A two-color external light interface for Level 3 AV takeover requests improves surrounding drivers' understanding and reduces accident odds by 76.8% in simulator tests compared to no interface.
A survey of autonomous driving: Common practices and emerging technologies,
4 Pith papers cite this work. Polarity classification is still indexing.
years
2026 4representative citing papers
SwarmDrive uses local SLMs on vehicles for event-triggered semantic V2V intent sharing and consensus, improving occluded intersection success from 68.9% to 94.1% and cutting latency to 151.4 ms in a 5-seed simulation.
A voice HMI that supplies both the trigger and the explicit reason for a request-to-intervene improves driver comprehension of ADS limits and lowers collision rates in simulator take-over scenarios.
Frequency-domain radar processing with Fourier SOFT in 2D improves robustness for radar-only odometry and multi-object tracking in high-dynamic scenes compared with feature-based methods.
citing papers explorer
-
An eHMI Presenting Request-to-Intervene and Takeover Status of Level 3 Automated Vehicles to Support Surrounding Traffic Safety
A two-color external light interface for Level 3 AV takeover requests improves surrounding drivers' understanding and reduces accident odds by 76.8% in simulator tests compared to no interface.
-
SwarmDrive: Semantic V2V Coordination for Latency-Constrained Cooperative Autonomous Driving
SwarmDrive uses local SLMs on vehicles for event-triggered semantic V2V intent sharing and consensus, improving occluded intersection success from 68.9% to 94.1% and cutting latency to 151.4 ms in a 5-seed simulation.
-
An Educational Human Machine Interface Providing Request-to-Intervene Trigger and Reason Explanation for Enhancing the Driver's Comprehension of ADS's System Limitations
A voice HMI that supplies both the trigger and the explicit reason for a request-to-intervene improves driver comprehension of ADS limits and lowers collision rates in simulator take-over scenarios.
-
Towards Multi-Object-Tracking with Radar on a Fast Moving Vehicle: On the Potential of Processing Radar in the Frequency Domain
Frequency-domain radar processing with Fourier SOFT in 2D improves robustness for radar-only odometry and multi-object tracking in high-dynamic scenes compared with feature-based methods.