Cut-In Gap Acceptance Toward Autonomous vs. Human-Driven Vehicles: Evidence from the Waymo Open Motion Dataset

2026-05-02

AI Summary

This study investigates whether human drivers adopt more aggressive longitudinal gaps when cutting in front of autonomous vehicles, a behavior with critical safety implications. Leveraging the Waymo Open Motion Dataset, the authors employ an eight-criteria lane-change detector to identify cut-in events in large-scale real-world highway scenarios and analyze 10 Hz trajectory data using speed-matching resampling and rigorous statistical hypothesis testing—including p-values, effect sizes, and chi-square tests. Results reveal that the median accepted gap when cutting in front of autonomous vehicles is significantly shorter by 1.99 meters (7.58 m vs. 9.57 m) compared to human-driven vehicles, with cut-in speeds 37% higher and 68% of events occurring at gaps under 10 meters. These findings indicate a systematic tendency for human drivers to interact more aggressively with autonomous vehicles, underscoring the need to recalibrate safety margins in planning and simulation models.

Abstract

Autonomous vehicles (AVs) are widely known to follow conservative, rule-based motion policies that surrounding drivers can learn to anticipate. A direct consequence is that human drivers may accept shorter longitudinal gaps when cutting in front of an AV than when targeting another human-driven vehicle (HDV). We test this hypothesis using the Waymo Open Motion Dataset (WOMD), which provides 25,906 real-world highway scenarios at 10 hertz. An eight-criterion lane-change detector extracts 706 HDV-to-AV and 3,172 HDV-to-HDV cut-in events from the same traffic environment. The median accepted gap in front of the Waymo AV is 7.58 meters versus 9.57 meters for HDV targets, a 1.99 meter reduction that is statistically significant (p equals 5.76 times 10 to the negative eighth power, d equals negative 0.224) and persists under speed-matched resampling. Cut-in speeds toward the AV are 37 percent higher (51.7 versus 37.7 kilometers per hour, d equals 0.502), and 68.0 percent of AV-targeted cut-ins occur below the 10 meter gap boundary versus 51.8 percent of HDV-targeted events (chi-squared equals 60.5, p is less than 10 to the negative thirteenth power). These results reveal a systematic and safety-relevant asymmetry in human gap-acceptance behavior that warrants AV-specific calibration of both motion-planning safety envelopes and traffic simulation models.

Problem

• gap acceptance
• autonomous vehicles
• human-driven vehicles
• cut-in behavior
• traffic safety

Innovation

• gap acceptance
• autonomous vehicles
• cut-in behavior
• Waymo Open Motion Dataset
• motion planning safety