elsarticle-template.pdf (17.95 MB)
Automatic obstacle avoidance of quadrotor UAV via CNN-based learning
journal contribution
posted on 2023-06-09, 21:07 authored by Xi Dai, Yuxin Mao, Tianpeng Huang, Na Qin, Deqing Huang, Yanan LiYanan LiIn this paper, a CNN-based learning scheme is proposed to enable a quadrotor unmanned aerial vehicle (UAV) to avoid obstacles automatically in unknown and unstructured environments. In order to reduce the decision delay and to improve the robustness for the UAV, a two-stage end-to-end obstacle avoidance architecture is designed, where a forward-facing monocular camera is used only. In the first stage, a convolutional neural network (CNN)-based model is adopted as the prediction mechanism. Utilizing three effective operations, namely depthwise convolution, group convolution and channel split, the model predicts the steering angle and the collision probability simultaneously. In the second stage, the control mechanism maps the steering angle to an instruction that changes the yaw angle of the UAV. Consequently, when the UAV encounters an obstacle, it can avoid collision by steering automatically. Meanwhile, the collision probability is mapped as a forward speed to maintain the flight or stop going forward. The presented automatic obstacle avoidance scheme of quadrotor UAV is verified by several indoor/outdoor tests, where the feasibility and efficacy have been demonstrated clearly. The novelties of the method lie in its low sensor requirement, light-weight network structure, strong learning ability and environmental adaptability.
History
Publication status
- Published
File Version
- Accepted version
Journal
NeurocomputingISSN
0925-2312Publisher
ElsevierExternal DOI
Department affiliated with
- Engineering and Design Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2020-04-21First Open Access (FOA) Date
2021-04-21First Compliant Deposit (FCD) Date
2020-04-21Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC