Quadcopters are among the most agile and dynamic machines ever created. In this talk, I’ll show how data-driven sensorimotor controllers can push quadcopters with only onboard sensing and computation to their physical limits. Such controllers enable quadcopters to fly faster and more agile than what was possible before in unstructured environments like cities, forests, and […]
Autonomous exploration and data-efficient learning are important ingredients for helping machine learning handle the complexity and variety of real-world interactions. In this talk, I will describe methods that provide these ingredients and serve as building blocks for enabling self-sufficient robot learning. First, I will outline a family of methods that facilitate active global exploration. Specifically, […]
Anomaly detection is a crucial task in the operation of complex systems such as industrial facilities, manufacturing plants, and large-scale science experiments. Failures in a sub-system can result in low yield, faulty products, or damage to components, making it essential to detect anomalies as quickly as possible. Despite the abundance of data available for complex […]
Millimeter-wave and terahertz bands are emerging as the most promising spectrum to meet the data-rate and latency demands of future wireless applications, including virtual reality and autonomous cars. Moreover, the large spectral availability together with the mm-scale wavelength, opens the opportunity of scaling the capacity of future wireless networks by supporting highly directional, high data […]
The aerosol lifecycle consists of processes that act on the micro-scale, yet the aerosols’ climate impacts are perceived on regional or global scales. Capturing this multiscale nature of the atmospheric aerosol poses considerable challenges for aerosol models since computational constraints limit the detail of aerosol representation, yet these details matter in determining large-scale aerosol impacts. […]
