arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.08539cs.ROcs.LGcs.SYeess.SY
收藏

刚体动力学的自动微分与连续灵敏度分析

Automatic Differentiation and Continuous Sensitivity Analysis of Rigid Body Dynamics

University of Southern California(南加州大学);Columbia University(哥伦比亚大学)

David Millard, Eric Heiden, Shubham Agrawal, Gaurav S. Sukhatme

摘要:

实现智能行为的一个关键因素是物理理解,使机器人能够在动态环境中推理其行为的影响。已经提出了几种方法来从告知基于模型的控制算法的数据中学习动态模型。虽然这种基于学习的方法可以对局部观察到的行为进行建模,但它们无法推广到更复杂的动态和长时间范围内。在这项工作中,我们介绍了一个微分物理模拟器的刚体动力学。利用微分方程积分和梯度计算的各种技术,我们比较了不同的参数估计方法,使我们能够推断出与物理系统的估计和控制相关的模拟参数。在轨迹优化的背景下,我们引入了一个闭环模型预测控制算法,通过经验推断的仿真参数,同时实现成本最小化的性能。

英文摘要:

A key ingredient to achieving intelligent behavior is physical understanding that equips robots with the ability to reason about the effects of their actions in a dynamic environment. Several methods have been proposed to learn dynamics models from data that inform model-based control algorithms. While such learning-based approaches can model locally observed behaviors, they fail to generalize to more complex dynamics and under long time horizons. In this work, we introduce a differentiable physics simulator for rigid body dynamics. Leveraging various techniques for differential equation integration and gradient calculation, we compare different methods for parameter estimation that allow us to infer the simulation parameters that are relevant to estimation and control of physical systems. In the context of trajectory optimization, we introduce a closed-loop model-predictive control algorithm that infers the simulation parameters through experience while achieving cost-minimizing performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