Quantized Deep Path-following Control on a Microcontroller

TL;DR

This paper demonstrates that deep neural networks can effectively implement predictive path-following control on microcontrollers, addressing quantization challenges with a post-stabilization method, enabling real-time autonomous motion control on low-cost hardware.

Contribution

It introduces a novel approach to approximate dynamic MPFC feedback laws using deep learning on microcontrollers, including techniques to mitigate quantization effects.

Findings

Deep neural networks accurately approximate MPFC feedback.

Post-stabilization reduces quantization-induced errors.

Simulation confirms real-time control feasibility on microcontrollers.

Abstract

Model predictive Path-Following Control (MPFC) is a viable option for motion systems in many application domains. However, despite considerable progress on tailored numerical methods for predictive control, the real-time implementation of predictive control and MPFC on small-scale autonomous platforms with low-cost embedded hardware remains challenging. While usual stabilizing MPC formulations lead to static feedback laws, the MPFC feedback turns out to be dynamic as the path parameter acts as an internal controller variable. In this paper, we leverage deep learning to implement predictive path-following control on microcontrollers. We show that deep neural networks can approximate the dynamic MPFC feedback law accurately. Moreover, we illustrate and tackle the challenges that arise if the target platform employs limited precision arithmetic. Specifically, we draw upon a post-stabilization with an additional feedback law to attenuate undesired quantization effects. Simulation examples underpin the efficacy of the proposed approach.