Reciprocal collision avoidance for quadrotors using on-board visual detection

Abstract

Abstract-In this paper we present a collision avoidance system based on visual detection. Our hardware consists of a Hummingbird quadrotor equipped with a large red marker with two built-in fish-eye cameras. Fusion of the measurements from the two cameras is done using a Gaussian-mixture probability hypothesis density filter, which allows for tracking several aircrafts at the same time. Our collision avoidance algorithm is based on navigation functions designed to cope with cameras characterized by limited field of view. Its mathematical correctness has been proven in a former paper [1]. The collision avoidance maneuver is performed without the vehicles explicitly exchanging information via communication but instead relying solely on on-board sensors. Our system has been validated in an indoor space with four different collision scenarios. Trajectory data was recorded with an external motion capture system and demonstrate good robustness against sensing noise.

On-board communication-based relative localization for collision avoidance in Micro Air Vehicle teams

“…Current implementations generally adopt mounted visual aids in the form of: colored balls (Roelofsen et al 2015), tags (Conroy et al 2014), or markers (Nägeli et al 2014). However, experiments during exploratory phases of this study have shown that the use of vision without such aids, for very small drones, and at low resolution [128 px × 96 px, as seen on a Lisa-S Ladybird (McGuire et al 2016)], is prone to either false positives or false negatives.…”

3D collision avoidance algorithm for Unmanned Aerial Vehicles with limited field of view constraints

“…In other words, none of these works explicitly addresses the FOV problem. Our previous work [12] is, to our knowledge, the first collision algorithm that takes into account the FOV limitations and has been experimentally validated [13].…”

Vision-based Unmanned Aerial Vehicle detection and tracking for sense and avoid systems

“…5. The implementation of the camera sensor model is similar to [19], which uses the standard camera with distortion model, with the exception of the measurement model for the apparent width w…”

“…For this reason, the state estimation in this framework is performed with a Gaussian-Mixture Probability Hypothesis Density filter (GM-PHD) described in [18]. The GM-PHD filter is a multitarget tracker that has been successfully applied to markerbased single-camera multi-target tracking in previous work [19]. In this paper, we apply the same methodology to the more general problem of marker-less multi-target tracking.…”