This work concerns the application of physics-informed neural networks to the modeling and control of complex robotic systems. Achieving this goal required extending Physics Informed Neural Networks to handle non-conservative effects. We propose to combine these learned models with model-based controllers originally developed with first-principle models in mind. By combining standard and new techniques, we can achieve precise control performance while proving theoretical stability bounds. These validations include real-world experiments of motion prediction with a soft robot and of trajectory tracking with a Franka Emika manipulator.

翻译：本文研究了将物理知识融入神经网络应用于复杂机器人系统建模与控制的问题。为实现这一目标，我们扩展了物理信息神经网络以处理非保守效应。提出将这些学习模型与原本基于第一性原理设计的模型预测控制器相结合。通过融合标准方法与新技术，在证明理论稳定性边界的同时实现精确控制性能。验证工作包括基于软体机器人的运动预测实验以及Franka Emika机械臂的轨迹跟踪实验。