http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Jihyun Yoon,Carl D. Crane III 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10
This paper presents a Quadtree algorithm which is one of the several possible methods that can be used to store an unknown amount of terrain data. The Quadtree algorithm is often used for visualizing large terrain. The Triangulated Irregular Network (TIN) method has been developed recently but it is difficult to make geographical operations such as neighbor finding, searching, and updating. The purpose of this paper is to show an easy way to implement these operations.
Jihyun Yoon,Carl D. Crane III 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8
This paper describes the autonomous ground vehicle developed by researchers at the University of Florida that participated in the 2007 DARPA Urban Challenge. Specifically, this paper introduces LADAR based terrain evaluation algorithms for an urban environment as well as off road. The terrain evaluation algorithm is very important for safe driving at high speed. On the real road, the driver is faced with numerous road conditions such as the smoothness of the road surface, curbs, or debris. For an unmanned vehicle to be successful, the algorithm has to decide whether the surface is traversable or non-traversable. For this reason, this paper focuses on the problem of extracting the ground terrain surface from 3-D point clouds obtained from LADAR sensors. The paper outlines the approach used by the University of Florida’ Team Gator Nation to address the question of classifying traversable road conditions.
Junghyun Kim,Carl D. Crane,Jungha Kim 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
This article aims to propose the navigation algorithm for autonomous driving of the skid steering vehicles based on the geometric method. The navigation system consists of two main concepts: the Skid Steering and Pure Pursuit methods. This study combines two concepts into one formula. And adds the two-compensation coefficient at the combined formula and organizes the concepts through mathematical proofs. The proposed formula has the advantage of being similar to the control of the ordinary vehicle with an Ackerman steering hardware system in a simple way and it doesn’t necessary the modeling process of the vehicle and various road environments. In the experiments section of this article, Simulations were conducted several times by varying the compensation coefficients to examine how to change the steering characteristics of the vehicle.
Jihyun Yoon,Carl D. Crane III 제어로봇시스템학회 2008 제어로봇시스템학회 국제학술대회 논문집 Vol.2008 No.10
This paper describes the development of an autonomous ground vehicle that participated in the 2007 DARPA Urban Challenge. Specifically, this pater introduces LADAR based static and moving obstacle detection algorithms for several traffic scenarios in the urban environment. The obstacle detection algorithm is critical for avoiding collisions with other vehicles and for safe driving at high speed. On the real road, the driver is faced with numerous traffic situations ranging from intersection traversal and lane changing to passing a stopped or slow moving car or performing a U-turn. For an unmanned vehicle to be successful, it must collect, iterpret and act on sensor data about the surrounding world. The 2007 DARPA Urban Challenge demonstrated various approaches to navigate through these traffic scenarios. This paper outlines the approach used by the University of Florida"s Team Gator Nation to address the question of both static and dynamic obstacle detection.
Path Planning for Unmanned Ground Vehicle In Urban Parking Area
Jihyun Yoon,Carl D. Crane 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10
This paper focuses on development of path planning for an Unmanned Ground Vehicle (UGV) during the parking behavior operation in an urban area. The proposed method developed in this paper is the Rapidly-exploring Random Tree (RRT) to search for a collision-free trajectory in an environment with moving and static obstacles. The collision avoidance is based on a geometric search in the transformed vehicle’s space. The line segments of the collision free path that is derived from the proposed method is interpolated to yield a smooth and short path. In order to test the strategy a C/C++ simulator incorporating an openGL visualizer was developed. The test vehicle is the Toyota Highlander hybrid vehicle which was developed for the 2007 DARPA Urban Challenge.
Active Relearning for Robust On-Road Vehicle Detection and Tracking
Vishnu K.Narayanan,Carl D. Crane, III 제어로봇시스템학회 2013 제어로봇시스템학회 국제학술대회 논문집 Vol.2013 No.10
This paper aims to introduce a novel robust real time system capable of rapidly detecting and tracking vehicles in a video stream using a monocular vision system. The framework used for this purpose is an actively relearned implementation of the Haar-like feature based Viola-Jones classifier capable of classifying image frame regions as a vehicle or non-vehicle. A passively trained supervised system (based on Adaboost) is initially built by cascading a set of weak classifiers working with Rectangular Haar-like features. An actively learned model is then generated from the initial passive classifier by querying misclassified instances when the model is evaluated on an independent dataset. This classifier is integrated with a Lucas-Kanade Optical Flow Tracker and an empirical distance estimation algorithm to evolve the system into a complete real-time detection and tracking system. The built model is then evaluated extensively on static as well as real world data and results are presented.
The Cognitive Driving Framework
Alan J. Hamlet,Patrick Emami,Carl D. Crane 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10
This paper describes a novel method for allowing an autonomous ground vehicle to predict the intent of other agents in an urban environment. This method, termed the cognitive driving framework, models both the intent and the potentially false beliefs of an obstacle vehicle. By modeling the relationships between these variables as a dynamic Bayesian network, filtering can be performed to calculate the intent of the obstacle vehicle as well as its belief about the environment. This joint knowledge can be exploited to plan safer and more efficient trajectories when navigating in an urban environment. Simulation results are presented that demonstrate the ability of the proposed method to calculate the intent of obstacle vehicles as an autonomous vehicle navigates a road intersection such that preventative maneuvers can be taken to avoid imminent collisions. The method is compared to a reactive planner in two intersection navigation scenarios.
C-EPS (C-type Electric Power Steering) 시뮬레이터 설계 및 제어 알고리즘 개발
박명욱(Myung-Wook Park),문희창(Hee-Chang Moon),김정하(Jung-Ha Kim),Carl D. Crane III 제어로봇시스템학회 2010 제어·로봇·시스템학회 논문지 Vol.16 No.6
EPS (Electric Power Steering) is important device for improving vehicle"s dynamics and static performances. This paper deals with simulator design for C-EPS (Colum type-EPS), development assist and returnability control algorithm. First, C-EPS system model was simply designed because EPS system is complex control system that has many unknown variables. These parameters were simplified through assumptions. Second, C-EPS simulator was designed for development of control algorithm. This simulator has SAS (Steering Angle Sensor), dual torque sensor, dual load cell for measuring rack force, dual linear actuator for generating tire force and Data Acquisition System. Using this simulator, control methods ware tested. Third, control algorithm was designed for torque assist and returnability. Assist torque map and returnability torque map were found by lots of simulation test. These torque maps were tuned for EPS actuator control. The simulation result was compared with non-EPS system result. In this research, the C-EPS simulator was designed for development of control algorithm about torque assistant and returnability. Using this simulator, control algorithm was improved.