报告题目： Omnidirectional-Vision Enabled Wheelchair Robot That Understands the Environment and User Intentions

报告人：Prof. Shigang Li, Graduate School of Information Sciences, Hiroshima City University, Japan

报告时间：2025年3月24日（星期一下午3：00-3：40）

报告地点：42教学楼320会议室

主办单位：电子信息工程学院

听众对象：学生和教职工

报告人简介： SHIGANG LI received the B.S. degree in electrical engineering from Beijing Tsinghua University, China, in 1985, and the M.S. and Ph.D. degrees from Osaka University, Japan, in 1990 and 1993, respectively. Now, he is a Professor with the Graduate School of Information Sciences, Hiroshima City University. His research interests include computer/robot vision, vision–language interfaces, and physical AI.

内容摘要： In this talk, I would like to introduce my research project on building a wheelchair robot that can understand environment and user intentions to assist its users effectively. The developed wheelchair robot features an omnidirectional camera to observe environment, and its user’s gaze point is also mapped onto the omnidirectional image to estimate the user’s intentions for effective assistance. Concretely, this talk consists of the following technical components: compensating the inclination of omnidirectional images to generate upright ones, estimating the depth of the surrounding environment from omnidirectional images, path following of wheelchair using an omnidirectional camera, wide-range gaze point estimation of wheelchair users by combining omnidirectional scene camera and face cameras. Future work is discussed also.