Meet Inspiring Speakers and Experts at our 3000+ Global Conference Series LLC LTD Events with over 1000+ Conferences, 1000+ Symposiums and 1000+ Workshops on Medical, Pharma, Engineering, Science, Technology and Business.

Explore and learn more about Conference Series LLC LTD : World’s leading Event Organizer


Koungsu Yi

Koungsu Yi

Seoul National University, South Korea

Title: Decision and motion planning at intersection for urban automated driving


Biography: Koungsu Yi


Automated vehicles are expected to be the sustainable future for safe driving, efficient traffic, and reduced energy consumption. Almost every challenge concerning modern road traffic such as traffic jam, road fatalities, carbon emissions, and parking space can be solved by smart mobility system such as automated vehicle-based car sharing. Most of major automakers have already commercialized various advanced driving assistance systems (ADAS) to enhance driving safety and to reduce driving workload, and are planning to commercialize Level 3~4 automated vehicles for personal mobility from the year of 2020. As of 2018, automated vehicle-based smart mobility systems are operated in several sites and it is expected that smart mobility services with large fleets of automated vehicles will be available in 100 cities in the year 2025. Although still there exist many technical challenges concerning full automated driving in urban environments, there has been rapid progress in the field of automated vehicles. In this talk, technical issues and recent developments for automated driving in urban environments will be presented. A hierarchical structure for decision and motion planning for autonomous driving at unsignalized intersection has been developed. Based on real road driving data analysis an intelligent driver-veicle models for cross-first or yield has been developed. Index variables for target intension inference at intersection have been defined and interacting multiple model (IMM) based intention inference scheme has been developed. A target inrention inference-based decision and motion planning has been investigated via computer simulation and successfully implemented on an automated driving vehicles.