Agile Robotics: from Frame Cameras to Neuromorphic Sensors

Davide Scaramuzza

University of Zurich, CH

Abstract

Robots play a crucial role in inspection, agriculture, logistics, automated driving, and search-and-rescue missions. Yet, they lag behind humans in speed, versatility, and robustness. I will show how combining model-based and machine-learning methods with the power of new, low-latency sensors, such as event cameras, can allow autonomous systems such as drones, legged robots, robot arms, and cars to achieve unprecedented agility and robustness. This can result in better productivity and safety of future autonomous systems.