MATTHEW J. JOHNSON
download pdfProfessional Interest
To unlock the potential of robotics and enhance the utility of robotic systems, particularly in close interaction with people. Specific areas of interest include:• Human-robot interaction
• Coordination
• Teamwork
• Control theory
• Interface design
• Artificial intelligence
• Machine learning
Education
Master of Science / Computer Science
• Texas A&M University at Corpus Christi - November 2001• GPA 4.0
• Graduate project was the design and development of a functioning autonomous delivery robot. The prototype employed a hybrid control architecture that combined reactive behaviors written in C and a cognitive layer written in Jess (Java Expert System Shell). It also included a graphical user-interface written in Java.
• Courses in Artificial intelligence, Neural Networks, Expert Systems, Algorithms, Simulation and Modeling
• Four semesters of C++ programming
Bachelor of Science / Aerospace Engineering
• University of Notre Dame – May 1992• GPA 3.0
• As Project Leader, coordinated all areas during design and development of a remotely piloted vehicle.
• Designed and implemented flight controls for remotely piloted vehicle.
EXPERIENCE
Research Associate for the Institute for Human and Machine Cognition (IHMC)
(July 2002 – present)I have spent the last six years working on a wide variety of research projects at a multidisciplinary research institute. A few selected projects are:
ARL CDIX
(October 2008 – present)This project seeks to help manage the limited bandwidth resources in a data rich environment. It is important to make use of knowledge about the overall system not just at the decision point, but also in the gathering point. Which pieces of data are given priority in the limited network capacity is equivalent to making the decision on what data you will consider and what you will ignore. Our demonstration will show how policy-guided data dissemination and reputation service can enhance mission effectiveness.
Learning Locomotion
(May 2006 – present)This project is a DARPA program with the goal of developing a new generation of learning algorithms to enable traversal of rough terrain by unmanned ground vehicles (UGV). This project was competitive and we performed very well against the other six teams. It required mainly software engineering and involved designing and implementing complex control systems for a quadruped robot. I contributed to all aspects of the system and was responsible to the planning component for the last two years.
Coordinated Operations
(May 2006 - August 2007)This project sought to advance our human-robot collaboration work. We developed a framework to allow teams comprised of humans and robot to operate together. Our demo included two humans (a Commander and a Lieutenant) and five robots (4 pioneer 3ATs and one IHMC-made tBot). The task was a hide-and-seek style task to find an intruder. The Commander dynamically formed two teams and then used the teams to search the NAS Pensacola pier. We used TRIPS natural language interface and KAoS policies to manage the teams and enforce appropriate teamwork behavior.
BUDSS - BrainPort Underwater Sensory Substitution Systems
(December 2005 - May 2006)This project leveraged the tongue display (BrainPort) developed by WICAB labs. This haptic display presents data to the tongue on a 10 x 10 array. We developed several images patterns that have been tested with Navy divers from Naval Surface Warfare Center in Panama City. We have also continued to advance our AMI architecture.
Augmented Cognition
(July 2002 - December 2005)This DARPA project was focused on examining various physiological measures of a human to detect cognitive state and adapt the user's application to improve performance. We developed several gauges based on a variety of physiological measures. We also developed an integration architecture (AMI) that provided a simple mechanism for incorporating new hardware into systems. This architecture was presented at HCI 2005 in Las Vegas and has been the backbone of several projects even today.
Naval Automation Information Management Technology for ONR
(May 2003 - April 2005)This project performed advanced research in the areas of unmanned underwater mobility, human-agent teamwork, agile computing, and mixed-initiative interaction. We developed a mixed-initiative system where a single user could control multiple robots through a multi-modal dialogue system to perform a lane finding task. We performed proactive network maintenance by moving robots to maintain network connectivity for the team. We also used a UAV to demonstrate opportunistic resource exploitation.
OZ flight display
(July 2002 - July 2003)OZ is an alternative method of presenting cockpit information which capitalizes on what the human eye was designed to see best, quickest, and easiest. OZ replaces cockpit gauges with a single computer screen that uses lines, circles and streaming "stars" to graphically show spatial orientation, aircraft location, flight performance, aircraft configuration, and engine status all in a single glance. I worked as a technical advisor for developing the fixed and rotary wing versions of OZ and developing the first documentation of OZ.
