Hi, I'm Mike Hamer
My research interests lie in the intersection of robotics, computation, and machine learning. Since 2011, I have been pursuing these interests through a Masters and then PhD at the Institute for Dynamic Systems and Control, ETH Zurich, where I have focused on the localization and coordination of robot swarms.
My research on the localization of robot swarms focuses on the application of ultra-wideband radio modules to the localization of robots in semi-structured environments. My publications in this field were some of the first, and my implementations of localization, control and state estimation algorithms have supported live quadrocopter shows, and have given a new degree of autonomy to the open-source Crazyflie micro-quadrocopter, to which my contributions include an improved flight controller, an extended Kalman filter, as well as numerous bug fixes and driver improvements.
My (very soon to be published) research on the coordination of robot swarms focuses on the generation of collision-free and dynamically feasible trajectories for swarms of hundreds to thousands of robots operating simultaneously and in close proximity. Watch this space.
In addition to my published research, I have experience applying deep (reinforcement) learning to real-world problems (using both PyTorch and Tensorflow). I enjoy programming (Python & C, and would love to use Rust/OCaml/Erlang for more than just hobby projects) and I get a kick from solving challenging problems efficiently.
I will be finishing my PhD soon and am looking for opportunities—Please get in touch!
Self-Calibrating Ultra-Wideband Network Supporting Multi-Robot Localization
IEEE Access 2018read more
The Flight Assembled Architecture Installation: Cooperative construction with flying machines
IEEE Control Systems 2014read more