A Data-Driven Aggressive Autonomous Racing Framework Utilizing Local Trajectory Planning with Velocity Prediction

2024-10-15

arXiv.org

AI Summary

To address the challenge of generating optimal velocity profiles for local trajectory planning on sharp-turning race tracks—thereby limiting autonomous racing performance—this paper proposes a Velocity-Prediction-Enhanced Model Predictive Contour Control (VPMPCC) framework. Our key contributions are: (1) a novel track-geometry-encoded reference velocity profile embedding mechanism, enabling structured modeling of velocity priors; (2) a racing-oriented Bayesian optimization objective function (OFR) that jointly optimizes lap time and trajectory robustness under safety constraints; and (3) zero-parameter-transfer capability from simulation to real-world deployment. Experiments demonstrate a 42.9% reduction in Bayesian optimization convergence iterations and achieve an average projected velocity of 93.2% of the vehicle’s steady-state limit on multi-sharp-turn tracks. The source code is publicly available.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Motion & Tracking

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Tracking, profiling, and countermeasures against them
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The development of autonomous driving has boosted the research on autonomous racing. However, existing local trajectory planning methods have difficulty planning trajectories with optimal velocity profiles at racetracks with sharp corners, thus weakening the performance of autonomous racing. To address this problem, we propose a local trajectory planning method that integrates Velocity Prediction based on Model Predictive Contouring Control (VPMPCC). The optimal parameters of VPMPCC are learned through Bayesian Optimization (BO) based on a proposed novel Objective Function adapted to Racing (OFR). Specifically, VPMPCC achieves velocity prediction by encoding the racetrack as a reference velocity profile and incorporating it into the optimization problem. This method optimizes the velocity profile of local trajectories, especially at corners with significant curvature. The proposed OFR balances racing performance with vehicle safety, ensuring safe and efficient BO training. In the simulation, the number of training iterations for OFR-based BO is reduced by 42.86% compared to the state-of-the-art method. The optimal simulation-trained parameters are then applied to a real-world F1TENTH vehicle without retraining. During prolonged racing on a custom-built racetrack featuring significant sharp corners, the mean projected velocity of VPMPCC reaches 93.18% of the vehicle's handling limits. The released code is available at https://github.com/zhouhengli/VPMPCC.

Problem

• Optimizes velocity profiles for autonomous racing at sharp corners.
• Integrates Velocity Prediction with Model Predictive Contouring Control.
• Reduces training iterations by 42.86% using Bayesian Optimization.

Innovation

• Velocity Prediction via Model Predictive Contouring Control
• Bayesian Optimization with Racing-adapted Objective Function
• Efficient training and real-world application without retraining