南开大学机器人与信息自动化研究所
Institute of Robotics and Automatic Information System
2012年秋季先进机器人与MEMS技术系列学术讲座
Seminar Series：Advanced Robotics & MEMS

题目：Topologically Modeling for Robotic Mapping, Localization and Navigation
报告人：刘明 博士
单位：Department of Mechanical and Process Engineering
Swiss Federal Institute of Technology (ETH) Zurich, Switzerland

时间：2013年1月2日 周三 下午2:30-4:30
地点：主楼227室

Abstract:
Mobile robots are intelligent agents to be designed to serve people in various circumstances. The target environments can be ranged from indoor to outdoor, 2D to 3D, structured to unstructured etc. With time,more and more robots will share these environments with humans. for example, service robots in family and autonomous cars on road etc. Beside the robots that humans utilize as auxiliary, sometimes robots can even do better than humans in extreme cases. Taking Urban Search And Rescue (USAR) missions as an instance, we could see that more and more robots are applied. These special robots act as intelligent team-members of the rescue team. In all these cases above, it is important that the robots are able to provide an efficient representation of the environment, which can be used as a common understanding among all involved subjects in the scenario. Works by psychologists demonstrated that Humans can understand their surroundings by mostly topological meanings. An example can be observed as for service robots. In most situations, human may like to control the robot by naming - go to the “kitchen” or “grandpa’s bed”. Topological modeling of the environment would greatly help these applications. Moreover, the navigation
among topological nodes in the environment is essential to carry out practical services. Based on these observations, with this talk, I present contributions in the field of robotics navigation, robot mapping, visual control, unsupervised and semi-supervised clustering algorithms, information theory based validation, parallel computing etc. Especially, all these aspects are tightly integrated with topological environment models.
Besides, I will introduce the current research of Autonomous Systems Lab (ASL) of ETH, which is one of the leading laboratories in the fields such as mobile robots, micro aerial vehicles, legged robots and surveillance robots.

Biography:
Ming Liu was born in Zibo, Shandong, P.R.China, 1984. He is an IEEE Student member since 2012. He received the B.A.degree in Automation at Tongji University in 2005. During his master study at Tongji University, he stayed one year in Erlangen-Nünberg University and Fraunhofer Institute IISB, Germany, as a visiting scholar. Since 2009, he has been working as PhD student in the Mechanical and Process Engineering department of ETH Zürich. He is a founding member of Shanghai SWing Automation Ltd. Co. He is also conducted with several NSF projects, and National 863-Hi-Tech-Plan projects in China, on dynamic system modeling and environment perception. As a team member, he won the second place of European Micro Aerial Vehicle Competition 2009. He won best student paper award as first author for MFI 2012, and best paper finalist for MFI 2012. He is the organizer and coordinator of a sequence of Sino-swiss projects in the field of manufacturing, control and design.
Ming Liu’s research interests include dynamic environment modeling, 3D mapping, machine learning and visual control. He is particularly interested in the investigation of novel, real-time online approaches in solving mobile robot mapping and navigation. In general, he can be stimulated by research in all robotic and intelligent system fields.
For further information please visit: http://www.asl.ethz.ch/people/lium/personal