• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.157-161
• /
• 2003

본 논문에서는 차량의 주행경로 최적화를 위해 강화학습 개념을 적용하고자 한다. 강화학습의 특징은 관심 대상에 대한 구체적인 지배 규칙의 정보 없이도 최적화된 행동 방식을 학습시킬 수 있는 특징이 있어서, 실제 차량의 주행경로와 같이 여러 교통정보 및 시간에 따른 변화 등에 대한 복잡한 고려가 필요한 시스템에 적합하다. 또한 학습을 위한 강화(보상, 벌칙)의 정도 및 기준을 조절해 즘으로써 다양한 최적주행경로를 제공할 수 있다. 따라서, 본 논문에서는 강화학습 알고리즘을 이용하여 다양한 최적주행경로를 제공해 주는 시스템을 구현한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.365-366
• /
• 2023

본 논문은 F1TENTH 와 같은 자율주행 경주 대회를 위한 고전적인 자율주행 알고리즘의 파라미터 최적화에 관한 연구를 다룬다. 고전적인 자율주행 알고리즘은 하이퍼파라미터의 영향을 크게 받고 더 나아가서 하이퍼파라미터의 설정에 따라서 성능의 차이가 크다. 이 하이퍼파라미터를 빠르게 찾기 위하여 Piece and Conquer Fireworks 방법을 제안한다. 결과적으로Random search에 비해서 일반 Fireworks알고리즘은 약8.3배, Piece and Conquer Fireworks알고리즘은 약 28.5배 빠른 성능을 보여준다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.10
• /
• pp.931-940
• /
• 2017

This paper describes a predictive fault diagnosis algorithm for autonomous vehicles based on a kinematic model that uses a sliding mode observer. To ensure the safety of autonomous vehicles, reliable information about the environment and vehicle dynamic states is required. A predictive algorithm that can interactively diagnose longitudinal environment and vehicle acceleration information is proposed in this paper to evaluate the reliability of sensors. To design the diagnosis algorithm, a longitudinal kinematic model is used based on a sliding mode observer. The reliability of the fault diagnosis algorithm can be ensured because the sliding mode observer utilized can reconstruct the relative acceleration despite faulty signals in the longitudinal environment information. Actual data based performance evaluations are conducted with various fault conditions for a reasonable performance evaluation of the predictive fault diagnosis algorithm presented in this paper. The evaluation results show that the proposed diagnosis algorithm can reasonably diagnose the faults in the longitudinal environment and acceleration information for all fault conditions.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.211-214
• /
• 2004

본 논문은 논리 연산을 이용한 실시간 주행 차량 분할 및 추적에 관한 알고리즘을 제안하였다. 연속된 프레임 간에 논리연산을 이용하여 영상을 분할하고, 배경과 잡음을 제거하였으며 영상에서 주행차량의 이동 영역을 추출하였다. 주행차량들을 논리 연산을 이용하여 영상분할 함으로써 기존 방법에 비해 평활화 및 에지추출 단계에서 나타날 수 있는 문제점들을 제거하였고, 전처리 단계를 줄였으며, 알고리즘을 단순화 하였다. 또한 추적되는 영상으로부터 위치와 컬러등의 주행 차량의 특징을 직접 추출 가능하도륵 하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.329-336
• /
• 2008

Nowadays with advancement in technology and aging society, the number of disabled citizens is increasing. The disabled citizens always need a caretaker for daily life routines especially for mobility. In future, the need is considered to increase more. To reduce the burden from the disabled, various devices for healthcare are introduced using computer technology. The power wheelchair is an important and convenient mobility device. The demand of power wheelchair is increasing for assistance in mobility. In this paper we proposed a robotic wheelchair for mobility aid to reduce the burden from the disabled. The main issue in an autonomous wheelchair is the automatic detection and avoidance of obstacles and going to the pre-designated place. The proposed algorithm detects the obstacles and avoids them to drive the wheelchair to the desired place safely. By this way, the disabled will not always have to worry about paying deep attention to the surroundings and his path.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.175-189
• /
• 2023

Fault detection and diagnosis (FDI) algorithms are actively being researched for ensuring the integrity and reliability of environment perception sensors in autonomous vehicles. In this paper, a fault detection algorithm based on a multi-sensor perception system composed of radar, camera, and lidar is proposed to guarantee the safety of an autonomous vehicle's perception system. The algorithm utilizes reference generation filters and residual generation filters based on finite impulse response (FIR) filter estimates. By analyzing the residuals generated from the filtered sensor observations and the estimated state errors of individual objects, the algorithm detects faults in the environment perception sensors. The proposed algorithm was evaluated by comparing its performance with a Kalman filter-based algorithm through numerical simulations in a virtual environment. This research could help to ensure the safety and reliability of autonomous vehicles and to enhance the integrity of their environment perception sensors.

