论文标题
通过神经网络增强可区分的模拟器，以缩小SIM2REAL差距
Augmenting Differentiable Simulators with Neural Networks to Close the Sim2Real Gap
论文作者
论文摘要
我们为铰接的刚体动力学提供了可区分的仿真体系结构，该构图可以在计算的任何时候使用神经网络的分析模型增强。通过基于梯度的优化，对模拟参数和网络权重的识别在现实世界数据集和SIM2SIM传输应用程序上的初步实验中有效地执行，而通过随机搜索方法克服了较差的本地Optima。
We present a differentiable simulation architecture for articulated rigid-body dynamics that enables the augmentation of analytical models with neural networks at any point of the computation. Through gradient-based optimization, identification of the simulation parameters and network weights is performed efficiently in preliminary experiments on a real-world dataset and in sim2sim transfer applications, while poor local optima are overcome through a random search approach.
