GateNet: An Efficient Deep Neural Network Architecture for Gate Perception Using Fish-Eye Camera in Autonomous Drone Racing

TY - CONF

T1 - GateNet: An Efficient Deep Neural Network Architecture for Gate Perception Using Fish-Eye Camera in Autonomous Drone Racing

AU - Pham, Xuan Huy

AU - Bozcan, Ilker

AU - Sarabakha, Andriy

AU - Haddadin, Sami

AU - Kayacan, Erdal

PY - 2021

Y1 - 2021

N2 - Fast and robust gate perception is of great importance in autonomous drone racing. We propose a convolutional neural network-based gate detector (GateNet1) that concurrently detects gate's center, distance, and orientation with respect to the drone using only images from a single fish-eye RGB camera. GateNet achieves a high inference rate (up to 60 Hz) on an onboard processor (Jetson TX2). Moreover, GateNet is robust to gate pose changes and background disturbances. The proposed perception pipeline leverages a fish-eye lens with a wide field-of-view and thus can detect multiple gates in close range, allowing a longer planning horizon even in tight environments. For benchmarking, we propose a comprehensive dataset (AU-DR) that focuses on gate perception. Throughout the experiments, GateNet shows its superiority when compared to similar methods while being efficient for onboard computers in autonomous drone racing. The effectiveness of the proposed framework is tested on a fully-autonomous drone that flies on previously-unknown track with tight turns and varying gate positions and orientations in each lap.

AB - Fast and robust gate perception is of great importance in autonomous drone racing. We propose a convolutional neural network-based gate detector (GateNet1) that concurrently detects gate's center, distance, and orientation with respect to the drone using only images from a single fish-eye RGB camera. GateNet achieves a high inference rate (up to 60 Hz) on an onboard processor (Jetson TX2). Moreover, GateNet is robust to gate pose changes and background disturbances. The proposed perception pipeline leverages a fish-eye lens with a wide field-of-view and thus can detect multiple gates in close range, allowing a longer planning horizon even in tight environments. For benchmarking, we propose a comprehensive dataset (AU-DR) that focuses on gate perception. Throughout the experiments, GateNet shows its superiority when compared to similar methods while being efficient for onboard computers in autonomous drone racing. The effectiveness of the proposed framework is tested on a fully-autonomous drone that flies on previously-unknown track with tight turns and varying gate positions and orientations in each lap.

UR - http://www.scopus.com/inward/record.url?scp=85124354114&partnerID=8YFLogxK

M3 - Paper

SP - 4176

EP - 4183

T2 - 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems

Y2 - 27 September 2021 through 1 October 2021

ER -