报告题目: 云嵌入式无人驾驶汽车决策支持系统

       Future Mobility: Cloud-Enabled Automotive Decision-Making Systems

       报 告 人：Zhaojian Li (李照剑)  Michigan State University

       报告时间：2017年12月21日下午4点

       报告地点：自动化学院泰山报告厅
报告人简介：
    李照剑，2015年获密歇根大学航空工程系飞行动力学与控制专业博士学位；2016年美国福特公司高级工程师，主要从事基于云计算的智能汽车控制系统研发；2017年任职密歇根州立大学机械工程系副教授；在国际权威期刊IEEE汇刊等发表30多篇论文，出版学术专著2部。
报告摘要：
    Interest in employing cloud computing for automotive applications is growing to support computation and data intensive tasks. The cloud can provide access to “big data" as well as real-time crowd-sourced information. Smart utilization of on-demand cloud resources can increase situation awareness and provide additional functionalities.
    In this talk, I will first present the Vehicle-to-Cloud-to-Vehicle framework and discuss its opportunities and challenges. The focus of the talk will be the exploitation of automotive vehicles to crowd-source road information. In this research, we developed an optimal state estimator for systems driven by jump-diffusion process. The developed estimator, together with an input observer, was used to estimate road profile and detect road anomalies such as potholes and speed bumps. I will also present an evolving clustering algorithm that is used to process the anomaly reports. Future work on Reinforcement Learning and Connected and Autonomous Vehicles will also be discussed.