Longitudinal Control for Autonomous Racing with Combustion Engine Vehicles

2025-04-24

AI Summary

In autonomous fuel-powered race car racing, mapping high-level trajectory tracking commands—particularly longitudinal acceleration—to low-level actuators (throttle, brake pressure, gear selection) remains challenging due to complex nonlinear dynamics and stringent real-time constraints. Method: This paper proposes the first longitudinal hierarchical control architecture tailored for a real-world F1 circuit—the Yas Marina Circuit—integrating actuator-coordinated modeling, real-time embedded vehicle dynamics constraints, and ABS, traction control, and brake preheating functionalities. The architecture supports modular integration of diverse tracking algorithms and vehicle models. Results: Validated via hardware-in-the-loop simulation and on-track vehicle testing, the system achieves precise tracking of highly dynamic longitudinal acceleration commands up to ±25 m/s² under limit-condition driving, with robust closed-loop stability. It significantly enhances both real-time performance and operational safety in autonomous fuel-racing applications.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Behavior Learning & Control
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Usually, a controller for path- or trajectory tracking is employed in autonomous driving. Typically, these controllers generate high-level commands like longitudinal acceleration or force. However, vehicles with combustion engines expect different actuation inputs. This paper proposes a longitudinal control concept that translates high-level trajectory-tracking commands to the required low-level vehicle commands such as throttle, brake pressure and a desired gear. We chose a modular structure to easily integrate different trajectory-tracking control algorithms and vehicles. The proposed control concept enables a close tracking of the high-level control command. An anti-lock braking system, traction control, and brake warmup control also ensure a safe operation during real-world tests. We provide experimental validation of our concept using real world data with longitudinal accelerations reaching up to $25 , frac{mathrm{m}}{mathrm{s}^2}$. The experiments were conducted using the EAV24 racecar during the first event of the Abu Dhabi Autonomous Racing League on the Yas Marina Formula 1 Circuit.

Problem

• Translates high-level trajectory commands to low-level vehicle controls
• Ensures safe operation with ABS and traction control systems
• Validates control concept using real-world racing data

Innovation

• Translates high-level commands to low-level vehicle controls
• Modular structure integrates various control algorithms
• Ensures safety with ABS and traction control