Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation
Name:
Teaching_UAVs_to_Race__ECCVW_18_.pdf
Size:
5.269Mb
Format:
PDF
Description:
Accepted Manuscript
Type
Conference PaperKAUST Department
Visual Computing Center (VCC)Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
Date
2019-01-29Preprint Posting Date
2017-08-19Online Publication Date
2019-01-29Print Publication Date
2019Permanent link to this record
http://hdl.handle.net/10754/626557
Metadata
Show full item recordAbstract
Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years. However, teaching UAVs to fly in challenging environments remains an unsolved problem, mainly due to the lack of training data. In this paper, we train a deep neural network to predict UAV controls from raw image data for the task of autonomous UAV racing in a photo-realistic simulation. Training is done through imitation learning with data augmentation to allow for the correction of navigation mistakes. Extensive experiments demonstrate that our trained network (when sufficient data augmentation is used) outperforms state-of-the-art methods and flies more consistently than many human pilots. Additionally, we show that our optimized network architecture can run in real-time on embedded hardware, allowing for efficient on-board processing critical for real-world deployment. From a broader perspective, our results underline the importance of extensive data augmentation techniques to improve robustness in end-to-end learning setups.Citation
Müller M, Casser V, Smith N, Michels DL, Ghanem B (2019) Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation. Physics of Solid Surfaces: 11–29. Available: http://dx.doi.org/10.1007/978-3-030-11012-3_2.Sponsors
This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the Visual Computing Center (VCC) funding.Publisher
Springer NatureJournal
Physics of Solid SurfacesConference/Event name
15th European Conference on Computer Vision, ECCV 2018arXiv
1708.05884Additional Links
https://link.springer.com/chapter/10.1007%2F978-3-030-11012-3_2ae974a485f413a2113503eed53cd6c53
10.1007/978-3-030-11012-3_2