GP-enhanced Autonomous Drifting Framework using ADMM-based iLQR

2025-03-14

AI Summary

Autonomous drift control for self-driving vehicles faces two major challenges in uncertain environments: significant nonlinear modeling errors and heavy real-time optimization computational burdens. To address these, this paper proposes a general-path-oriented autonomous drift control framework. Our method innovatively integrates Gaussian process (GP) residual compensation with an ADMM-accelerated iterative linear quadratic regulator (iLQR): GP regression learns and compensates for dynamics model residuals online to enhance robustness, while the alternating direction method of multipliers (ADMM) decomposes the iLQR optimal control problem to ensure real-time performance. Experimental results demonstrate that the proposed approach reduces lateral root-mean-square error (RMSE) by 38% and cuts average per-step computation time by 75% compared to IPOPT. It thus effectively decouples the traditional trade-off between control accuracy and real-time feasibility, establishing a new paradigm for high-performance autonomous drifting in complex scenarios.

Technology Category

• Search and Optimization: Learning to Search
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Autonomous drifting is a complex challenge due to the highly nonlinear dynamics and the need for precise real-time control, especially in uncertain environments. To address these limitations, this paper presents a hierarchical control framework for autonomous vehicles drifting along general paths, primarily focusing on addressing model inaccuracies and mitigating computational challenges in real-time control. The framework integrates Gaussian Process (GP) regression with an Alternating Direction Method of Multipliers (ADMM)-based iterative Linear Quadratic Regulator (iLQR). GP regression effectively compensates for model residuals, improving accuracy in dynamic conditions. ADMM-based iLQR not only combines the rapid trajectory optimization of iLQR but also utilizes ADMM's strength in decomposing the problem into simpler sub-problems. Simulation results demonstrate the effectiveness of the proposed framework, with significant improvements in both drift trajectory tracking and computational efficiency. Our approach resulted in a 38$%$ reduction in RMSE lateral error and achieved an average computation time that is 75$%$ lower than that of the Interior Point OPTimizer (IPOPT).

Problem

• Addresses model inaccuracies in autonomous vehicle drifting.
• Mitigates computational challenges in real-time control systems.
• Improves drift trajectory tracking and computational efficiency.

Innovation

• GP regression compensates model residuals effectively
• ADMM-based iLQR optimizes trajectory rapidly
• Framework reduces RMSE error and computation time