Deep Learning Alternative to Explicit Model Predictive Control for Unknown Nonlinear Systems

Abstract

We present differentiable predictive control (DPC) as a deep learning-based alternative to the explicit model predictive control (MPC) for unknown nonlinear systems. In the DPC framework, a neural state-space model is learned from time-series measurements of the system dynamics. The neural control policy is then optimized via stochastic gradient descent approach by differentiating the MPC loss function through the closed-loop system dynamics model. The proposed DPC method learns model-based control policies with state and input constraints, while supporting time-varying references and constraints. In embedded implementation using a Raspberry-Pi platform, we experimentally demonstrate that it is possible to train constrained control policies purely based on the measurements of the unknown nonlinear system. We compare the control performance of the DPC method against explicit MPC and report efficiency gains in online computational demands, memory requirements, policy complexity, and construction time. In particular, we show that our method scales linearly compared to exponential scalability of the explicit MPC solved via multiparametric programming.

References in corpus (15)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Hamiltonian Neural Networks
• Learning Latent Dynamics for Planning from Pixels
• Differentiable MPC for End-to-end Planning and Control
• Input Convex Neural Networks
• Neural Lyapunov Control
• Deep Learning-Based Model Predictive Control for Resonant Power Converters
• Nonlinear Systems Identification Using Deep Dynamic Neural Networks
• DC3: A learning method for optimization with hard constraints
• Constrained Neural Ordinary Differential Equations with Stability Guarantees
• Linearly Constrained Neural Networks
• A Neural Network Architecture to Learn Explicit MPC Controllers from Data
• Structured Neural Network Dynamics for Model-based Control
• A Differentiable Physics Engine for Deep Learning in Robotics