论文标题
物理嵌入了神经网络车辆模型以及使用潜在功能的风险意识自主驾驶中的应用
Physics Embedded Neural Network Vehicle Model and Applications in Risk-Aware Autonomous Driving Using Latent Features
论文作者
论文摘要
已经使用基于物理学的模型对非全面车辆运动进行了广泛的研究。使用这些模型时，使用线性轮胎模型来解释车轮/接地相互作用时的常见方法，因此可能无法在各种环境下完全捕获非线性和复杂动力学。另一方面，神经网络模型已在该域中广泛使用，证明了功能强大的近似功能。但是，这些黑盒学习策略完全放弃了现有的知名物理知识。在本文中，我们无缝将深度学习与完全不同的物理模型相结合，以赋予神经网络具有可用的先验知识。所提出的模型比大范围比香草神经网络模型显示出更好的概括性能。我们还表明，我们的模型的潜在特征可以准确地表示侧向轮胎力，而无需进行任何其他训练。最后，我们使用从潜在特征得出的本体感受信息开发了一种风险感知的模型预测控制器。我们在未知摩擦下的两个自动驾驶任务中验证了我们的想法，表现优于基线控制框架。
Non-holonomic vehicle motion has been studied extensively using physics-based models. Common approaches when using these models interpret the wheel/ground interactions using a linear tire model and thus may not fully capture the nonlinear and complex dynamics under various environments. On the other hand, neural network models have been widely employed in this domain, demonstrating powerful function approximation capabilities. However, these black-box learning strategies completely abandon the existing knowledge of well-known physics. In this paper, we seamlessly combine deep learning with a fully differentiable physics model to endow the neural network with available prior knowledge. The proposed model shows better generalization performance than the vanilla neural network model by a large margin. We also show that the latent features of our model can accurately represent lateral tire forces without the need for any additional training. Lastly, We develop a risk-aware model predictive controller using proprioceptive information derived from the latent features. We validate our idea in two autonomous driving tasks under unknown friction, outperforming the baseline control framework.
