Implementation and Performance Evaluation of In-vehicle Highway Back-of-Queue Alerting System Using the Driving Simulator

Abstract

This paper proposes a prototype in-vehicle highway back-of-queue alerting system that is based on an Androidbased smartphone app, which is capable of delivering warning information to on-road drivers approaching traffic queues. To evaluate the effectiveness of this alerting system, subjects were recruited to participate in the designed test scenarios on a driving simulator. The test scenarios include three warning types (no alerts, roadside alerts, and in-vehicle auditory alerts), three driver states (normal, distracted, and drowsy), and two weather conditions (sunny and foggy). Driver responses related to vehicle dynamics data were collected and analyzed. The results indicate that on average, the drowsy state decreases the minimum time-to-collision by 1.6 seconds compared to the normal state. In-vehicle auditory alerts can effectively increase the driving safety across different combinations of situations (driver states and weather conditions), while roadside alerts perform better than no alerts.

Quantifying the Impact of In-Cab Alerts on Truck Speed Reductions in Ohio

“…The Pennsylvania Turnpike equipped more than 150 maintenance and service patrol vehicles with the ability to broadcast emergency alerts and found that roadside crashes reduced from thirty in 2018 to zero in 2020 [22]. FHWA's Next Generation Traffic Incident Management (TIM) under Every Day Counts (EDC-6) initiative also highlights the importance of digital alerts and responder-to-vehicle (R2V) alerts for active responders in the vicinity and for back-of-queue warning [23] as a new potential implementation option for improving TIM strategies [24].…”

TrEP: Transformer-Based Evidential Prediction for Pedestrian Intention with Uncertainty

“…A Limited trajectory prediction horizon may be sufficient for automatic braking features focusing on last-second braking to improve safety, but cannot support efficient motion planning for higher-level automatic cars to interact with pedestrians smoothly. Some studies have shown that human drivers need at least 3 seconds of prediction horizon to plan driving behaviors during pedestrian interactions (Herman et al 2021;Zhang et al 2022aZhang et al , 2021bPang, Guo, and Zhuang 2022), indicating a similar requirement for automatic driving algorithms. Also, in the case to detect the out-of-ODD event and start the transition from automatic control to manual driving, drivers need up to 20 seconds to fully control the car given a sudden automatic driving failure (Eriksson and Stanton 2017;Merat et al 2014), which poses high requirements of pedestrian behavior prediction horizon as well to ensure driving safety.…”