https://www.motiflab.net/projects/Recent content in Projects & Datasets on MOTIF LabHugoen-ushttps://www.motiflab.net/projects/openlka/Mon, 01 Jan 0001 00:00:00 +0000https://www.motiflab.net/projects/openlka/<h2 id="what-it-is">What it is</h2> <p><strong>OpenLKA</strong> is the first open benchmark dataset of lane-keeping-assist (LKA) behavior collected from a wide range of <em>production</em> autonomous vehicles in real driving. Released in January 2025, it pairs CAN-bus signals with synchronized forward-facing video and lane-perception output, captured across multiple market vehicles under varied roadway and weather conditions in the Tampa, Florida region.</p> <h2 id="why-it-matters">Why it matters</h2> <p>Lane-keeping assist is one of the most widely deployed ADAS features, but its real-world performance is opaque: most public benchmarks are built on simulated environments or single-vehicle test fleets, and the behavior of production LKA systems differs widely between manufacturers. Without an open, multi-vehicle dataset, researchers cannot calibrate microsimulations of mixed-autonomy traffic, evaluate disengagement risk, or model the variance in LKA-equipped vehicle behavior that capacity and safety analyses now have to contend with.</p>