Abstract:

As robots move out of the lab and factory and into more challenging environments, uncertainty in the robot’s state, dynamics, and contact conditions becomes a fact of life. We will never be able to perfectly predict the forces on the robot’s feet as it walks through unknown mud or control the deflections of a branch as it pushes past. Uncertainty in contact conditions are particularly challenging because of the discontinuous nature of contact — we can exert large forces on an object when we are touching it, but zero force on it when we are just a millimeter away. In this talk, I’ll present some recent work in handling uncertainty in dynamics and contact conditions, in order to both reduce that uncertainty where we can but also generate strategies that do not require perfect knowledge of the world state. Specifically, I will present results on learning off-road driving in novel environments, walking control for legged robots through vegetation, and manipulation strategies with high speed impacts.

Bio:

Aaron M. Johnson is an Associate Professor of Mechanical Engineering at Carnegie Mellon University, with additional appointments in the Robotics Institute and Electrical & Computer Engineering departments. He received his PhD from the University of Pennsylvania in 2014. His research interests are in hybrid systems, state estimation, control, legged robots, and field robotics. He is the recipient of the NSF Career award, the ARO Young Investigator Award, and the Best Paper award at the ICRA Workshop on Legged Robots, among other awards.