. Our reward design is composable, tunable, and explainable by using fundamental concepts from conventional humanoid control. We rigorously validated and benchmarked the learning framework which consistently produced robust locomotion behaviors in various test scenarios. Further, we demonstrated the capability of learning robust and versatile policies in the presence of disturbances, such as terrain irregularities and external pushes.

原文作者：Chuanyu Yang, Kai Yuan, Shuai Heng, Taku Komura, Zhibin Li

原文地址：https://arxiv.org/abs/2005.10195