Research Scientist

Ian Perera is a Research Scientist at IHMC working on human-machine and human-human dialogue analysis and systems, situated language understanding, and natural language understanding for Social Cybersecurity. He received his B.S.E. in Digital Media Design at the University of Pennsylvania, and obtained his PhD in Computer Science at the University of Rochester in 2016 with Dr. James F. Allen as his advisor. For his PhD thesis, he worked with Dr. Allen to develop the SALL-E system, which uses child language learning strategies and pragmatic reasoning to learn object names and properties in real-time from ambiguous natural language descriptions with only a limited number of examples.

Since joining IHMC in 2013, he has served as key personnel on numerous DARPA, IARPA, AFRL, and ARL projects, and is currently a PI for the DARPA Civil Sanctuary program, which seeks to use novel language understanding and cognitive science methods for deescalating heated social media conversations. Continuing his work on human-machine teams and interfaces, he is also currently co-PI on an Air Force SBIR for improving and assessing trust of AI agents through co-training. He also recently served as co-Investigator for a NASA STTR focused on understanding where crew and operators are in a technical procedure through natural language analysis of their discussions.

Most recently his work has centered around language and speech analysis for understanding physiological and neuro-cognitive state. He co-developed the ViSTA teaming task, a novel multimodal assessment tool that uses situated dialogue analysis to measure cognitive and communicative performance in stressful, multi-tasking situations. ViSTA came out of his work on the DARPA MBA program and was deployed and validated in a VirTra simulator on-base. His laptop-based version of ViSTA is currently being studied for more widespread application and investigation into its potential for assessing cognitive health.

His prior work includes building dialogue systems with belief modeling and pragmatic reasoning for robots in a human-robot collaborative task and performing semantic extraction from text in a variety of domains, such as human-robot communication, human dialogues, and news articles.