New Artificial Intelligence approaches for future UAV Ground Control Stations

The increasing interest in the use of Unmanned Aerial Vehicles (UAV) in the last years has opened up a new complex area of research applications. Many works have been focused on the applicability of new Artificial Intelligence techniques to facilitate the successfully execution of UAV operations from the Ground Control Stations (GCSs). Some of the most demanded applications in this field are the reduction of the workload of operators and the automation of training processes. This paper presents new algorithms focused on this field: a Multi-Objective Genetic Algorithm for solving Mission Planning and Replanning problems and a Procedure Following Evaluation methodology based on Petri Nets. This paper is based on a framework that simulates a GCS with support for multiple UAVs. The functionality of this framework has been extended in two different directions: on the one hand, to deal with Mission Designing, Automated Mission Planning and Replanning, and Alert Generation; and, on the other hand, to perform different analysis tasks of the UAV operators. Using this framework, a test mission has been executed and debriefed, focusing on the main AI-based issues described in this work.

[1]  Antonio González-Pardo,et al.  Finding behavioral patterns of UAV operators using Multichannel Hidden Markov Models , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[2]  Cristina Cuerno Rejado,et al.  RPAS integration in non segregated airspace: the SESAR approach , 2014 .

[3]  Aníbal Ollero,et al.  Tanker UAV for Autonomous Aerial Refueling , 2015, ROBOT.

[4]  Emilio Frazzoli,et al.  Linear temporal logic vehicle routing with applications to multi‐UAV mission planning , 2011 .

[5]  P. Pronovost,et al.  The checklist--a tool for error management and performance improvement. , 2006, Journal of critical care.

[6]  J. Wu,et al.  High-Resolution Planimetric Mapping from UAV Video for Quick-Response to Natural Disaster , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[7]  Francesca Guerriero,et al.  A multi-objective approach for unmanned aerial vehicle routing problem with soft time windows constraints , 2014 .

[8]  María Dolores Rodríguez-Moreno,et al.  Performance Evaluation of Multi-UAV Cooperative Mission Planning Models , 2015, ICCCI.

[9]  Arnaud Giacometti,et al.  20 years of pattern mining: a bibliometric survey , 2014, SKDD.

[10]  María Dolores Rodríguez-Moreno,et al.  MOGAMR: A Multi-Objective Genetic Algorithm for real-time Mission Replanning , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[11]  José Antonio López Orozco,et al.  A Real World Multi-UAV Evolutionary Planner for Minimum Time Target Detection , 2016, GECCO.

[12]  Key Dismukes,et al.  The Challenge of Aviation Emergency and Abnormal Situations , 2005 .

[13]  Carmen Peláez-Moreno,et al.  Deep Maxout Networks Applied to Noise-Robust Speech Recognition , 2014, IberSPEECH.

[14]  Narciso García Santos,et al.  Hand gesture recognition using infrared imagery provided by leap motion controller , 2016, ACIVS 2016.

[15]  A. Ollero,et al.  Immersive displays for building spatial knowledge in multi-UAV operations , 2015, 2015 International Conference on Unmanned Aircraft Systems (ICUAS).

[16]  Wil M.P. van der Aalst,et al.  Three good reasons for using a Petri-net-based workflow management system , 1996 .

[17]  Tao Li,et al.  A Unified View on Clustering Binary Data , 2006, Machine Learning.

[18]  María Dolores Rodríguez-Moreno,et al.  Solving complex multi-UAV mission planning problems using multi-objective genetic algorithms , 2017, Soft Comput..

[19]  Mingyue Ding,et al.  Real-Time Route Planning for Unmanned Air Vehicle with an Evolutionary Algorithm , 2003, Int. J. Pattern Recognit. Artif. Intell..

[20]  Víctor Rodríguez-Fernández,et al.  A study on performance metrics and clustering methods for analyzing behavior in UAV operations , 2017, J. Intell. Fuzzy Syst..

[21]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[22]  Scotty D. Craig,et al.  Training Issues for Remotely Piloted Aircraft Systems from a Human Systems Integration Perspective , 2016 .

[23]  Ricardo Bencatel,et al.  Unmanned Air Vehicles for coastal and environmental research , 2009 .

[24]  Roman Barták,et al.  Constraint Programming: In Pursuit of the Holy Grail , 1999 .

[25]  Roldán Gómez,et al.  Multi-UAV Coordination and Control Interface , 2016 .

[26]  Maria E. Orlowska,et al.  Analyzing Process Models Using Graph Reduction Techniques , 2000, Inf. Syst..

[27]  Carlos Cuevas,et al.  Robust image registration with global intensity transformation , 2015, 2015 International Symposium on Consumer Electronics (ISCE).

[28]  Antonio Artés-Rodríguez,et al.  Individual performance calibration using physiological stress signals , 2015, ArXiv.

[29]  David Camacho,et al.  Analysing temporal performance profiles of UAV operators using time series clustering , 2016, Expert Syst. Appl..

[30]  Aníbal Ollero,et al.  A cooperative perception system for multiple UAVs: Application to automatic detection of forest fires , 2006, J. Field Robotics.

[31]  Nicholas Roy,et al.  Comparing Learning Techniques for Hidden Markov Models of Human Supervisory Control Behavior , 2009 .