Wang, Yuhang (University of South Florida), Alhuraish, Abdulaziz (Imam Abdulrahman Bin Faisal University), Yuan, Shengming (University of South Florida), Zhou, Hao (University of South Florida)

OpenLKA: An Open Dataset of Lane Keeping Assist from Recent Car Models under Real-World Driving Conditions

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on April 2, 2026

Abstract

Lane Keeping Assist (LKA) is widely adopted in modern production vehicles, yet its real-world performance remains opaque due to the system's proprietary control stack, preventing researchers from diagnosing or improving this technology. To fill the gap, this paper presents OpenLKA, the first open, large-scale dataset for LKA evaluation and improvement. It includes 389.1 hours of LKA-steered data from 62 production vehicle models, collected through extensive road testing in Tampa, Florida and global contributors from the open-source community. The dataset spans a wide range of challenging scenarios, including degraded lane markings, complex road geometries, adverse weather, lighting conditions and various surrounding traffic. The dataset is multimodal, comprising: i) decoded vehicle internal messages including key LKA signals (e.g., system disengagements, lane detection failures); ii) synchronized high-resolution videos from a mounted dash camera; and iii) rich scene annotations generated by a vision language model, covering lane visibility, pavement quality, weather, lighting, and traffic conditions etc. Collectively, OpenLKA provides a comprehensive platform for benchmarking the real-world performance of production LKA systems, identifying safety-critical operational scenarios, and assessing the readiness of current road infrastructure for autonomous driving. The dataset is publicly available at: url{https://github.com/OpenLKA}.