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 2110.01894cs.LGcs.RO
收藏

结合物理学和深度学习来学习连续时间动力学模型

Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models

Technical University of Darmstadt(达姆施塔特工业大学)

Michael Lutter, Jan Peters

摘要:

深度学习已广泛用于机器人的学习算法中。深度网络的一个缺点是,这些网络是黑箱表示。因此,学习的近似值忽略了物理学或机器人学的现有知识。特别是对于学习动态模型,这些黑盒模型是不可取的,因为基本原理已经很好地理解,标准的深度网络可以学习违反这些原理的动态。为了使用深度网络学习动力学模型,以保证物理上合理的动力学,我们引入了物理启发的深度网络,将物理学的第一原理与深度学习相结合。我们将拉格朗日力学纳入模型学习中,以便所有近似模型都遵守物理定律并保持能量。深度拉格朗日网络(DeLaN)使用两个网络参数化系统能量。通过最小化Euler-Lagrange微分方程的平方残差得到的参数。因此,所得到的模型不需要特定的知识的个别系统,是可解释的,并可以用作正向,反向和能量模型。以前,这些属性仅在使用需要运动学结构的知识的系统辨识技术时获得。我们将DeLaN应用于学习动力学模型,并将这些模型应用于控制模拟和物理刚体系统。结果表明,所提出的方法获得的动力学模型,可应用于物理系统的实时控制。与标准的深度网络相比,物理启发的模型可以更好地学习模型并捕获动态的底层结构。

英文摘要:

Deep learning has been widely used within learning algorithms for robotics. One disadvantage of deep networks is that these networks are black-box representations. Therefore, the learned approximations ignore the existing knowledge of physics or robotics. Especially for learning dynamics models, these black-box models are not desirable as the underlying principles are well understood and the standard deep networks can learn dynamics that violate these principles. To learn dynamics models with deep networks that guarantee physically plausible dynamics, we introduce physics-inspired deep networks that combine first principles from physics with deep learning. We incorporate Lagrangian mechanics within the model learning such that all approximated models adhere to the laws of physics and conserve energy. Deep Lagrangian Networks (DeLaN) parametrize the system energy using two networks. The parameters are obtained by minimizing the squared residual of the Euler-Lagrange differential equation. Therefore, the resulting model does not require specific knowledge of the individual system, is interpretable, and can be used as a forward, inverse, and energy model. Previously these properties were only obtained when using system identification techniques that require knowledge of the kinematic structure. We apply DeLaN to learning dynamics models and apply these models to control simulated and physical rigid body systems. The results show that the proposed approach obtains dynamics models that can be applied to physical systems for real-time control. Compared to standard deep networks, the physics-inspired models learn better models and capture the underlying structure of the dynamics.

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。

↑