Student presents research on Human-Robot interaction
A Cornell College senior presented his research at the premier conference on Human-Robot Interaction.
Alex Hubers, a computer science major, presented his research at the 10th annual ACM/IEEE International Conference on Human-Robot Interaction, March 2-5, in Portland, Oregon. The conference, which is sponsored by the Association for Computing Machinery and the Institute of Electrical and Electronics Engineers Computer Society, attracts researchers from across the world who attend to share and discuss the latest theories, technology, data, and videos furthering the state-of-the-art in human-robot interaction. The conference is highly selective and aims to showcase the very best interdisciplinary and multidisciplinary research in human-robot interaction with roots in and broad participation from communities that include robotics, human-computer interaction, artificial intelligence, engineering, and social and behavioral sciences.
An abstract of Hubers’ paper, “Video Manipulation Techniques for the Protection of Privacy in Remote Presence Systems,” was published in the conference proceedings, and a full-text version is available online. The research and resulting paper is the product of collaborative research over the past two summers with Ross Sowell, assistant professor of computer science at Cornell College. The paper was co-authored by Hubers and Sowell, along with colleagues at Oregon State University and five current and former Cornell students: junior Emily Andrulis, senior Tanner Stirrat, Ruonan Zhang ’14, Levi Scott ’13, and Duc Tran.
The research focused on the fact that systems that give control of a mobile robot to a remote user raise privacy concerns about what the user can see and do through the robot. Hubers and the others conducted two user studies. In the first, participants were asked to watch a video captured by a robot exploring an office environment and to complete a series of observational tasks. The results of that study showed manipulations of the video stream can lead to fewer privacy violations. The second study showed that video manipulations were able to protect privacy without making it more difficult for the remote user to complete tasks.
