Kineto-Dynamical Planning and Accurate Execution of Minimum-Time Maneuvers on Three-Dimensional Circuits

2025-02-05

AI Summary

Addressing the open challenge of online minimum-time maneuver planning and execution for autonomous racing on three-dimensional (3D) tracks, this paper proposes the Artificial Racing Driver (ARD) framework. Methodologically, ARD introduces: (i) the first kineto-dynamical (KD) vehicle model explicitly designed for 3D tracks—achieving high-fidelity dynamic representation while enabling real-time re-planning; and (ii) an efficient nonlinear model predictive controller (E-NMPC) tightly integrated with the KD model to realize closed-loop optimal control. In high-fidelity simulation, ARD’s closed-loop lap time approaches the offline minimum-lap-time solution (MLT-VS), substantially outperforming existing baselines. Moreover, trajectory re-planning demonstrates strong robustness, and execution error analysis confirms ARD’s simultaneous efficacy and accuracy in complex 3D maneuvers.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Online planning and execution of minimum-time maneuvers on three-dimensional (3D) circuits is an open challenge in autonomous vehicle racing. In this paper, we present an artificial race driver (ARD) to learn the vehicle dynamics, plan and execute minimum-time maneuvers on a 3D track. ARD integrates a novel kineto-dynamical (KD) vehicle model for trajectory planning with economic nonlinear model predictive control (E-NMPC). We use a high-fidelity vehicle simulator (VS) to compare the closed-loop ARD results with a minimum-lap-time optimal control problem (MLT-VS), solved offline with the same VS. Our ARD sets lap times close to the MLT-VS, and the new KD model outperforms a literature benchmark. Finally, we study the vehicle trajectories, to assess the re-planning capabilities of ARD under execution errors. A video with the main results is available as supplementary material.

Problem

• Online planning of 3D maneuvers
• Accurate execution of minimum-time strategies
• Integration of KD model with E-NMPC

Innovation

• Kineto-Dynamical vehicle model
• Economic nonlinear model predictive control
• High-fidelity vehicle simulator