论文标题
联络网：学习不连续的接触动力学，并具有平稳的隐式表示
ContactNets: Learning Discontinuous Contact Dynamics with Smooth, Implicit Representations
论文作者
论文摘要
学习机器人动力学的通用方法假设运动是连续的，从而导致不现实的模型预测受到不连续影响和陈述行为的系统。在这项工作中，我们通过对接触诱导的不连续性固有的结构进行平稳而隐含的编码来解决这一冲突。我们的方法，联系人网络学习了体内签名距离和联系框架雅各布族人的参数化，该表示与机器人技术的许多仿真，控制和计划环境兼容。此外，我们还需要通过僵硬或非平滑动力学来区分以互补性和最大耗散原则启发的新型损失功能。我们的方法在60秒的现实世界数据中进行训练时，可以预测现实的影响，非渗透和陈述。
Common methods for learning robot dynamics assume motion is continuous, causing unrealistic model predictions for systems undergoing discontinuous impact and stiction behavior. In this work, we resolve this conflict with a smooth, implicit encoding of the structure inherent to contact-induced discontinuities. Our method, ContactNets, learns parameterizations of inter-body signed distance and contact-frame Jacobians, a representation that is compatible with many simulation, control, and planning environments for robotics. We furthermore circumvent the need to differentiate through stiff or non-smooth dynamics with a novel loss function inspired by the principles of complementarity and maximum dissipation. Our method can predict realistic impact, non-penetration, and stiction when trained on 60 seconds of real-world data.
