中国科大学位与研究生教育
课程名称: 教师:
当前位置:
 >> 
 >> 
自动驾驶的传感器融合
自动驾驶的传感器融合
教师介绍

本讲教师:Ting Yuan
所属学科:工科
人  气:644

课程介绍
Dr. Ting Yuan is currently a Senior Research Scientist at the Mercedes-Benz Research & Development North America, Inc., Sunnyvale, where his fields of endeavor lie in detection, classification and tracking of moving/static objects using information from camera, Radar and Lidar systems and data fusion for the multi-sensor systems. He received his Ph.D. degree from the Electrical and Computer Engineering Department at the University of Connecticut, Storrs, CT, USA in 2013. He has more than 10 years research experience in Object Tracking, Sensor Fusion and Localization. Autonomous driving poses unique challenges for real world sensor fusion systems due to the complex driving environment where the autonomous vehicle finds itself in and interacts itself with surrounding objects. Precise knowledge of the relevant participants becomes a key component for the task of comprehensive environmental perception and scene understanding. We will talk about the current trend about autonomous driving in Silicon Valley. We will introduce the different environment representations frameworks from heterogeneous automotive sensors e.g. Radars, stereo/mono cameras and Lidars. The relevant state estimation algorithms, sensor fusion frameworks and the evaluation procedures with reference ground truth are presented in detail. An interesting glimpse of the data set obtained from a sensor configuration that would be used in the future Mercedes Benz autonomous vehicles will be shown. In particular, we try to elaborate the relationship in proper sensor setup, clean software architecture, and advanced algorithms for a satisfying autonomous vehicular settings and requirements.

评论

针对该课程没有任何评论,谈谈您对该课程的看法吧?
  • 用户名: 密 码:
致谢:本课件的制作和发布均为公益目的,免费提供给公众学习和研究。对于本课件制作传播过程中可能涉及的作品或作品部分内容的著作权人以及相关权利人谨致谢意!
课件总访问人次:16351196
中国科学技术大学研究生网络课堂试运行版,版权属于中国科学技术大学研究生院。
本网站所有内容属于中国科学技术大学,未经允许不得下载传播。
地址:安徽省合肥市金寨路96号;邮编:230026。TEL:+86-551-63602922;E-mail:wlkt@ustc.edu.cn。