Learn Proportional Derivative Controllable Latent Space from Pixels
Learn Proportional Derivative Controllable Latent Space from Pixels
复制标题
DOI：
10.1109/case49997.2022.9926535
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Weiyao Wang;Marin Kobilarov;Gregory Hager
中科院分区：
文献类型：
--
作者：
Weiyao Wang;Marin Kobilarov;Gregory Hager
基于像素的潜在空间动力学模型的最新进展显示了基于视觉的模型预测控制（MPC）的可喜进展。然而，在真实的时间中执行MPC可能是具有挑战性的，因为其在每个时间步长中的密集计算成本。我们建议引入额外的学习目标，以执行学习的潜在空间是比例导数可控的。在执行时，简单的PD控制器可以直接应用于潜在的空间编码的像素，产生简单而有效的控制系统的视觉观察。我们表明，我们的方法优于基线方法，在各种环境中产生强大的目标达到和轨迹跟踪。
Recent advances in latent space dynamics model from pixels show promising progress in vision-based model predictive control (MPC). However, executing MPC in real time can be challenging due to its intensive computational cost in each timestep. We propose to introduce additional learning objectives to enforce that the learned latent space is proportional derivative controllable. In execution time, the simple PD-controller can be applied directly to the latent space encoded from pixels, to produce simple and effective control to systems with visual observations. We show that our method outperforms baseline methods to produce robust goal reaching and trajectory tracking in various environments.