Dr. G. Michael Youngblood is a senior applied researcher at the Palo Alto Research Center (PARC, a Xerox company) in the Human-Machine Collaboration Area. He currently focuses on human-machine collaboration system research. These tools utilize mixed-initiative and often components of explainable AI. He recently worked on mobile computing platforms (embedded systems) and interactive artificial intelligence systems (AI with humans in the loop) to facilitate positive behavior change in individual and social contexts. His research work has also focused on learning and understanding spatiotemporal elements in real and virtual environments in order to guide decisions by AI assisting elements. This work has involved mobile robots, smart houses and buildings, interactive 3D gaming, and mobile computing. He is known for his "Can-Do" attitude, optimism in the face of imminent disaster, and ability to get the job done on time, on budget, and by design.

Specialties: Interactive Artificial Intelligence, Simulation and Games, User Assessment and Modeling, Knowledge and Information Data Structures and Processing, Machine and Human Learning, UX, Software Architecture, and Large-scale Systems

Dr. Youngblood is or has been a member in good standing of AAAI, ACM, ACM/SIGART, ACM/SIGGRAPH, IGDA, IEEE, and IEEE-CS. He is a Tau Beta Pi fellow, and also a member of the DARPA Computer Science Study Group (CSSG).

Statement of Research

At a high-level, I consider my research to be in the area of interactive artificial intelligence (AI).

My specific areas of research focus are

1. Intelligent Agents that work with humans in real-time, often collaboratively

2. Computer-aided Authoring and User Modeling for capturing knowledge in support for controlling task-oriented support AI

3. Spatial reasoning and support data structures for intelligent systems

In general, my research interests are in discovering complimentary artificial intelligence (AI) techniques that are more powerful in combination than by themselves (gestalt systems). For example, using stream mining and compression techniques to discover patterns on data to build a hierarchical Markov model and then learning on top of this model to make it a HPOMDP (my thesis work). I am interested in searching for improvements and advances in decision-making, recommendation, persuasion, and interactive intelligent systems that allow for coping with real-time and real-world environments, and investigating the development of human-consistent systems that become more intuitive for humans to work with and feel more natural to interact with in our increasingly technological society.

My preference is to work in applied AI, and my strength is in integrated intelligent systems—applying techniques in new and novel combinations, expanding their capability under new constraints posed by their application, and making a tangible improvement in the applied domain. I feel that my strength is in applying theoretical techniques to real-world/real-time problems.

My past work as a professor was in the exploration of agent learning, faster agent creation techniques, generation of knowledge from geometry, middleware support for AI, and the integration of academic AI techniques into current electronic entertainment games.

I then spent a number of years at PARC focused on intelligent systems in the health and behavior change area with a focus on mobile and ambient implementations.

Recently, still at PARC, I have been pursing scientific inquiry into human-machine collaboration and what makes for successful collaborations. This involves mixed-initiative, user modeling, and numerous techniques of interactive AI. The big goal is to create machine collaborators that humans feel create true collaborations and are not just tools.


While only reflective of about 60% of my publications, this chart from my Microsoft Academic page shows my continual impact on the field, even after leaving academia in 2012.

Select Publications


Larger External Research Grants ($14,178,397 total)

  • PARC ($12,387,355 total)

    • DARPA AIE COnstructive Machine-learning Battles with Adversary Tactics (COMBAT) - Conflict-resolving Hierarchical Adversarial planneR Guided by Extracted text (CHARGE)

      • PI: Roni Stern, Co-PI: Leora Morgenstern, Key Personnel: Michael Youngblood, Peter Patel-Schneider

      • $999,845

    • DARPA Explainable AI (XAI) Program - COmmon Ground Learning and Explanation (COGLE)

      • PI: Mark Stefik, Co-PIs: Michael Youngblood, Peter Pirolli (IHMC), Christian Lebiere (CMU), Ramamoorthy Subramanian (Edinburgh), Honglak Lee (UMich)

      • $7,331,193 + $800,000 PARC match = $8,131,193

    • NIH R-1 - Personalized Health Behavior System to Promote Well-Being in Older Adults

      • U. MIAMI PI: Sara Czaja, PARC PI : Peter Pirolli, PARC Co-I: Michael Youngblood

      • $2,025,247

    • NSF Smart and Connected Health - FITTLE+: Theory and Models for Smartphone Ecological Momentary Intervention

      • PI: Peter Pirolli, Co-PIs: Michael Youngblood, Bob Kraut (CMU)

      • $1,231,070

  • UNC Charlotte ($1,035,542 total)

    • NSF BRIDGES, Co-PI - $250,000

    • (Unnamed Corporation) Energy Behavior Change, Co-PI - $178,000

    • DARPA CSSG Phase 2, PI - $488,862

    • DARPA CSSG Phase 1, PI - $76,680

  • UT Arlington ($755,500 total)

    • DARPA Transfer Learning, Co-PI - $620,000

    • Bell Helicopter-Textron Autonomous Vehicles Lab Activity Support Grant, Co-PI - $60,000

    • NRL TIELT, Co-PI - $75,500

Other Items of Potential Interest

Attributions:Wizard icon by Icons8
Unless otherwise noted, all page and website content Copyright MCMLXX-MMXX by G. Michael Youngblood. All Rights Reserved.