学术论坛讲座-Chin-An Tan教授—6月25日
发布时间: 2019-06-21      浏览次数: 1365    发布人: 汤蓓
1


学术论坛通知:本期学术论坛由Wayne State UniversityProfessor Chin-An Tan主讲


题目:Sensor Fusion andMotion Planning for Autonomous Vehicles: Application to Automated ParkingSystem


报告人:Professor Chin-An Tan


时间: 2019625日,15:30-16:30


地点:机械楼南高厅


报告摘要:

Most camera-basedauto-parking features are limited to partial autonomy, not intelligent enough topark a vehicle automatically without the participation of a driver. Camera-basedauto-parking systems can detect parking spots but cannot accurately localisethe vehicle as well as the parking spot. Our objective is to design advancedsensor fusion and motion planning algorithms for an Automated Parking Assist(APA) system. These algorithms are specifically designed for ADAS under lowvelocity and requires high precision vehicle maneuvering, by increasing thelocalisation accuracy, in terms of vehicle and parking spot locations. The APAsystem will help the driver to search for available parking spots and drive thevehicle into the parking spot safely. The strategic architecture of theauto-parking system includes environment perception, sensor data fusion, motionplanning, and vehicle control. Perception algorithms such as line detection andobject detection will be discussed. Sensor data fusion and data associationusing Extended Kalman Filter for parking spot and vehicle location tracking aredeveloped. Rapidly-exploring Random Tree (RRT) motion planning algorithm isused to generate a path, leading the vehicle to park into the parking spot.Simulations for sensor data processing, data association and motion planningare conducted in a Robot Operating System (ROS) environment. A versatilevirtual environment with vehicle dynamics model and control algorithms aredeveloped in the simulation environment. Parking spot detection, vehiclebehavior decision making, and motion planning are tested, based on virtualsensor signals modelled in ROS. Simulation results show that the vehicle candrive automatically into the parking spot without the participation of adriver. Experiments on a fully instrumented vehicle are being planned tovalidate these and other mobility simulation results.

报告人简介:

Professor Chin-An Tangraduated from the University of California at Berkeley with B.S. and Ph.D.degrees in Mechanical Engineering, and from the California Institute ofTechnology with a M.S. degree in Aeronautics. Upon completion of graduatestudies, he joined the Mechanical Engineering Department of Wayne State University,and is currently a full Professor. His research and technical interests lie inthe fields of structural dynamics and vibration, mechatronics, systemidentification, and NVH applications. Current research topics and interestsinclude: dynamic modeling and controls with applications to autonomous drivingof vehicles, robotics, and ultrasonic welding processes in automotive batterymanufacturing; moving

vehicles interactingwith continuous structures; wave propagation and absorption in multi-physicssystems. Prof. Tan is a Fellow of theAmerican Society of Mechanical Engineers (ASME). He has served as AssociateEditors for ASME Applied Mechanics Review and ASME Journal of Vibration andAcoustics, an Associate Dean of Engineering at Wayne State, and on theEditorial Board of the Communications in Nonlinear Science and NumericalSimulations. Recently, he has also served as a technical consultant to theelectric vehicle battery manufacturing program at the General Motors ResearchLaboratory.


欢迎广大师生参加!