MnRI Colloquium Speaker - James Humann

Title: Path Planning for Ground-Air Robot Teams with Energy Sharing

Abstract: The Army is researching path-planning for teams of ground robots and drones in the context of long-endurance autonomous surveillance missions. Unmanned ground and air vehicles have complementary strengths, namely long battery life in the ground vehicles and maneuverability in the air vehicles. Recent subsystem innovations allow the air vehicles to track their own energy levels and autonomously dock and recharge on the ground vehicles. This allows the team to operate for 8+ hours autonomously, but adds complexity to team path planning, which we solve using multiple approaches from greedy solvers to reinforcement learning. In this talk, we will share the problem formulation, simulation, algorithms, and results of recent outdoor experimentation.

 Bio: James Humann is a Mechanical Engineer with the US Army Research Laboratory (ARL). His research is focused on design, simulation, and control of multirobot systems. He received a BS in Mechanical Engineering from the University of Oklahoma, and an MS and PhD from the University of Southern California, with an emphasis in mechanical design and systems engineering. He recently relocated to Minneapolis to collaborate with researchers at the University of Minnesota. His most recent work includes path planning for energy-sharing teams of ground and air robots in a persistent surveillance mission. He oversees academic collaborators’ development of path planning algorithms, and brings their work in-house at ARL by developing simulations and an API for their solvers as a bridge to ARL robotics stack.