Title: User Modelling for Personalised Dressing Assistance by Humanoid Robots
报告题目：基于人型机器人提供个性化穿衣帮助的用户模型方法
Abstract: Assistive humanoid robots in home environments are steadily increasing in popularity. Due to significant variabilities in human behaviour, as well as physical characteristics and individual preferences, personalising assistance poses a challenging problem. Among various tasks in home environments, assistive dressing has great potential for strong societal impact, allowing elderly or disabled people to maintain aspects of their autonomy. However, it remains a challenging task for humanoid robots. In this talk, I will present three user modelling methods using different sensor information for humanoid robots to provide personalised dressing assistance to human users. We aim to address the important and challenging issue of user modelling: a robot learns to infer a user body model from multimodal streaming data, as well as user preferences, and adapts the assistance it provides to maximise its utility to the user.
报告摘要：目前，家庭环境下的辅助型人型机器人越来越受到大众的欢迎。由于每一个人在行为方式、身体特征和个人喜好方面存在显著差异，因此智能机器人如何针对不同的用户提供个性化的帮助是一个具有挑战性的问题。在家庭环境下的众多任务里，机器人辅助穿衣可以帮助老年人或者残障人士维持生活上的穿衣自理，因此具有极大的研究潜力和社会影响。但是，这个功能的实现对于人型机器人来说仍具有非常大的难度。在本次报告中，我将讲述三种不同的用户模型方法，这三种方法分别利用不同的传感器信息，帮助机器人对不同的用户提供个性化的穿衣帮助。我们的目的在于解决用户模型方法中一个重要的问题——就是机器人根据多模态的数据和用户的喜好进行学习并推测出用户的身体模型，从而能够针对不同用户来调整它的行为以提供最大化的帮助。
Biography: Dr Yixing Gao is a Teaching Fellow in the School of Computer Science at the University of Birmingham. She was admitted to the Special Class for the Gifted Young at Xi’an Jiaotong University at the age of 15, followed by the joint undergraduate & graduate programme in the Department of Electrical & Electronic Engineering. After completing a BSc in Automation, she obtained a full PhD scholarship from China Scholarship Council to pursue a PhD degree in robotics at Imperial College London, under the supervision of Professor Yiannis Demiris. After her graduation, she continued her research as a postdoctoral researcher at Imperial College London. Her research interests are assistive humanoid robots, assistive dressing robots, human-robot interaction, user modelling and computer vision. She has published two papers (oral) as the first author in the prestigious IEEE/RSJ conference on Intelligent Robots and Systems (IROS), along with other papers published on international journals and conferences. She has peer-reviewed journal and conference papers for Robotics and Autonomous Systems, IEEE Robotics and Automation Letters, Autonomous Robots, Frontiers in Robotics and AI, IEEE Transactions on Cognitive and Developmental Systems, Frontiers in Neurorobotics and IEEE RoboSoft. She was invited by Robots and Intelligent Systems Symposium of London PhD Network to give a presentation on assistive dressing by humanoid robots at Imperial College London.
报告人简介：高一星，英国伯明翰大学计算机系讲师。十五岁考入西安交通大学少年班，两年后本硕连读保送至西安交通大学电子与信息工程学院。自动化专业本科毕业后，研一期间被英国帝国理工大学(Imperial College London)破格录取为机器人专业的博士研究生，获得国家留学基金委公派出国四年全额奖学金，赴英国帝国理工大学师从Yiannis Demiris教授攻读博士。毕业后继续在英国帝国理工大学从事了博士后研究，现为英国伯明翰大学计算机系讲师。研究方向为辅助型人型机器人、智能穿衣机器人、人机交互、用户建模和计算机视觉。曾在国际机器人领域顶级会议IROS以第一作者身份发表两篇论文，均被选为口头报告论文，并在多个国际期刊和会议上发表论文。担任Robotics and Autonomous Systems, IEEE Robotics and Automation Letters, Autonomous Robots, Frontiers in Robotics and AI, IEEE Transactions on Cognitive and Developmental Systems, Frontiers in Neurorobotics, IEEE RoboSoft国际期刊和会议的审稿人。曾受伦敦博士联盟之机器人与智能系统座谈会的邀请，在英国帝国理工大学进行了题为辅助型穿衣的人型机器人的学术报告演讲。
报告时间：12月16日 上午9:30-10:30
报告地点：水务集团大楼403教室
主办单位：吉林大学人工智能学院
