News
Thursday, May 10: Source code and data are now available for our CHI'12 paper on Accurate Measurements of Pointing Performance from In Situ Observations.
Monday, May 7: Our paper on Human Computation Tasks with Global Constraints received an honorable mention at CHI 2012.
Thursday, March 1: "We argue that it is both the possibility and the efficiency of access that are necessary for meaningful and equitable participation of society." -- read about our take on the future of accessibility (and how it ties with AI, intelligent user interfaces, and mobile computing) in the March-April issue of ACM interactions.
About The Group
The Intelligent Interactive Systems Group at Harvard was founded in September of 2009. We are interested in how intelligent technologies can enable novel ways of interacting with computation, and in the new challenges that human abilities, limitations and preferences create for machine learning algorithms embedded in interactive systems.
About Intelligent Interactive Systems
Intelligent Interactive Systems are fundamentally hard to design because they require intelligent technology that is well suited for people's abilities, limitations, and preferences; they also require entirely novel interactions that can give the user a predictable and reliable experience despite the fact that the underlying technology is inherently proactive, unpredictable, and occasionally wrong. Thus, design of successful intelligent interactive systems requires intimate knowledge of and ability to innovate in two very disparate areas: human-computer interaction and artificial intelligence or machine learning.
What We Do
Our projects span the full range from formal user studies to statistical machine learning. We have worked on developing new intelligent technologies to enable novel interactions (e.g., SUPPLE system) and on understanding the principles underlying how people interact with intelligent systems (e.g., the project on exploring the design space of adaptive user interfaces). Our Brain-Computer Interface project aims at developing a new set of interactions for efficiently controlling complex applications, and we are also interested in building and studying complete applications. One particular area of inteterest is the ability-based user interfaces -- an approach for adapting interactions to the individual abilities of people with impairments or of able-bodied people in unusual situations.