Elastica: A Compliant Mechanics Environment for Soft Robotic Control
Elastica: A Compliant Mechanics Environment for Soft Robotic Control
复制标题
DOI：
10.1109/lra.2021.3063698
复制
发表时间：
2021-04-01
影响因子：
5.2
通讯作者：
Gazzola, Mattia
中科院分区：
文献类型：
--
作者：
Naughton, Noel;Sun, Jiarui;Gazzola, Mattia
软体机器人是出了名的难以控制。这部分是由于缺乏能够捕捉其复杂连续介质力学的模型和模拟器，导致缺乏充分利用身体顺应性的控制方法。目前可用的方法要么太计算要求或过于简单的物理假设，导致缺乏可用的仿真资源，用于开发这样的控制方案。为了解决这个问题，我们引入了Elastica，这是一个开源的仿真环境，可以对可以弯曲、扭曲、剪切和拉伸的柔软细长杆的动力学进行建模。我们将Elastica与五种最先进的强化学习（RL）算法（TRPO，PPO，DDPG，TD3和SAC）相结合。我们成功地证明了分布式，动态控制的软机械臂在四个场景中，既有大的动作空间，RL学习是困难的，和小的动作空间，RL演员必须学会与其环境进行交互。培训集中在1 000万项政策评价中，对学到的政策进行近实时评价。
Soft robots are notoriously hard to control. This is partly due to the scarcity of models and simulators able to capture their complex continuum mechanics, resulting in a lack of control methodologies that take full advantage of body compliance. Currently available methods are either too computational demanding or overly simplistic in their physical assumptions, leading to a paucity of available simulation resources for developing such control schemes. To address this, we introduce Elastica, an open-source simulation environment modeling the dynamics of soft, slender rods that can bend, twist, shear, and stretch. We couple Elastica with five state-of-the-art reinforcement learning (RL) algorithms (TRPO, PPO, DDPG, TD3, and SAC). We successfully demonstrate distributed, dynamic control of a soft robotic arm in four scenarios with both large action spaces, where RL learning is difficult, and small action spaces, where the RL actor must learn to interact with its environment. Training converges in 10 million policy evaluations with near real-time evaluation of learned policies.