报告时间：2018年7月3日早上10:30-11:30
报告地点：浙江大学紫金港校区蒙民伟楼402会议室
报告题目：Towards Autonomous Navigation in the Wild
报告人：黄国权 助理教授
主持人：章国锋 教授

Abstract:
Autonomous vehicles are emerging in many different application domains from self-driving cars and drone delivery to underwater survey. While tremendous progress in autonomous navigation has been made in the past decades, many challenges still remain, in particular, when operating in GPS-denied complex real world. For example, existing sate estimation algorithms of robot localization tend to become inconsistent (i.e., the state estimates are biased and the error covariance estimates are different from the true ones), causing mission failure in a short period of time. This problem is even exacerbated if resources available to vehicles are stringent (which is almost always the case for engineered robotic systems). Moreover, current onboard navigation systems are not secure and can be hijacked or deliberately controlled for malicious purposes, exposing us to unprecedented vulnerabilities due to increasing proliferation of autonomous vehicles as well as malicious attacks.
In this talk, I will present some of our recent work on taking up these challenges. In particular, I will discuss our observability-constrained methodology for improving estimation consistency in the context of robot localization and mapping including simultaneous localization and mapping (SLAM), visual-inertial navigation system (VINS) and multi-robot cooperative localization (CL). Moreover, I will highlight our recent results on secure estimation for  map-based localization, deep loop closure for SLAM, and visual-inertial navigation under resource constraints. Lastly, I will extend these results to underwater navigation.

Bio:
Guoquan (Paul) Huang is currently an Assistant Professor of Mechanical Engineering (ME), Electrical and Computer Engineering (ECE), and Computer and Information Sciences (CIS), at the University of Delaware (UD), where he is leading the Robot Perception and Navigation Group (RPNG). He is also an Adjunct Professor at the Zhejiang University, Hangzhou, China and a Senior Consultant at the Huawei 2012 Laboratories. From 2012 to 2014, he was a Postdoctoral Associate at MIT CSAIL (Marine Robotics Group). He received the B.Eng. (2002) in Automation (Electrical Engineering) from the University of Science and Technology, Beijing, China, and the M.Sc. (2009) and Ph.D. (2012) in Computer Science from the University of Minnesota. From 2003 to 2005, he was a Research Assistant with the Department of Electrical Engineering, Hong Kong Polytechnic University. His research interests include sensing, localization, mapping, and perception of autonomous ground, aerial, and underwater robots. Dr. Huang received the 2006 Academic Excellence Fellowship from the University of Minnesota, the 2011 Chinese Government Award for Outstanding Self-Financed Students Abroad, the 2015 UDRF Award, the 2016 NSF CRII Award, the 2017 UD Makerspace Faculty Fellow, the 2018 ASME Robotics Delegation of SATEC, the 2018 Google Daydream Faculty Research Award, and was the Finalist for the 2009 Best Paper Award from the Robotics: Science and Systems Conference (RSS).