Parallel Branch Model Predictive Control on GPUs

TL;DR

This paper introduces a GPU-accelerated parallel solver for branch Model Predictive Control that leverages tree structure and parallel algorithms to improve performance, especially on large-scale problems.

Contribution

The paper presents a novel GPU-based solver for branch MPC that exploits parallelism in both the prediction horizon and scenarios, handling constraints with an augmented Lagrangian method.

Findings

Achieves competitive performance on short horizon problems.

Outperforms CPU-based solvers on large-scale problems.

Utilizes parallel scan algorithm for temporal parallelism.

Abstract

We present a parallel GPU-accelerated solver for branch Model Predictive Control problems. Based on iterative LQR methods, our solver exploits the tree-sparse structure and implements temporal parallelism using the parallel scan algorithm. Consequently, the proposed solver enables parallelism across both the prediction horizon and the scenarios. In addition, we utilize an augmented Lagrangian method to handle general inequality constraints. We compare our solver with state-of-the-art numerical solvers in two automated driving applications. The numerical results demonstrate that, compared to CPU-based solvers, our solver achieves competitive performance for problems with short horizons and small-scale trees, while outperforming other solvers on large-scale problems.