Nonlinear Predictive Control on a Heterogeneous Computing Platform

TL;DR

This paper presents a novel implementation of nonlinear predictive control on a heterogeneous platform combining CPU and FPGA, achieving significant memory and speed improvements over existing methods.

Contribution

It introduces a new structure-exploiting approach for the KKT matrix, enabling efficient control on heterogeneous hardware with a new software tool, Protoip.

Findings

18x memory savings compared to existing methods

36x speedup over ARM Cortex-A9 implementation

Enhanced verification with Protoip platform

Abstract

We propose an implementation of an interior-point-based nonlinear predictive controller on a heterogeneous processor. The workload can be split between a general-purpose CPU and a field-programmable gate array to trade off the contradicting design objectives of control performance and computational resource usage. A new way of exploiting the structure of the KKT matrix yields significant memory savings. We report an 18x memory saving, compared to existing approaches, and a 36x speedup over a software implementation with an ARM Cortex-A9 processor. We also introduce a new release of Protoip, which abstracts low-level details of heterogeneous programming and allows processor-in-the-loop verification.