Faculty Advisor/Mentor
Hong Yang
Location
Virginia Modeling, Analysis and Simulation Center, Room 2100
Conference Title
Modeling, Simulation and Visualization Student Capstone Conference 2023
Conference Track
Visual Environments & Visualization
Document Type
Paper
Abstract
Self-driving cars raise safety concerns, particularly regarding pedestrian interactions. Current research lacks a systematic understanding of these interactions in diverse scenarios. Autonomous Vehicle (AV) performance can vary due to perception accuracy, algorithm reliability, and environmental dynamics. This study examines AV-pedestrian safety issues, focusing on low visibility conditions, using a co-simulation framework combining virtual reality and an autonomous driving simulator. 40 experiments were conducted, extracting surrogate safety measures (SSMs) from AV and pedestrian trajectories. The results indicate that low visibility can impair AV performance, increasing conflict risks for pedestrians. AV algorithms may require further enhancements and validations for consistent safety performance in low visibility scenarios.
Keywords:
Autonomous vehicles, Pedestrians, Virtual reality, CARLA simulator, Conflict Risk, Simulation, Safety
Start Date
4-20-2023
End Date
4-20-2023
Recommended Citation
Yan, Zizheng; Liu, Yang; and Yang, Hong, "Enhancing Pedestrian-Autonomous Vehicle Safety in Low Visibility Scenarios: A Comprehensive Simulation Method" (2023). Modeling, Simulation and Visualization Student Capstone Conference. 1.
https://digitalcommons.odu.edu/msvcapstone/2023/virtualandvisualization/1
DOI
10.25776/47g8-3c16
Included in
Artificial Intelligence and Robotics Commons, Automotive Engineering Commons, Theory and Algorithms Commons
Enhancing Pedestrian-Autonomous Vehicle Safety in Low Visibility Scenarios: A Comprehensive Simulation Method
Virginia Modeling, Analysis and Simulation Center, Room 2100
Self-driving cars raise safety concerns, particularly regarding pedestrian interactions. Current research lacks a systematic understanding of these interactions in diverse scenarios. Autonomous Vehicle (AV) performance can vary due to perception accuracy, algorithm reliability, and environmental dynamics. This study examines AV-pedestrian safety issues, focusing on low visibility conditions, using a co-simulation framework combining virtual reality and an autonomous driving simulator. 40 experiments were conducted, extracting surrogate safety measures (SSMs) from AV and pedestrian trajectories. The results indicate that low visibility can impair AV performance, increasing conflict risks for pedestrians. AV algorithms may require further enhancements and validations for consistent safety performance in low visibility scenarios.