DeepQ Stepper: A framework for reactive dynamic walking on uneven terrain
DeepQ Stepper: A framework for reactive dynamic walking on uneven terrain
复制标题
DOI：
10.1109/icra48506.2021.9562093
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Avadesh Meduri;M. Khadiv;L. Righetti
中科院分区：
文献类型：
--
作者：
Avadesh Meduri;M. Khadiv;L. Righetti
由于非线性动力学模型的捕获区域计算困难，双足机器人的响应式步进和推力恢复通常局限于平坦地形。在本文中，我们通过提出一种新的3D反应步进器DeepQ步进器来解决这一限制，该步进器可以使用强化学习近似学习简化和完整机器人动态模型的3D捕获区域，然后可用于找到最佳步骤。该步进器可以考虑机器人的整个动力学，这在大多数反应式步进器中被忽略，从而导致性能的显着改善。DeepQ步进器可以处理有障碍物的非凸地形，在跟踪不同速度的同时在受限的表面上行走，并以恒定的低计算成本从外部干扰中恢复。
Reactive stepping and push recovery for biped robots is often restricted to flat terrains because of the difficulty in computing capture regions for nonlinear dynamic models. In this paper, we address this limitation by proposing a novel 3D reactive stepper, the DeepQ stepper, that can approximately learn the 3D capture regions of both simplified and full robot dynamic models using reinforcement learning, which can then be used to find optimal steps. The stepper can take into account the entire dynamics of the robot, ignored in most reactive steppers, leading to a significant improvement in performance. The DeepQ stepper can handle nonconvex terrain with obstacles, walk on restricted surfaces like stepping stones while tracking different velocities, and recover from external disturbances for a constant low computational cost.