ADVANCED DRIVER ASSISTANCE SYSTEM CAR FOLLOWING MODEL OPTIMIZATION FRAMEWORK USING GENETIC ALGORITHM IMPLEMENTED IN SUMO TRAFFIC SIMULATION

ECU Author/Contributor (non-ECU co-authors, if there are any, appear on document)

Matt J Carroll (Creator)

Institution

East Carolina University (ECU )

Web Site: http://www.ecu.edu/lib/

Abstract: As advanced driver-assistance systems (ADAS) such as smart cruise control and lane keeping\nhave become common technologies, self-driving above SAE level 3 are being competitively\ndeveloped by major automobile manufacturers, autonomous vehicles (AVs) will prevail in\nthe near future traffic network. In particular, evasive action algorithms with collision detec-\ntion by sensors and faster braking response will enable AVs to drive with a shorter gap at\nhigher speeds which has not been possible with human drivers. Such technologies will be able\nto improve current traffic performance as long as raising concerns on safety are addressed.\nTherefore, there have been efforts to improve understanding between stakeholders such as\nregulatory authorities and developers to draw a consensus about autonomous driving stan-\ndard and regulations. Meanwhile, a mixed traffic network with human driving vehicles and\nAVs will show transient system behavior based on penetration rate of AVs thereby requiring\ndifferent optimal AV settings. We are interested in understanding this system behavior over\ntransitional period to achieve an optimal traffic performance with safety as a hard constraint.\nWe investigate the system behavior with agent-based simulation with different penetration\nrates by mixing of human-driving and AV vehicle models, identify the key parameters of\nADAS algorithms for traffic flow, and find the optimal parameter set per penetration rate\nby using genetic algorithm (GA). Simulation results with optimal parameter values reveal\nimprovement in average traffic performance measures such as flow (5.6% increase), speed\n(4.9% increase), density (15.9% decrease), and waiting time (48.2% decrease). We provide\nsimulation examples and discuss the implication of the optimal parameter values for both\ntraffic control authorities and AV developers during the transitional period.\n2

Additional Information

Publication

Thesis

Language: English

Date: 2023

Subjects

Advanced Driver-Assistance Systems (ADAS);Autonomous Vehicle (AV);Genetic Algorithm (GA)

Email this document to