Sim to Real:使用模拟进行3D感知和导航

所属专题:计算机视觉

嘉宾 : 杨睿刚 | 百度三维视觉首席科学家

讲师介绍

专题演讲嘉宾: 杨睿刚

百度 三维视觉首席科学家

RuigangYang is currently Chief Scientist for 3D Vision at Baidu Research. He leads theRobotics and Autonomous Driving Lab (RAL). Before joining Baidu. he was a fullprofessor of Computer Science at the University of Kentucky. He obtained hisPhD degree from University of North Carolina at Chapel Hill and his MS degreefrom Columbia University. His research interests span over computer graphicsand computer vision, in particular in 3D reconstruction and 3D data analysis.He has published over 100 papers, which, according to Google Scholar, hasreceived over 10000 citations with an h-index of 50 (as of 2018). He hasreceived a number of awards, including US NSF Career award in 2004, bestdemonstration award in CVPR 2006, and University of Kentucky’s Dean’s Research Award in2013. He is currently an associate editor of IEEE TPAMI and a senior member ofIEEE.

 杨睿刚,目前是百度研究部3D Vision的首席科学家。他领导机器人和自动驾驶实验室(RAL)。在加入百度之前,他是肯塔基大学计算机科学的全职教授。他在北卡罗来纳大学教堂山分校获得博士学位,在哥伦比亚大学获得硕士学位。他的研究兴趣涉及计算机图形学和计算机视觉,特别是3D重建和3D数据分析。他发表了100多篇论文,根据Google Scholar的说法,已经收到了超过10000篇论文,其h指数为50(截至2018年)。他曾获得多项奖项,包括2004年美国NSF职业奖,2006年CVPR最佳示范奖,以及2013年肯塔基大学院长研究奖。他目前是IEEE TPAMI副主编和IEEE高级会员。

议题介绍

演讲:Sim to Real:使用模拟进行3D感知和导航

Theimportance for simulations, in both robotics and more recently autonomous driving,has been more and more recognized. In this talk, I will talk the fairlyextensive line of simulation research at Baidu’s Robotics and Autonomous Driving Lab (RAL), fromlow-level sensor simulation, such as LIDAR, to high-level behavior simulation, such as drivers/pedestrians.  These different simulations tools aredesigned to either produce an abundant amount of annotated data to train deepneural network, or directly provide an end-to-end environment to test allaspects of robots/autonomous vehicles movement capabilities.

在机器人技术和最近的自动驾驶中,模拟的重要性已得到越来越多的认可。在本次演讲中,我将讨论百度机器人和自动驾驶实验室(RAL)中相当广泛的仿真研究,从低级传感器仿真(如LIDAR)到高级行为仿真(如驾驶员/行人)。这些不同的模拟工具旨在产生大量注释数据以训练深度神经网络,或直接提供端到端环境来测试机器人/自动车辆运动能力的所有方面。

交通指南

© 2019 Baidu - GS(2018)5572号 - 甲测资字1100930 - 京ICP证030173号 - Data © 长地万方
本网站图片存储由七牛云独家支持