• Journal of Korea Spatial Information System Society
• /
• v.10 no.3
• /
• pp.31-43
• /
• 2008

Travel time prediction is an indispensable to many advanced traveler information systems(ATIS) and intelligent transportation systems(ITS). In this paper we propose a method to predict travel time using $Na{\ddot{i}}ve$ Bayesian classification method which has exhibited high accuracy and processing speed when applied to classily large amounts of data. Our proposed prediction algorithm is also scalable to road networks with arbitrary travel routes. For a given route, we consider time-varying average segment velocity to perform more accuracy of travel time prediction. We compare the proposed method with the existing prediction algorithms like link-based prediction algorithm [1] and Micro T* algorithm [2]. It is shown from the performance comparison that the proposed predictor can reduce MARE (mean absolute relative error) significantly, compared with the existing predictors.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.924-926
• /
• 2017

본 논문에서는 좁고 곡률이 큰 도로에서의 자율 주행을 위한 AVM 시스템 기반의 알고리즘을 제안한다. 기존의 전방을 주시하는 모노/스테레오 카메라를 이용한 차선 인식 방법을 이용한 자율주행 알고리즘은 모노/스테레오 카메라의 제한된 FOV (Field of View)로 인해 좁고 곡률이 큰 도로에서의 자율 주행에 한계가 있다. 제안하는 알고리즘은 AVM 시스템을 기반으로 하여 이 한계를 극복하고자 한다. AVM 시스템에서 얻은 영상을 차선의 색상 정보를 이용해 차선의 영역을 이진화 한다. 이진화 영상으로부터, 차량의 뒷바퀴 주변의 관심영역을 시작으로 재귀적 탐색법을 이용하여 좌, 우 차선을 검출한다. 검출된 좌, 우 차선의 중앙선을 차량의 경로로 삼고 조향각을 산출해 낸다. 제한하는 알고리즘을 실제 차량에 적용시킨 실험을 수행하였고, 운전면허 시험장의 코스를 차선의 이탈없이 주행 가능함을 실험적으로 확인하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.265-275
• /
• 2023

The purpose of this paper is to devise an optimal route allocation algorithm for automated vehicle(AV) in monitoring quality of road infrastructure to support the road safety. The tasks of an AV in this paper include visiting node-links at least once during its operation and checking status of road infrastructure, and coming back to its depot.. In selecting optimal route, its priority goal is visiting the node-links with higher risks while reducing costs caused by operation. To deal with the problem, authors devised reward maximizing algorithm for AVs. To check its validity, the authors developed simple toy network that mimic node-link networks and assigned costs and rewards for each node-link. With the toy network, the reward maximizing algorithm worked well as it visited the node-link with higher risks earlier then chinese postman route algorithm (Eiselt, Gendreau, Laporte, 1995). For further research, the reward maximizing algorithm should be tested its validity in a more complex network that mimic the real-life.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.5
• /
• pp.609-617
• /
• 2013

This paper presents a near-minimum time path planning algorithm for autonomous driving. The problem of near-minimum time path planning is an optimization problem in which it is necessary to take into account not only the geometry of the circuit but also the dynamics of the vehicle. The path planning algorithm consists of a candidate path generation and a velocity optimization algorithm. The candidate path generation algorithm calculates the compromises between the shortest path and the path that allows the highest speeds to be achieved. The velocity optimization algorithm calculates the lap time of each candidate considering the vehicle driving performance and tire friction limit. By using the calculated path and velocity of each candidate, we calculate the lap times and search for a near-minimum time path. The proposed algorithm was evaluated via computer simulation using CarSim and Matlab/Simulink.