:: ICCAS 2015 ::

WC02		[OS] Vehicle Control
Time : 16:30~18:00 Room : 102		Chair : Kyongsu Yi (Seoul National University, )



16:30~16:45	WC02-1

Three-Dimensional Time-Space Grid Allocation Algorithm for Traffic Control of Autonomous Vehicles at an Intersection
Jaeyong Kim, Jin Gyu Lee, Seungjoon Lee, Hyuntae Kim, Hyungbo Shim(Seoul National University, Korea, Republic of ), Yongsoon Eun(Daegu Geyeongbuk Institute of Science & Technology, Korea, Republic of ), KangWon LEE(Korea Polytechnic University, Korea, Republic of )

Two-dimensional (2-D) time-space diagram have been widely used to analyze the flow of the traffic. However, it has limitations to make a plan that guarantees the collision avoidance of vehicles at the intersections. In this paper, we introduce the three-dimensional (3-D) time-space diagram and demonstrate its effectiveness in describing the movements of vehicles at the intersections. We also propose an algorithm based on the grid allocation of 3-D time-space diagram to avoid collision between vehicles to achieve the autonomous intersection.



16:45~17:00	WC02-2

A Method of Digital Map Construction with Road Feature Extraction Using 2-Dimensional Laser Range Finder
Kyung Jae Ahn(Graduate School of Kookmin University, Korea, Republic of ), Taekgyu Lee, Yeonsik Kang(Kookmin University, Korea, Republic of )

These days, robust autonomous navigation incorporates the information on the digital map including variety of road features such as position of lane markings, road boundaries and etc. In this study, a method of extracting road features are developed using two dimensional laser range finder (LRF). In particular, range measurements are employed to identify the road surface using split and merge method. In addition, the reflectivity measurements are used to identify lane markings on the road surface. Finally a digital map of road surface is constructed which is useful for robust autonomous naviga



17:00~17:15	WC02-3

An Smart Key-initiated Multiple Operating System for Personalized Connected Cars
Sangho Lee, Shiho Kim(Yonsei University, Korea, Republic of )

We have proposed a personalized smart key initiated in-vehicle multiple operating system of connected cars using a virtualization technique. The driver can select her/his preferred OS among the guest operating systems running on the host. The proposed infotainment system can provide a fully customizable operating system with personalized environment.



17:15~17:30	WC02-4

High-level Automated Driving on Complex Urban Roads with Enhanced Environment Representation
Beomjun Kim, Dingwook Kim, Kyuwon Kim, kyongsu yi(seoul national university, Korea, Republic of )

This paper describes a fully automated driving algorithm on complex urban roads with LiDAR, vision, and GPS/map based environment representation with guaranteed safety. The proposed algorithm consists of the following three steps: an environment representation, a safety driving envelope decision, and a motion optimization. An environment representation system consists of three main modules: object classification, vehicle/non-vehicle tracking and map/lane based localization. A motion planning modules derives an optimal motion as a function of time, from the environment representation results. A



17:30~17:45	WC02-5

Decision Making for Automated Driving at Unsignalized Intersection
Dong-Kyoung Kye, Seong-Woo Kim, Seung-Woo Seo(Seoul National University, Korea, Republic of )

This paper presents intention-aware autonomous driving at unsignalized intersections. The intention of traffic participant is modeled as a Dynamic Bayesian Network (DBN). Given the inference result, an intention-aware decision making problem is modeled as a Partially Observable Markov Decision Process (POMDP), which is regarded as one of the most widely used models for sequential decision making problem under uncertain environments. We implemented the proposed system in a passenger car, and effectiveness of the proposed algorithm is evaluated through experiments at real urban roads