NASA Human-Robot Teamwork
(July 2002 - December 2003)This project explored the issues of human-robot teamwork in a NASA context. These were the first robots at IHMC. We used a speech dialogue system to control two robots in a simple task of taking a picture of an astronaut. Pieces of this scenario were used in actual field studies at the Utah desert research site.
SELECTED PUBLICATIONS
2008
Johnson, M., Bradshaw, J. M., Jung, H., Suri, N., & Carvalho, M. Policy Management across Multiple Platforms and Application Domains. In the Proceedings of the IEEE Workshop on Policies for Distributed Systems and Networks 2008 (POLICY 2008). Palisades, NY, June 2-4Johnson, M., Feltovich, P.J., Bradshaw, J.M., & Bunch, L. Human-Robot Coordination through Dynamic Regulation. In the Proceedings of the International Conference on Robotics and Automation (ICRA 2008). Pasadena, California, May 19-23
Johnson, M., Feltovich, P.J., & Bradshaw, J.M. R2 Where Are You? Designing Robots for Collaboration with Humans. In the Proceedings of the Workshop on Social Interaction with Intelligent Indoor Robots (SI3R 2008) Pasadena, California, May 20
Johnson, M., Intlekofer, K, Jung, H., Bradshaw, J. M., Allen, J., Suri, N., & Carvalho, M. Coordinated Operations in Mixed Teams of Humans and Robots, In the Proceedings of the International Conference on Distributed Human-Machine Systems 2008 (DHMS 2008). Athens, Greece, October 22-24
2007
Bradshaw, J. M., Feltovich, P. J., Johnson, M., Bunch, L. Breedy, M., Jung, H., Lott, J. & Uszok, A. Coordination in Human-Agent-Robot Teamwork, Proceedings of the AAAI AAAI Fall Symposium on Regarding the "Intelligence" in Distributed Intelligent Systems (Invited Paper), 2007Rebula, J., Neuhaus, P., Bonnlander, B., Johnson, M., Pratt, J. A controller for the LittleDog Quadruped Walking on Rough Terrain. In Proceedings of the IEEE International Conference on Robotics and Automation, 2007
Feltovich, P.J., Bradshaw, J. M., Clancey, W.J., Johnson, M., & Bunch, L. Progress Appraisal as a Challenging Element of Coordination in Human and Machine Joint Activity. In the Pre-Proceedings of the Engineering Societies in the Agent's World 07 (ESAW07). Athens, Greece, October 22-24
2006
Matthew Johnson, Jeffrey M. Bradshaw, Paul Feltovich, Renia Jeffers, Hyuckchul Jung, and Andrzej Uszok, A Semantically Rich Policy Based Approach to Robot Control, Proceedings of the International Conference on Informatics in Control, Automation and Robotics, 2006Feltovich, P. J., Bradshaw, J. M., Clancey, W. J., & Johnson, M. Toward an Ontology of Regulation: Socially-Based Support for Coordination in Human and Machine Joint Activity. In the Pre-Proceedings of the Engineering Societies in the Agent's World 06 (ESAW06). Athens, Greece, October 22-24
2005
Matthew Johnson, Shri Kulkarni, Anil Raj, Roger Carff, Jeffery M. Bradshaw, AMI: An adaptive multi-agent framework for Augmented Cognition. Proceedings of the 11th International Conference on Human-Computer Interaction, Las Vegas, NV, 22-27 July 2005.Jeffrey M. Bradshaw, Hyuckchul Jung, Shri Kulkarni, Matthew Johnson, Paul Feltovich, James Allen, Larry Bunch, Nathanael Chambers, Lucian Galescu, Renia Jeffers, Niranjan Suri, William Taysom, and Andrzej Uszok, Kaa: Policy-based Explorations of a Richer Model for Adjustable Autonomy, Proceedings of the International Joint Conference on Autonomous Agents and Multi Agent Systems, 2005