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

2026-03-11

AI Summary

This work addresses the challenge of leveraging GPU parallelism for real-time trajectory optimization in autonomous systems subject to nonlinear constraints, where conventional CPU-based solvers fall short. We propose the first end-to-end GPU-native parallel temporal-domain optimal control framework, which integrates sequential convex programming (SCP) with a consensus-based alternating direction method of multipliers (ADMM). By decomposing the problem along the time dimension into parallelizable subproblems and employing a sparse-algebra-free computational architecture, our approach enables joint optimization of multiple trajectories and supports robust model predictive control (MPC) extensions. Evaluated on embedded edge platforms, the framework achieves planning frequencies exceeding 100 Hz, a 4× throughput improvement, and a 51% reduction in energy consumption, while maintaining GPU utilization above 96%.

Technology Category

• Search and Optimization: Non-convex Optimization
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• real-time trajectory optimization
• nonlinear constrained systems
• GPU acceleration
• parallel-in-time computing
• autonomous systems

Innovation

• GPU-native optimization
• parallel-in-time
• sequential convex programming
• consensus ADMM
• real-time trajectory optimization