• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.434-437
• /
• 2018

본 논문에서는 ROS (Robot Operating System)에 대해서 소개하고 ROS를 이용해 드론의 제어기와 필터를 구현해본다. 드론이 강인한 성능을 보이기 위해서는 기체의 상태에 대한 더 정확한 추정이 필요하다. 드론이 기체좌표계로 출력하는 각 축(x축, y축, z축)에 대한 선속도, 선가속도를 더 정확히 추정하기 위해 칼만 필터를 설계하며 칼만 필터를 통과한 상태 변수를 제어 입력으로 하는 PID(Proportional Integral Derivative) 제어기를 설계한다. 실험적인 부분에서는 제어기와 자율 주행 알고리즘을 접목시켜 드론이 자신의 상태를 추정하고 알고리즘을 순차적으로 진행하는 과정을 살펴본다. 마지막으로 알고리즘을 통해 드론의 임무 수행 여부를 살펴보고 정밀한 제어를 위한 추가적인 제어기 설계 방법과 연구 방향을 제시하고자 한다.

• 항공우주시스템공학회지
• /
• 제13권3호
• /
• pp.15-22
• /
• 2019

본 논문에서는 무인항공기의 자율 비행을 위한 전역 및 지역 경로 비행 시스템을 제안한다. 전체적인 시스템은 ROS 로봇 운영체제를 기반으로 구축하였다. 무인항공기에 탑재된 임베디드 컴퓨터는 2-D Lidar를 이용하여 장애물을 검출하고, 실시간으로 VFH 기반의 지역 경로와 제안하는 Modified $RRT^*$-Smart 기반의 전역 경로를 생성한다. 또한, 무인항공기의 비행컨트롤러에 Mavros 통신 프로토콜을 이용하여 생성된 경로에 따른 이동 명령을 내린다. 지상국 컴퓨터는 장애물 정보를 수신하여 2-D SLAM 지도를 생성하고, 목적 지점을 임베디드 컴퓨터에 전달하며 무인항공기의 상태를 관장한다. 제안하는 무인항공기의 자율 비행 시스템을 3-D 공간 상의 시뮬레이터 및 실제 비행을 통해 검증하였다.

• 제어로봇시스템학회논문지
• /
• 제21권2호
• /
• pp.87-94
• /
• 2015

This paper proposes a situation awareness method based on data fusion and independent objects for autonomous driving in on-road environment. The proposed method, designed to achieve an accurate analysis of driving situations in on-road environment, executes preprocessing tasks that include coordinate transformations, data filtering, and data fusion and independent object based situation assessment to evaluate the collision risks of driving situations and calculate a desired velocity. The method was implemented in an open-source robot operating system called ROS and tested on a closed road with other vehicles. It performed successfully in several scenarios similar to a real road environment.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 추계학술발표대회
• /
• pp.961-964
• /
• 2017

드론의 대중화에 따른 사고위험의 증가로 안전한 조종 방법에 대한 연구의 필요성이 대두되었다. 따라서 조종자의 조종능력에 구애받지 않는 자율비행제어기술이 필요하게 되었고, 이를 보다 안정적으로 구현하기 위하여 자율주행 소프트웨어 플랫폼으로 주목받고 있는 Robot Operating System(ROS)를 사용하였다. ROS를 기반으로 Laser Range Finder(LRF)와 Particle Filter를 사용하여 자율적으로 객체추적이 가능하며 지능적으로 장애물을 회피하여 비행 할 수 있는 안정적인 자율비행제어시스템을 구현하고자 한다.

• 자동차안전학회지
• /
• 제13권4호
• /
• pp.123-128
• /
• 2021

This paper present box feature estimation from LiDAR point cluster using maximum likelihood Method. Previous LiDAR tracking method for autonomous driving shows high accuracy about velocity and heading of point cluster. However, Assuming the average position of a point cluster as the vehicle position has a lower accuracy than ground truth. Therefore, the box feature estimation algorithm to improve position accuracy of autonomous driving perception consists of two procedures. Firstly, proposed algorithm calculates vehicle candidate position based on relative position of point cluster. Secondly, to reflect the features of the point cluster in estimation, the likelihood of the particle scattered around the candidate position is used. The proposed estimation method has been implemented in robot operating system (ROS) environment, and investigated via simulation and actual vehicle test. The test result show that proposed cluster position estimation enhances perception and path planning performance in autonomous driving.

