Drexel University College of Computing & Informatics (CCI) Assistant Professor Christopher J. MacLellan recently received two research grants from the Army Research Laboratory (ARL) as part of the Army Strengthening Teamwork for Robust Operations in Novel Groups (STRONG) program.
MacLellan and Drexel will serve as PI for the project “Human-Guided ML for Futuristic Human-Machine Teaming” ($1.5 million from Feb. 2022 to Jan. 2025), in collaboration with Carnegie Mellon University and the University of Wisconsin-Madison.
This three-year project is aimed at creating interactive machine learning techniques that enable more effective teaming between humans and machines. To achieve this goal, MacLellan and fellow researchers within his Teachable AI Lab (TAIL) will develop a set of asymmetric cooperative multiplayer games that can serve as a testbed for humans and artificial intelligence (AI) agents to partner up to solve problems. On this effort, TAIL is developing AI agents for these games, and will also be developing teachable AI agents that can learn from natural interactions with their partners while participating in cooperative problem solving.
His second funded project, titled “The Co-evolution of Human-AI Adaptation,” will be conducted in collaboration with University of California San Diego (PI) and the University of Colorado Boulder. On this three-year project, CCI’s TAIL team will develop AI agents that leverage a technique called interactive task learning, which lets humans teach an agent to perform novel tasks through natural language dialog. To evaluate this system, human participants will team up with TAIL’s AI agents to accomplish tasks in a virtual reality game environment. To accomplish virtual reality tasks, the human participants will leverage the AI agents as personal assistants — teaching them to do new tasks as needed.
The U.S. Army Combat Capabilities Development Command, known as DEVCOM, Army Research Laboratory is the Army’s research laboratory strategically placed under the Army Futures Command. ARL is the Army’s sole fundamental research laboratory focused on cutting-edge scientific discovery, technological innovation, and transition of knowledge products that offer incredible potential to improve the Army’s chances of surviving and winning any future conflicts.
MacLellan’s research areas include human-computer interaction, AI, machine learning (ML), and data science. His work explores the development of computational models of how people learn and solve problems; how these models can support the development of effective learning technologies — at scale; and how data collected from these educational technologies can in turn be leveraged to drive development of better cognitive models and learning theories.
Previous to joining Drexel’s faculty, MacLellan was lead scientist at Soar Technology, Inc. where he developed novel AI/ML technologies to support end users in making better decisions and learning more effectively. He holds a PhD and MS in Human-Computer Interaction from Carnegie Mellon University, and a BS in Computer Science and Mathematics from the University of Wyoming. Learn more about his work at chrismaclellan.com