Using Data-Driven Domain Randomization to Transfer Robust Control Policies to Mobile Robots
Using Data-Driven Domain Randomization to Transfer Robust Control Policies to Mobile Robots
复制标题
DOI：
10.1109/icra.2019.8794343
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Matthew Sheckells;Gowtham Garimella;Subhransu Mishra;Marin Kobilarov
中科院分区：
文献类型：
--
作者：
Matthew Sheckells;Gowtham Garimella;Subhransu Mishra;Marin Kobilarov
这项工作开发了一种技术，使用机器人的运动轨迹来创建高质量的随机动力学模型，然后在仿真中利用该模型来训练具有相关性能保证的控制策略。我们通过收集1/5比例敏捷地面车辆的动力学数据，拟合随机动力学模型，并在模拟中训练策略，在躲避障碍物的情况下，以6.5m/S的速度绕过椭圆形赛道，从而演示了这一想法。我们证明了控制策略可以在预测性能损失很小的情况下转移回真实车辆。我们将其与使用简单的解析汽车模型来训练策略的方法进行了比较，结果表明，使用从数据中学习的具有随机性的模型可以在轨迹跟踪精度和碰撞概率方面获得更高的性能。此外，我们的经验表明，当执行使用适合车辆数据的深度随机动力学模型优化的策略时，模拟得出的性能保证转移到实际车辆上。
This work develops a technique for using robot motion trajectories to create a high quality stochastic dynamics model that is then leveraged in simulation to train control policies with associated performance guarantees. We demonstrate the idea by collecting dynamics data from a 1/5 scale agile ground vehicle, fitting a stochastic dynamics model, and training a policy in simulation to drive around an oval track at up to 6.5 m/s while avoiding obstacles. We show that the control policy can be transferred back to the real vehicle with little loss in predicted performance. We compare this to an approach that uses a simple analytic car model to train a policy in simulation and show that using a model with stochasticity learned from data leads to higher performance in terms of trajectory tracking accuracy and collision probability. Furthermore, we show empirically that simulation-derived performance guarantees transfer to the actual vehicle when executing a policy optimized using a deep stochastic dynamics model fit to vehicle data.