Parallel-in-Time Nonlinear Optimal Control via GPU-native Sequential Convex Programming

TL;DR

This paper presents a GPU-native, parallelized trajectory optimization framework for nonlinear autonomous systems, achieving high-speed planning and energy efficiency by leveraging temporal splitting and consensus-based algorithms.

Contribution

It introduces a fully GPU-based sequential convex programming method with temporal splitting, enabling massively parallel trajectory optimization on edge computing platforms.

Findings

Achieves over 100 Hz planning rate on GPU hardware.

Realizes 4x speedup and 51% energy reduction compared to CPU baseline.

Successfully extends to robust MPC with stochastic disturbances.

Abstract

Real-time trajectory optimization for nonlinear constrained autonomous systems is critical and typically performed by CPU-based sequential solvers. Specifically, reliance on global sparse linear algebra or the serial nature of dynamic programming algorithms restricts the utilization of massively parallel computing architectures like GPUs. To bridge this gap, we introduce a fully GPU-native trajectory optimization framework that combines sequential convex programming with a consensus-based alternating direction method of multipliers. By applying a temporal splitting strategy, our algorithm decouples the optimization horizon into independent, per-node subproblems that execute massively in parallel. The entire process runs fully on the GPU, eliminating costly memory transfers and large-scale sparse factorizations. This architecture naturally scales to multi-trajectory optimization. We validate the solver on a quadrotor agile flight task and a Mars powered descent problem using an on-board edge computing platform. Benchmarks reveal a sustained 4x throughput speedup and a 51% reduction in energy consumption over a heavily optimized 12-core CPU baseline. Crucially, the framework saturates the hardware, maintaining over 96% active GPU utilization to achieve planning rates exceeding 100 Hz. Furthermore, we demonstrate the solver's extensibility to robust Model Predictive Control by jointly optimizing dynamically coupled scenarios under stochastic disturbances, enabling scalable and safe autonomy.