Flow cytometry (FC) is an analytical technique which is used in biological research to identify cell types and in the clinical context to diagnose human diseases including hematological malignancies[1]. FC characterizes cell types by measuring the light scatter and fluorescence emission properties of fluorochrome-labeled antibodies from each of the thousands of cells a sample contains[2]. Based on the measured intensity of the fluorescence and the light scatter of these cell events, cells are distinguished from contaminants, and then each cell is classified into a specific cell population. Traditionally, this classification is done by manually identifying and partitioning (i.e. 'gating') these populations based on visual inspection of mostly two-dimensional intensity histograms of two respective fluorescence emission detectors (Figure 1). Figure 1 Schematic manual gating workflow which corrects for measurement variances across samples caused by the batch effect. The first obstacle during gating is the batch effect, i.e. technical variance of event measurements across samples, caused e.g. by the variability of the staining procedure or by the decay of the exciting laser and the fluorescence emissions of fluorophore-bound antibodies.

Robotics is the next frontier in the progress of Artificial Intelligence (AI), as the real world in which robots operate represents an enormous, complex, continuous state space with inherent real-time requirements. One extreme challenge in robotics is currently formed by autonomous drone racing. Human drone racers can fly through complex tracks at speeds of up to 190 km/h. Achieving similar speeds with autonomous drones signifies tackling fundamental problems in AI under extreme restrictions in terms of resources. In this article, we present the winning solution of the first AI Robotic Racing (AIRR) Circuit, a competition consisting of four races in which all participating teams used the same drone, to which they had limited access. The core of our approach is inspired by how human pilots combine noisy observations of the race gates with their mental model of the drone's dynamics to achieve fast control. Our approach has a large focus on gate detection with an efficient deep neural segmentation network and active vision. Further, we make contributions to robust state estimation and risk-based control. This allowed us to reach speeds of ~9.2m/s in the last race, unrivaled by previous autonomous drone race competitions. Although our solution was the fastest and most robust, it still lost against one of the best human pilots, Gab707. The presented approach indicates a promising direction to close the gap with human drone pilots, forming an important step in bringing AI to the real world.