Learning a controller fusion network by online trajectory filtering for vision-based UAV racing
KAUST DepartmentComputer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
VCC Analytics Research Group
Visual Computing Center (VCC)
Permanent link to this recordhttp://hdl.handle.net/10754/660366
MetadataShow full item record
AbstractAutonomous UAV racing has recently emerged as an interesting research problem. The dream is to beat humans in this new fast-paced sport. A common approach is to learn an end-to-end policy that directly predicts controls from raw images by imitating an expert. However, such a policy is limited by the expert it imitates and scaling to other environments and vehicle dynamics is difficult. One approach to overcome the drawbacks of an end-to-end policy is to train a network only on the perception task and handle control with a PID or MPC controller. However, a single controller must be extensively tuned and cannot usually cover the whole state space. In this paper, we propose learning an optimized controller using a DNN that fuses multiple controllers. The network learns a robust controller with online trajectory filtering, which suppresses noisy trajectories and imperfections of individual controllers. The result is a network that is able to learn a good fusion of filtered trajectories from different controllers leading to significant improvements in overall performance. We compare our trained network to controllers it has learned from, end-to-end baselines and human pilots in a realistic simulation; our network beats all baselines in extensive experiments and approaches the performance of a professional human pilot.
CitationMuller, M., Li, G., Casser, V., Smith, N., Michels, D. L., & Ghanem, B. (2019). Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-Based UAV Racing. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). doi:10.1109/cvprw.2019.00083
SponsorsThis work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.
Conference/Event name32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
RelationsIs Supplemented By:
Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV Racing. URL: https://youtu.be/hGKlE5X9Z5U
Embedded External Content