Proposed RSS 2019 Workshop
June 22-26, 2019
Robots are increasingly becoming members of our everyday community. Self-driving cars, surgical and rehabilitation devices, and social and assistive robots operate alongside human end-users to carry out interactive tasks. In order for robots to transition from isolated systems to intelligent partners, however, these robots need to understand the humans they are interacting with: how to learn from human actions, how humans adapt to robots, and how robot actions can influence nearby humans.
This workshop promotes a discussion on the role of computational models of humans in robotics, and highlights the different ways in which robots can model human partners to achieve fluent, efficient, and successful interactions. We're bringing together researchers to explore challenges in computational human-robot interaction, where we plan to discuss technical advances in:
We seek contributions and insight from researchers whose interests span human modeling, human-robot interaction, and learning from humans.
Logistics: 25 minute talks followed by 5 minute discussions.
|08:50 AM - 09:00 AM||Workshop Introduction|
|09:00 AM - 09:30 AM||speaker 1|
|09:30 AM - 10:00 AM||speaker 2|
|10:00 AM - 10:30 AM||Discussion and Coffee Break|
|10:30 AM - 11:00 AM||speaker 3|
|11:00 AM - 11:30 AM||speaker 4|
|11:30 AM - 12:00 PM||Panel w/ First Four Speakers|
|12:00 PM - 02:00 PM||Lunch Break|
|02:00 PM - 02:30 PM||speaker 5|
|02:30 PM - 03:00 PM||speaker 6|
|03:00 PM - 03:30 PM||speaker 7|
|03:30 PM - 04:00 PM||Poster Session and Coffee Break|
|04:00 PM - 03:30 PM||speaker 8|
|04:30 PM - 05:00 PM||speaker 9|
|05:00 PM - 05:30 PM||Debate w/ Last Five Speakers|
This workshop will focus on two emerging areas in computational HRI: adaptation and influencing.
Adaptation considers how robots and humans modify their behavior to adjust to one another. One common example of adaptation is learning: we want robots that learn the right behavior from human partners. But there is another side to adaptation---just as the robot learns from the human, humans can also modify their behavior when interacting with robot partners. Both sides of adaptation will be discussed in this workshop.
Influencing refers to how a robot can leverage its actions to proactively change the behavior of nearby humans. Influential behavior can arise when a single human and robot are interacting---for instance, a self-driving car slowing down to cause a human-driven car to follow suit---as well as when teams of humans and robots are working to complete a task. This workshop will discuss the relationship between computational human models and influential robot behavior.
This workshop will be of interest to researchers who study computational HRI, and want to discuss, learn about, and present recent advances in adaptation and influencial behavior.
Dylan Losey is a postdoctoral scholar in the Computer Science Department at Stanford University. His research interests lie at the intersection of human-robot interaction, control theory, and machine learning. He develops algorithms that enable robots to teach and learn from humans through physical interactions. Dylan received his Ph.D. in Mechanical Engineering from Rice University in 2018, and was previously a visiting scholar at the University of California, Berkeley. He is awarded the 2017 IEEE/ASME Transactions on Mechatronics Best Paper Award, and was an NSF Graduate Research Fellow.
Minae Kwon is a first year Ph.D. candidate in the Computer Science department at Stanford. She is broadly interested in enabling robots to intelligently interact with, influence, and adapt to humans. Specifically, she has worked on projects that include creating expressive robot motions, modeling and influencing multi-agent human teams, and enabling a robot to adapt to a human partner over repeated interactions. Minae is supported by the Stanford School of Engineering Fellowship.
Dorsa Sadigh is an assistant professor in Computer Science and Electrical Engineering at Stanford University. Her research interests lie in the intersection of robotics, learning and control theory, and algorithmic human-robot interaction. Specifically, she works on developing efficient algorithms for autonomous systems that safely and reliably interact with people. Dorsa has received her doctoral degree in Electrical Engineering and Computer Sciences (EECS) at UC Berkeley in 2017, and has received her bachelor's degree in EECS at UC Berkeley in 2012. She is awarded the Amazon Faculty Research Award, the NSF and NDSEG graduate research fellowships as well as the Leon O. Chua departmental award.