Evolutionary Approaches for Flying Robots
Episode #207: Evolutionary Approaches for Flying Robots
Interviewee: Guido De Croon
In this episode on the Robots Podcast, I interview Guido De Croon about Evolutionary Robotics and its use to design behaviors for flying robots. We discuss a recent paper by Kirk Schepe et al., in which the DelFly UAV robot learns to fly through an open window when trapped inside a room thanks to a controller optimized using a Genetic Algorithm. The controller is programmed using a Behavior Tree Framework, which is more intuitive and adaptable than the traditional Neural Network framework. This helps the user to manually adapt the controller to handle the differences between the simulation and the real world. Guido then discusses the challenges and benefits of using Evolutionary Robotics to learn robot behaviors.