Efficient Trajectory Optimization for Autonomous Racing via Formula-1 Data-Driven Initialization

2026-03-07

AI Summary

This work addresses the sensitivity of minimum-time trajectory optimization in autonomous racing to initial guesses, where conventional geometric initialization often leads to slow convergence or suboptimal solutions. To overcome this limitation, the authors present the first use of real-world Formula 1 telemetry data to construct a multi-track trajectory dataset, enabling the training of a neural network that directly predicts expert-level racing line offsets from local track geometry. This data-driven approach provides high-quality initial guesses for optimal control solvers without requiring explicit vehicle dynamics modeling. Evaluated across 17 distinct tracks, the method significantly accelerates solver convergence and reduces computation time compared to traditional initialization strategies, while preserving optimal lap times—demonstrating an effective integration of data-driven learning with optimal control for autonomous racing.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Trajectory optimization is a central component of fast and efficient autonomous racing. However practical optimization pipelines remain highly sensitive to initialization and may converge slowly or to suboptimal local solutions when seeded with heuristic trajectories such as the centerline or minimum-curvature paths. To address this limitation, we leverage expert driving behavior as a initialization prior and propose a learning-informed initialization strategy based on real-world Formula 1 telemetry. To this end, we first construct a multi-track Formula~1 trajectory dataset by reconstructing and aligning noisy GPS telemetry to a standardized reference-line representation across 17 tracks. Building on this, we present a neural network that predicts an expert-like raceline offset directly from local track geometry, without explicitly modeling vehicle dynamics or forces. The predicted raceline is then used as an informed seed for a minimum-time optimal control solver. Experiments on all 17 tracks demonstrate that the learned initialization accelerates solver convergence and significantly reduces runtime compared to traditional geometric baselines, while preserving the final optimized lap time.

Problem

• trajectory optimization
• autonomous racing
• initialization sensitivity
• suboptimal convergence
• expert driving behavior

Innovation

• trajectory optimization
• data-driven initialization
• autonomous racing
• neural network
• Formula 1 telemetry