Incorporating prior knowledge of physics laws and structural properties of dynamical systems into the design of deep learning architectures has proven to be a powerful technique for improving their computational efficiency and generalization capacity. Learning accurate models of robot dynamics is critical for safe and stable control. Autonomous mobile robots, including wheeled, aerial, and underwater vehicles, can be modeled as controlled Lagrangian or Hamiltonian rigid-body systems evolving on matrix Lie groups. In this paper, we introduce a new structure-preserving deep learning architecture, the Lie group Forced Variational Integrator Network (LieFVIN), capable of learning controlled Lagrangian or Hamiltonian dynamics on Lie groups, either from position-velocity or position-only data. By design, LieFVINs preserve both the Lie group structure on which the dynamics evolve and the symplectic structure underlying the Hamiltonian or Lagrangian systems of interest. The proposed architecture learns surrogate discrete-time flow maps allowing accurate and fast prediction without numerical-integrator, neural-ODE, or adjoint techniques, which are needed for vector fields. Furthermore, the learnt discrete-time dynamics can be utilized with computationally scalable discrete-time (optimal) control strategies.
翻译:将物理法学和动态系统结构特性的先前知识纳入深层学习结构的设计中,已证明是提高计算效率和普及能力的有力技术。学习机器人动态的准确模型对于安全和稳定的控制至关重要。自动移动机器人,包括轮式、空中和水下飞行器,可以仿照在矩阵Libe组上演进的Lagrangian或汉密尔顿硬体系统。在本文中,我们引入了一个新的结构保存深度学习结构结构结构的新结构,即Lie Group强迫变异集成器网络(LieFVIN),它能够从位置速度或仅以位置为主的数据中学习受控制的Lagrangian或汉密尔顿群的动态模型。根据设计,LieFVIN可以保存动态演变所依赖的利组结构以及汉密尔密尔顿或拉格朗热系统所依赖的静脉冲结构。在本文件中学习了一种结构保护离散时间流图,以便能够准确和快速地预测Ligrang-Intrator、线-mode或相连接技术,而这些技术是矢量载场域场域域域域域域域域域域域域域域域域域域域所需的。此外,学习了离式动态分析战略,并用。