FLYBO: A Unified Benchmark Environment for Autonomous Flying Robots

Abstract

Figure 1: An MAV equipped with odometry-and active depth sensors autonomously explores a complex synthetic area from FLYBO (a) while gradually mapping the scene throughout different exploration stages and planning trajectories online (b-d).Simultaneously, the perceived surfaces are also reconstructed online (close-up views). FLYBO provides datasets, references and a framework to benchmark such systems w.r.t their volumetric exploration and online surface reconstruction capabilities.

LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF

“…In order to ensure the simulation data is as close to real as possible, on the one hand, we use a realistic city scene model which comes form Kirill Sibiriakov [18], on the other hand, we collect the vehicle motion data and camera data separately to enable the frequency and quality, which is derived from the method in the paper [23]. In comparison to urban datasets [2] [8] which are creating by using the oblique aerial photography technique, our dataset has higher fidelity when it comes to the texture details.…”