Onboard Detection and Localization of Drones Using Depth Maps

Abstract

Obstacle avoidance is a key feature for safe drone navigation. While solutions are already commercially available for static obstacle avoidance, systems enabling avoidance of dynamic objects, such as drones, are much harder to develop due to the efficient perception, planning and control capabilities required, particularly in small drones with constrained takeoff weights. For reasonable performance, obstacle detection systems should be capable of running in real-time, with sufficient field-of-view (FOV) and detection range, and ideally providing relative position estimates of potential obstacles. In this work, we achieve all of these requirements by proposing a novel strategy to perform onboard drone detection and localization using depth maps. We integrate it on a small quadrotor, thoroughly evaluate its performance through several flight experiments, and demonstrate its capability to simultaneously detect and localize drones of different sizes and shapes. In particular, our stereo-based approach runs onboard a small drone at 16 Hz, detecting drones at a maximum distance of 8 meters, with a maximum error of 10% of the distance and at relative speeds up to 2.3 m/s. The approach is directly applicable to other 3D sensing technologies with higher range and accuracy, such as 3D LIDAR.

On-Line Optimal Ranging Sensor Deployment for Robotic Exploration

“…As a final simulation test, we verified that the SLAM-like assumption of the anchor estimated positions âi cannot be considered as a random variable, as discussed in Section IV-B. To empirically prove this fact, we have carried out 10 6 Monte Carlo trials where δ i uncertainty is treated as a random variable contributing to the random, zero-mean white noise in (10) and hence applying the multilateration (5), which results in the position uncertainty in Figure 9, dashed line. As can be noticed, this assumption end up with a non-negligible bias on the estimates of the estimated position ŝk (the Figure 9 reports the bias on the xk axis, but it acts similarly on ŷk ).…”

Improving real-time drone detection for counter-drone systems

“…Carrio et al (24) used AirSim to train a CNN detection network with 16 layers by automatically labelling depth maps. Depth maps were obtained by stereo-matching of the Red-Green-Blue (RGB) image pairs of the virtual ZED stereo camera on the AirSim drone.…”

Drónok és hagyományos légi járművek közös légtérben történő alkalmazásának repülésbiztonsági kockázatai

“…A probléma az, hogy nem egyformán tudunk kis méretű mozgó tárgyakat és nagyobb méretűeket érzékelni. A különböző gyártók már használnak a fedélzeten statikus (álló) akadályok elkerülését szolgáló rendszereket, de dinamikus (mozgó) akadályok elkerülése ennél jóval bonyolultabb kihívást jelent technológiailag [15].…”