• 자동차안전학회지
• /
• 제13권4호
• /
• pp.14-19
• /
• 2021

This paper presents LiDAR static obstacle map based vehicle dynamic state estimation algorithm for urban autonomous driving. In an autonomous driving, state estimation of host vehicle is important for accurate prediction of ego motion and perceived object. Therefore, in a situation in which noise exists in the control input of the vehicle, state estimation using sensor such as LiDAR and vision is required. However, it is difficult to obtain a measurement for the vehicle state because the recognition sensor of autonomous vehicle perceives including a dynamic object. The proposed algorithm consists of two parts. First, a Bayesian rule-based static obstacle map is constructed using continuous LiDAR point cloud input. Second, vehicle odometry during the time interval is calculated by matching the static obstacle map using Normal Distribution Transformation (NDT) method. And the velocity and yaw rate of vehicle are estimated based on the Extended Kalman Filter (EKF) using vehicle odometry as measurement. The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment, and is verified with data obtained from actual driving on urban roads. The test results show a more robust and accurate dynamic state estimation result when there is a bias in the chassis IMU sensor.

• 한국ITS학회 논문지
• /
• 제20권3호
• /
• pp.86-99
• /
• 2021

본 연구는 V2I통신을 이용하여 교차로 등의 사각지대로 인해 발생할 수 있는 충돌 사고를 예방하기 위한 충돌 방지체계를 제안한다. 교차로의 인프라에 위치한 Vision센서와 LiDAR센서가 물체를 인식하고 사고 위험이 있는 차량에게 경고함으로써 사고를 미연에 방지한다. 딥러닝 기반의 YOLOv4를 이용하여 교차로에 진입하는 물체를 인식하고 LiDAR 센서와의 Calibration을 통해 대상 물체와의 맨하탄 거리값을 이용하여 충돌 예상시간과 제동거리에 대한 가중치를 계산하고 안전거리를 확보한다. 차량-인프라간 통신은 ROS통신을 이용하였으며 충돌 경고 외에도 진입 물체의 Class, 거리, 진행속도 등의 다양한 정보를 차량에 전달함으로써 사고를 미연에 방지하고자 하였다.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권3호
• /
• pp.209-215
• /
• 2022

As intelligent autonomous driving vehicle development has become a big topic around the world, accurate reference dynamics estimation has been more important than before. Current systems generally use speed and heading information sensed from a distant point as a vehicle reference dynamic, however, the dynamics between different points are not same especially during rotating motions. In order to estimate properly estimate the reference dynamics from the information such as velocity and heading sensed at a point distant from the reference point such as center of gravity, this study proposes estimating reference dynamics from any location in the vehicle by combining the Bicycle and Ackermann models. A test system was constructed by implementing multiple GNSS/INS equipment on an Robot Operating System (ROS) and an actual car. Angle and speed errors of 10° and 0.2 m/s have been reduced to 0.2° and 0.06 m/s after applying the suggested method.

• 자동차안전학회지
• /
• 제14권2호
• /
• pp.39-44
• /
• 2022

This paper presents LiDAR static obstacle map based vehicle position correction algorithm for urban autonomous driving. Real Time Kinematic (RTK) GPS is commonly used in highway automated vehicle systems. For urban automated vehicle systems, RTK GPS have some trouble in shaded area. Therefore, this paper represents a method to estimate the position of the host vehicle using AVM camera, front camera, LiDAR and low-cost GPS based on Extended Kalman Filter (EKF). Static obstacle map (STOM) is constructed only with static object based on Bayesian rule. To run the algorithm, HD map and Static obstacle reference map (STORM) must be prepared in advance. STORM is constructed by accumulating and voxelizing the static obstacle map (STOM). The algorithm consists of three main process. The first process is to acquire sensor data from low-cost GPS, AVM camera, front camera, and LiDAR. Second, low-cost GPS data is used to define initial point. Third, AVM camera, front camera, LiDAR point cloud matching to HD map and STORM is conducted using Normal Distribution Transformation (NDT) method. Third, position of the host vehicle position is corrected based on the Extended Kalman Filter (EKF).The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment and showed better performance than only lane-detection algorithm. It is expected to be more robust and accurate than raw lidar point cloud matching algorithm in autonomous driving.

• Journal of Advanced Research in Ocean Engineering
• /
• 제3권3호
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.