Abstract
AbstractThis paper presents an EKF-based self-attitude estimation with a DNN (deep neural network) learning landscape information. The method integrates gyroscopic angular velocity and DNN inference in the EKF. The DNN predicts a gravity vector in a camera frame. The input of the network is a camera image, the outputs are a mean vector and a covariance matrix of the gravity. It is trained and validated with a dataset of images and corresponded gravity vectors. The dataset is collected in a flight simulator because we can easily obtain various gravity vectors, although the method is not only for UAVs. Using a simulator breaks the limitation of amount of collecting data with ground truth. The validation shows the network can predict the gravity vector from only a single shot image. It also shows that the covariance matrix expresses the uncertainty of the inference. The covariance matrix is used for integrating the inference in the EKF. Flight data of a drone is also recorded in the simulator, and the EKF-based method is tested with it. It shows the method suppresses accumulative error by integrating the network outputs.
Funder
New Energy and Industrial Technology Development Organization
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Control and Optimization,Mechanical Engineering,Instrumentation,Modelling and Simulation
Reference20 articles.
1. Vaganay J, Aldon MJ, Fournier A (1993) Mobile robot attitude estimation by fusion of inertial data. In: Proceedings of 1993 IEEE International Conference on Robotics and Automation (ICRA), pp. 277–282
2. Thrun S, Burgard W, Fox D (2005) In: Probabilistic Robotics, pp. 309–336. The MIT Press
3. Rusinkiewicz S, Levoy M (2001) Efficient variants of the icp algorithm. In: Proceedings of Third International Conference on 3-D Digital Imaging and Modeling, pp. 145–152
4. Biber P, er, WS (2003) The normal distributions transform: a new approach to laser scan matching. In: Proceedings of 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
5. Engel J, Stueckler J, Cremers D (2014) Lsd-slam: Large-scale direct monocular slam. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 834–849
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献