Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models

Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models
复制标题

用可微接触模型扩展拉格朗日和哈密顿神经网络

DOI:
--
复制
发表时间:
2021
期刊:
Neural Information Processing Systems
影响因子:
--
通讯作者:
Amit Chakraborty
Amit Chakraborty
中科院分区:
--
文献类型:
--
作者:
Yaofeng Desmond Zhong;Biswadip Dey;Amit Chakraborty

文献摘要

参考文献

被引文献

相似文献

适当的归纳偏差的结合在从数据中学习动态方面起着关键作用。越来越多的工作一直在探索通过将拉格朗日或哈密顿动力学编码到神经网络架构中来加强学习动力学中的能量守恒的方法。这些现有的方法是基于微分方程,不允许状态的不连续性,从而限制了人们可以学习的系统的类别。然而,在现实中,大多数物理系统,如腿式机器人和机器人操纵器,涉及接触和碰撞,这引入了状态的不连续性。在本文中,我们介绍了一个可微接触模型,它可以捕捉接触力学:无摩擦/摩擦,以及弹性/非弹性。该模型还可以适应不等式约束,例如对关节角度的限制。所提出的接触模型扩展了拉格朗日和哈密顿神经网络的范围,允许同时学习的接触和系统属性。我们证明了这个框架上的一系列具有挑战性的2D和3D物理系统具有不同的恢复和摩擦系数。学习的动态可以用作下游基于梯度的优化任务(例如规划和控制)的可微物理模拟器。
The incorporation of appropriate inductive bias plays a critical role in learning dynamics from data. A growing body of work has been exploring ways to enforce energy conservation in the learned dynamics by encoding Lagrangian or Hamiltonian dynamics into the neural network architecture. These existing approaches are based on differential equations, which do not allow discontinuity in the states and thereby limit the class of systems one can learn. However, in reality, most physical systems, such as legged robots and robotic manipulators, involve contacts and collisions, which introduce discontinuities in the states. In this paper, we introduce a differentiable contact model, which can capture contact mechanics: frictionless/frictional, as well as elastic/inelastic. This model can also accommodate inequality constraints, such as limits on the joint angles. The proposed contact model extends the scope of Lagrangian and Hamiltonian neural networks by allowing simultaneous learning of contact and system properties. We demonstrate this framework on a series of challenging 2D and 3D physical systems with different coefficients of restitution and friction. The learned dynamics can be used as a differentiable physics simulator for downstream gradient-based optimization tasks, such as planning and control.
DOI: --
发表时间: 2020-06
期刊: ArXiv
影响因子: --
作者:
Shuqi Yang;Xingzhe He;Bo Zhu
通讯作者: Shuqi Yang;Xingzhe He;Bo Zhu
用于动力外骨骼的虚拟弹簧和阻尼器的能量整形控制
DOI: 10.1109/cdc40024.2019.9029624
发表时间: 2019
期刊: IEEE Conference on Decision and Control
影响因子: --
作者:
Lin, Jianping;Divekar, Nikhil;Lv, Ge;Gregg, Robert D.
通讯作者: Gregg, Robert D.
学习通过可微分物理模拟滑动未知物体
DOI: 10.15607/rss.2020.xvi.099
发表时间: 2020
期刊: Robotics science and systems
影响因子: --
作者:
Song, Changkyu;Boularias, Abdeslam
通讯作者: Boularias, Abdeslam
DOI: 10.1021/acscatal.5b02014
发表时间: 2016-01-01
期刊: ACS CATALYSIS
影响因子: 12.9
作者:
Nicholls, Thomas P.;Constable, Grace E.;Bissember, Alex C.
通讯作者: Bissember, Alex C.
可解释的多项式神经常微分方程。
DOI: 10.1063/5.0130803
发表时间: 2023
期刊: Chaos (Woodbury, N.Y.)
影响因子: --
作者:
Fronk,Colby;Petzold,Linda
通讯作者: Petzold,Linda