Learning quadrupedal locomotion over challenging terrain
Learning quadrupedal locomotion over challenging terrain
复制标题
DOI：
10.1126/scirobotics.abc5986
复制
发表时间：
2020-10-21
期刊：
影响因子：
25
通讯作者：
Hutter, Marco
中科院分区：
文献类型：
--
作者：
Lee, Joonho;Hwangbo, Jemin;Hutter, Marco
腿部运动可以将机器人的操作领域扩展到地球上一些最具挑战性的环境中。然而，传统的控制器的腿运动是基于精心设计的状态机，明确触发执行的运动原语和反射。这些设计增加了复杂性，但缺乏动物运动的通用性和鲁棒性。在这里，我们提出了一个强大的控制器盲目四足运动在具有挑战性的自然环境。我们的方法结合了本体感觉反馈的运动控制，并演示了零杆泛化从模拟到自然环境。在仿真中采用强化学习方法对控制器进行训练。该控制器由作用于本体感受信号流的神经网络策略驱动。该控制器在训练过程中从未遇到过的条件下保持其鲁棒性：可变形地形，如泥和雪，动态立足点，如碎石，以及地上障碍物，如厚厚的植被和喷涌的水。所提出的工作表明，在自然环境中的鲁棒运动可以通过在简单的域中训练来实现。
Legged locomotion can extend the operational domain of robots to some of the most challenging environments on Earth. However, conventional controllers for legged locomotion are based on elaborate state machines that explicitly trigger the execution of motion primitives and reflexes. These designs have increased in complexity but fallen short of the generality and robustness of animal locomotion. Here, we present a robust controller for blind quadrupedal locomotion in challenging natural environments. Our approach incorporates proprioceptive feedback in locomotion control and demonstrates zero-shot generalization from simulation to natural environments. The controller is trained by reinforcement learning in simulation. The controller is driven by a neural network policy that acts on a stream of proprioceptive signals. The controller retains its robustness under conditions that were never encountered during training: deformable terrains such as mud and snow, dynamic footholds such as rubble, and overground impediments such as thick vegetation and gushing water. The presented work indicates that robust locomotion in natural environments can be achieved by training in simple domains.