Our research has four themes. The first theme focuses on ways to help people design graphics to visualize and thus better understand information. We have been studying this problem in the context of SAGE (System for Automated Graphics and Explanation). SAGE enhances user-directed design by providing tools that: create the novel displays that users specify, complete partial specifications, retrieve previously created graphics based on their appearance and/or their data content, and design graphics completely autonomously when users request them.
The second theme running through all our work is developing environments for data exploration. We aim to develop visual environments where users directly perceive and act upon information. We have developed a drag-and-drop information-centric paradigm, in which applications as discrete entities no longer appear. This paradigm is implemented in Visage (Very Integrated SAGE).
The third theme has to do with interactive techniques, which all of our systems support in various ways. We are focusing on them most in the SDM (which stands for Selective Dynamic Manipulation) paradigm, which is implemented in a system of the same name. The SDM paradigm is based on physicalization, which has to do with creating "physical" graphical objects to represent abstract information objects. This paradigm gives users the ability to move and stretch the graphical objects, analogous to the manner in which users might manipulate physical models placed on a table.
The fourth theme is automatic presentation. An automatic presentation system is an intelligent interface component which receives information from a user or application program and designs a combination of graphics and text that effectively conveys this information. SAGE has been one arena for us to test ideas in. We have automated caption generation to explain SAGE's automatically generated graphics. We are currently working on the automatic generation of full briefings in AutoBrief.
The fifth theme is visual query environments (VQE). VQE is a Visual Query Environment for expressing queries involving navigation among multiple objects, aggregating these objects, and defining derived attributes for them.
|The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.|
Contact Us | Update Instructions