Entropy-Based Search Combined with a Dual Feedforward-Feedback Controller for Landmark Search and Detection for the Navigation of a UAV Using Visual Topological Maps
We introduce a novel method for landmark search and detection for the autonomous indoor navigation of an Unmanned Aerial Vehicle (UAV) using visual topological maps. The main contribution of this paper is the combination of the entropy of an image, with a dual feedforward-feedback controller for the task of object/landmark search and detection. As the entropy of an image is directly related to the presence of a unique object or the presence of different objects inside the image (the lower the entropy of an image, the higher its probability of containing a single object inside it; and conversely, the higher the entropy, the higher its probability of containing several different objects inside it), we propose to implement landmark and object search and detection as a process of entropy maximization which corresponds to an image containing several target landmarks candidates. After converging to an image with maximum entropy containing several candidates for the target landmark, the UAV´s controller switches to the landmark´s homing mode based on a dual feed-forward/feedback controller aimed at driving the UAV towards the target landmark. After the presentation of the theoretical foundations of the entropy-based search. The paper ends with the experimental work performed for its validation.
KeywordsUnmanned Aerial Vehicles Entropy search Vision-based dual anticipatory reactive controllers Nearest Neighbors Methods Topological Maps
Unable to display preview. Download preview PDF.
- 1.Maravall, D., de Lope, J., Fuentes Brea, J.P.: A Vision-Based Dual Anticipatory/Reactive Control Architecture for Indoor Navigation of an Unmanned Aerial Vehicle Using Visual Topological Maps. In: Ferrández Vicente, J.M., Álvarez Sánchez, J.R., de la Paz López, F., Toledo Moreo, F. J. (eds.) IWINAC 2013, Part II. LNCS, vol. 7931, pp. 66–72. Springer, Heidelberg (2013)CrossRefGoogle Scholar
- 2.Maravall, D., de Lope, J., Fuentes, J.P.: Fusion of probabilistic knowledge-based classification rules and learning automata for automatic recognition of digital images. Pattern Recognition Letters (2013)Google Scholar
- 3.Oudeyer, P.-Y., Kaplan, F.: What is intrinsic motivation? A typology of computational approaches. Frontiers in Neurorobotics 1, Article.6 (2007)Google Scholar
- 4.Kawato, M.: Feedback-Error-Learning Neural Network for Supervised Motor Learning. Advanced Neural Computers (1990)Google Scholar
- 6.Kawato, M.: Internal models for motor control and trajectory planning. Neurobiology 9, 718–727 (1999)Google Scholar
- 9.Barlow, J.S.: The Cerebellum and Adaptive Control. Cambridge University Press (2002)Google Scholar
- 10.Piskorski, S., Brulez, N., D’Haeyer, F.: A.R.Drone Developer Guide SDK 2.0, Parrot (2012)Google Scholar
- 11.Bristeau, P.-J., Callou, F., Vissiere, D., Petit, N.: The Navigation and Control Technology Inside the AR.Drone micro UAV. Preprints of the IFAC World Congress Milano (2011)Google Scholar
- 12.Jayatilleke, L., Zhang, N.: Landmark-based Localization for Unmanned Aerial Vehicles. IEEE (2013)Google Scholar