An assessment of the effect of green signal countdown timers on drivers’ behavior and on road safety at intersections, based on driving simulator experiments and naturalistic observation studies

Yan, Wei; Wong, S. C.; Loo, Becky P.Y.; Wu, Connor Y. H.; Huang, Helai; Pei, Xin; Meng, Fang

doi:10.1016/j.jsr.2022.04.001

Cited by 10 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, because current work mainly focuses on the system side, a driving simulator is an appropriate technique which provides approaches to simulating how real drivers interact with the driving environment (e.g., an intelligent driving system). There exists practical applications of driving simulators which involve a wide range of traffic areas and vehicle techniques, such as advanced driver assistance systems [ 12 ], driver education in driving automation [ 13 ], assessment of safety at signalized intersection [ 14 ], and so on. For example, Simović et al [ 15 ] employ an in-laboratory driving simulator to investigate how different factors can influence the e-bicycle speed perception of human drivers.…”

Section: Introductionmentioning

confidence: 99%

IvCDS: An End-to-End Driver Simulator for Personal In-Vehicle Conversational Assistant

Yin

Peng

et al. 2022

IJERPH

View full text Add to dashboard Cite

An advanced driver simulator methodology facilitates a well-connected interaction between the environment and drivers. Multiple traffic information environment language processing aims to help drivers accommodate travel demand: safety prewarning, destination navigation, hotel/restaurant reservation, and so on. Task-oriented dialogue systems generally aim to assist human users in achieving these specific goals by a conversation in the form of natural language. The development of current neural network based dialogue systems relies on relevant datasets, such as KVRET. These datasets are generally used for training and evaluating a dialogue agent (e.g., an in-vehicle assistant). Therefore, a simulator for the human user side is necessarily required for assessing an agent system if no real person is involved. We propose a new end-to-end simulator to operate as a human driver that is capable of understanding and responding to assistant utterances. This proposed driver simulator enables one to interact with an in-vehicle assistant like a real person, and the diversity of conversations can be simply controlled by changing the assigned driver profile. Results of our experiment demonstrate that this proposed simulator achieves the best performance on all tasks compared with other models.

show abstract