Real-Time Neural MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms

• Published in: IEEE robotics and automation letters Vol. 8; no. 4; pp. 2397 - 2404
• Main Authors: Salzmann, Tim, Kaufmann, Elia, Arrizabalaga, Jon, Pavone, Marco, Scaramuzza, Davide, Ryll, Markus
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: aerial systems: Mechanics and control; Aerodynamics; Complexity; Computational modeling; Computer architecture; Control systems; Deep learning; Dynamics; Embedded systems; First principles; Iterative methods; Machine learning; Machine learning for robot control; model learning for control; Neural networks; Optimization; Predictive control; Predictive models; Real time operation; Real-time systems; Rotary wing aircraft; Tracking errors; Vehicle dynamics; Windows (intervals)
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2023.3246839

Model Predictive Control (MPC) has become a popular framework in embedded control for high-performance autonomous systems. However, to achieve good control performance using MPC, an accurate dynamics model is key. To maintain real-time operation, the dynamics models used on embedded systems have been limited to simple first-principle models, which substantially limits their representative power. In contrast to such simple models, machine learning approaches, specifically neural networks, have been shown to accurately model even complex dynamic effects, but their large computational complexity hindered combination with fast real-time iteration loops. With this work, we present Real-time Neural MPC , a framework to efficiently integrate large, complex neural network architectures as dynamics models within a model-predictive control pipeline. Our experiments, performed in simulation and the real world onboard a highly agile quadrotor platform, demonstrate the capabilities of the described system to run learned models with, previously infeasible, large modeling capacity using gradient-based online optimization MPC. Compared to prior implementations of neural networks in online optimization MPC we can leverage models of over 4000 times larger parametric capacity in a 50 Hz real-time window on an embedded platform. Further, we show the feasibility of our framework on real-world problems by reducing the positional tracking error by up to 82% when compared to state-of-the-art MPC approaches without neural network dynamics.