Hardware Neural Control of CartPole and F1TENTH Race Car

TL;DR

This paper presents FPGA-based neural network controllers trained to imitate nonlinear model predictive control, enabling high-frequency, real-time control of physical cartpole and F1TENTH race car systems with improved performance over traditional NMPC.

Contribution

It introduces FPGA neural controllers trained via supervised learning to replicate NMPC, achieving faster control rates and better real-world performance.

Findings

Neural controllers match NMPC in simulation

Neural controllers outperform NMPC in real-world tests

Achieve kHz control rates on physical hardware

Abstract

Nonlinear model predictive control (NMPC) has proven to be an effective control method, but it is expensive to compute. This work demonstrates the use of hardware FPGA neural network controllers trained to imitate NMPC with supervised learning. We use these Neural Controllers (NCs) implemented on inexpensive embedded FPGA hardware for high frequency control on physical cartpole and F1TENTH race car. Our results show that the NCs match the control performance of the NMPCs in simulation and outperform it in reality, due to the faster control rate that is afforded by the quick FPGA NC inference. We demonstrate kHz control rates for a physical cartpole and offloading control to the FPGA hardware on the F1TENTH car. Code and hardware implementation for this paper are available at https:// github.com/SensorsINI/Neural-Control-Tools.