Hardware Neural Control of CartPole and F1TENTH Race Car
This addresses the problem of expensive real-time control for robotics and autonomous systems by enabling high-frequency, low-cost hardware implementations, though it is incremental as it applies an existing imitation learning approach to new hardware platforms.
This work tackles the high computational cost of nonlinear model predictive control (NMPC) by training hardware FPGA neural network controllers to imitate NMPC, achieving kHz control rates on physical systems like a cartpole and F1TENTH race car, where the neural controllers match NMPC performance in simulation and outperform it in reality due to faster inference.
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.