Investigating Autonomous Agents

Electrical engineer Professor Frank Lewis and Associate Professors Yan Wan and Ali Davoudi were awarded a three-year, $750,000 Army Research Office grant to investigate how to improve control of networked groups of autonomous and human agents through new distributed reinforcement learning constructs.

The researchers will use fundamental science and mathematics theories to investigate interactions of humans, communication topologies, autonomous and adversarial agents, and uncertain environments. They will then develop adaptive and optimal solutions for mixed convoys with both humans and driverless/ autonomous vehicles.

“The desired result is to get the entire group to perform as a single entity that improves the behavior of each individual agent,” Dr. Lewis says. “This will also help individual agents and the group to reject the negative effects of adversaries because each agent can adjust and learn from its neighbors if there is suspicious behavior.”