20160318-07 肖健雄：Three Design Principles for Robust Robot Perception

【16-07期VALSE Webinar活动】

报告嘉宾：肖健雄（Princeton University）

报告时间：2016年3月18日（星期五）上午10:00（北京时间）

主持人：郭裕兰（国防科技大学）

报告题目：Three Design Principles for Robust Robot Perception

文章信息：Paper title, authors, Journal,2015

报告摘要：Recent years have seen tremendous progress in the development of autonomous machines. Autonomous cars have driven over a million miles, and robots regularly perform tasks too dangerous or monotonous for human beings. However, despite these advancements, robots are still highly dependent on human operators or carefully designed environments. In one prominent example, the DARPA Robotics Challenge asked dozens of robots to complete tasks in a mock disaster response scenario. But no team felt that the robots could robustly perceive their surroundings, opting to outsource all perception to humans. Team KAIST, the eventual winner, "found that the most (actually all) famous algorithms are not very effective in real situations."

In this talk, I will address how to bridge the gap between computer vision and robot perception, summarizing my experience in three design principles. First, I will argue that it is crucial for the algorithm to fully operate end-to-end in three-dimensions, introducing a newly created area called "3D Deep Learning". I will demonstrate this idea on object detection, view planning, and mapping in the household robotics scenario. Second, I will highlight the importance of direct perception to estimate affordances for a robot's actions, demonstrating the idea in an autonomous driving application. Third, I will propose the design of robot systems with failure modes of perception in mind, allowing for pitfall avoidance and an extremely high level of robustness. Finally, I will briefly mention some ongoing works in Big Data Robotics, Robot Learning, and Human Robot Collaboration.

报告人简介：Jianxiong Xiao is an Assistant Professor in the Department of Computer Science at Princeton University and the director of the Princeton Vision Group. He received his Ph.D. from the Computer Science and Artificial Intelligence Laboratory (CSAIL) at Massachusetts Institute of Technology (MIT) in 2013. Before that, he received a BEng. and MPhil. in Computer Science from the Hong Kong University of Science and Technology in 2009. His research focuses on bridging the gap between computer vision and robotics by building extremely robust and dependable computer vision systems for robot perception. In particular, he is interested in 3D Deep Learning, RGB-D Recognition and Mapping, Household Robotics, Autonomous Driving, and Robot Learning. His work has received the Best Student Paper Award at the European Conference on Computer Vision (ECCV) in 2012 and Google Research Best Papers Award for 2012, and has appeared in popular press in the United States. Jianxiong was awarded the Google U.S./Canada Fellowship in Computer Vision in 2012, MIT CSW Best Research Award in 2011, and two Google Research Awards in 2014 and in 2015. More information can be found at: http://vision.princeton.edu.