Certain difficulties in path forecasting and filtering problems are based in the initial hypothesis of estimation and filtering techniques. Common hypotheses include that the system can be modeled as linear, Markovian, Gaussian, or all at one time. Although, in many cases, there are strategies to tackle problems with approaches that show very good results, the associated engineering process can become highly complex, requiring a great deal of time or even becoming unapproachable. To have tools to tackle complex problems without starting from a previous hypothesis but to continue to solve classic challenges and sharpen the implementation of estimation and filtering systems is of high scientific interest. This paper addresses the forecast–filter problem from deep learning paradigms with a neural network architecture inspired by natural language processing techniques and data structure. Unlike Kalman, this proposal performs the process of prediction and filtering in the same phase, while Kalman requires two phases. We propose three different study cases of incremental conceptual difficulty. The experimentation is divided into five parts: the standardization effect in raw data, proposal validation, filtering, loss of measurements (forecasting), and, finally, robustness. The results are compared with a Kalman filter, showing that the proposal is comparable in terms of the error within the linear case, with improved performance when facing non-linear systems.

New applications are continuously appearing with drones as protagonists, but all of them share an essential critical maneuver—landing. New application requirements have led the study of novel landing strategies, in which vision systems have played and continue to play a key role. Generally, the new applications use the control and navigation systems embedded in the aircraft. However, the internal dynamics of these systems, initially focused on other tasks such as the smoothing trajectories between different waypoints, can trigger undesired behaviors. In this paper, we propose a landing system based on monocular vision and navigation information to estimate the helipad global position. In addition, the global estimation system includes a position error correction module by cylinder space transformation and a filtering system with a sliding window. To conclude, the landing system is evaluated with three quality metrics, showing how the proposed correction system together with stationary filtering improves the raw landing system.

No abstract