Víctor Rodríguez-Fernández

Design and development of a lightweight multi-UAV simulator

UAVs have become enormously popular over the last few years. These new systems could make a remarkable improvement in public safety and have many applications in a variety of fields such as agriculture or postage of packages. In order to test UAV capacities and train UAV mission operators, several simulators are used, and the use of them usually entails high costs. This work presents a low-cost and easily distributable simulator, focused on simulating missions carried out by multiple UAVs and extracting data from them. To evaluate its effectiveness, it has been subjected to stress testing with thousands of virtual users, proving to have a potentially competitive response.

A multi-UAV Mission Planning videogame-based framework for player analysis

The problem of Mission Planning for a large number of Unmanned Air Vehicles (UAVs) comprises a set of locations to visit in different time windows, and the actions that the vehicle can perform based on its features, such as sensors, speed or fuel consumption. Although this problem is increasingly more supported by Artificial Intelligence systems, nowadays human factors are still critical to guarantee the success of the designed plan. Studying and analyzing how humans solve this problem is sometimes difficult due to the complexity of the problem and the lack of data available. To overcome this problem, we have developed an analysis framework for Multi-UAV Cooperative Mission Planning Problem (MCMPP) based on a videogame that gamifies the problem and allows a player to design plans for multiple UAVs intuitively. On the other hand, we have also developed a mission planner algorithm based on Constraint Satisfaction Problems (CSPs) and solved with a Multi-Objective Branch & Bound (MOBB) method which optimizes the objective variables of the problem and gets the best solutions in the Pareto Optimal Frontier (POF). To prove the environment potential, we have performed a comparative study between the plans generated by a heterogenous group of human players and the solutions obtained by this planner.

Automatic profile generation for UAV operators using a simulation-based training environment

Unmanned aerial vehicles (UAVs) are becoming a hot topic in the last few years for several research areas, such as aeronautics or computer science. Big companies such as Airbus or Amazon aim to incorporate this technology to their current systems to improve the quality of their services while reducing the human costs. However, current UAV technology requires a strong human supervisory control and this supposes an important potential risk. Therefore, it is critical to keep track of the pilot behavior to be able to determine whether he is ready or not to operate with this technology. To deal with this problem, we have developed a methodology based on different performance metrics to automatically evaluate planning and monitoring skills of new users trained in a multi-UAV simulation environment. This methodology, based on unsupervised learning and fuzzy logic, can automatically generate a profile of future operators and use it to assess their skills.

Analysing temporal performance profiles of UAV operators using time series clustering

The continuing growth in the use of Unmanned Aerial Vehicles (UAVs) is causing an important social step forward in the performance of many sensitive tasks, reducing both human and economical risks. The work of UAV operators is a key aspect to guarantee the success of this kind of tasks, and thus UAV operations are studied in many research fields, ranging from human factors to data analysis and machine learning. The present work aims to describe the behaviour of operators over time using a profile-based model where the evolution of the operator performance during a mission is the main unit of measure. In order to compare how different operators act throughout a mission, we describe a methodology based of multivariate-time series clustering to define and analyse a set of representative temporal performance profiles. The proposed methodology is applied in a multi-UAV simulation environment with inexperienced operators, obtaining a fair description of the temporal behavioural patterns followed during the course of the simulation.

A method for building predictive HSMMs in interactive environments

The study of user behavior based on his/her interactions with a system is widely extended over several fields of research. Often, it is useful to have an underlying model to generate behavioral predictions, allowing the system to automatically adapt to the user and to detect deviations from an expected behavior. In this work, we develop a general method to create, select and validate a Hidden Semi-Markov Model (HSMM) to predict behavior in interactive environments, based on previously seen interactions. The method is completely data-driven, unrestricted by any prior knowledge of the model structure, and easy to automate once some parameters has been adjusted. To test the proposed method, a multi-UAV mission simulator has been used, obtaining a model able to perform adequate predictions in terms of quality and time.

Modeling the Behavior of Unskilled Users in a Multi-UAV Simulation Environment

The use of Unmanned Aerial Vehicles (UAVs) has been growing over the last few years. The accelerated evolution of these systems is generating a high demand of qualified operators, which requires to redesign the training process and focus on a wider range of candidates, including inexperienced users in the field, in order to detect skilled-potential operators. This paper uses data from the interactions of multiple unskilled users in a simple multi-UAV simulator to create a behavioral model through the use of Hidden Markov Models (HMMs). An optimal HMM is validated and analyzed to extract common behavioral patterns among these users, so that it is proven that the model represents correctly the novelty of the users and may be used to detect and predict behaviors in multi-UAV systems.

User profile analysis for UAV operators in a simulation environment

Unmanned Aerial Vehicles have been a growing field of study over the last few years. The use of unmanned systems require a strong human supervision of one or many human operators, responsible for monitoring the mission status and avoiding possible incidents that might alter the execution and success of the operation. The accelerated evolution of these systems is generating a high demand of qualified operators, which requires to redesign the training process to deal with it. This work aims to present an evaluation methodology for inexperienced users. A multi-UAV simulation environment is used to carry out an experiment focused on the extraction of performance profiles, which can be used to evaluate the behavior and learning process of the users. A set of performance metrics is designed to define the profile of a user, and those profiles are discriminated using clustering algorithms. The results are analyzed to extract behavioral patterns that distinguish the users in the experiment, allowing the identification and selection of potential expert operators.

A study on performance metrics and clustering methods for analyzing behavior in UAV operations

Unmanned Aerial Vehicles (UAVs) are starting to provide new possibilities to human societies and their demand is growing according to the new industrial application fields for these revolutionary tools. The current systems are still evolving, specially from an Artificial Intelligence perspective, which is increasing the different tasks that UAVs can perform. However, the current state still requires a strong human supervision. As a consequence, a good preparation for UAV operators is mandatory due to some of their applications might affect human safety. During the training process, it is important to measure the performance of these operators according to different factors that can help to decide what operators are more suitable for different kinds of missions creating operator profiles. Having this goal in mind, this work aims to present an extensive and robust methodology to automatically extract different performance profiles from the training process of operators in an UAV simulation environment. Our method combines the definition of a set of performance metrics with clustering techniques to define operators profiles, ensuring that the behavior discrimination is suitable and consistent.

Finding behavioral patterns of UAV operators using Multichannel Hidden Markov Models

In recent years Unmanned Aerial Vehicles (UAVs) have become a very popular topic in many different research fields and industrial applications. These technologies, and the related industries, are expected to grow dramatically by 2020. Although the systems designed to control UAVs are increasingly autonomous, the role of UAV operators is still a critical aspect that guarantee the mission success, specially when one single operator must supervise multiple UAVs. For this reason, much effort from different areas has been put into the study and analysis of the operator behavior. This work presents a new method to find and model behavioral patterns among UAV operators in a lightweight multi-UAV simulation environment. Our approach is based on MultiChannel (or Multivariate) Hidden Markov Models (MC-HMMs), which allow to gather in the same model parallel data sequences, such as the combination of operator interactions and mission events. The different steps for preprocessing data, creating, selecting and analyzing the model are described, and an experiment with inexperienced operators has been carried out to show how a descriptive model of behaviour can be generated using this modelling technique.

Analyzing Planning and Monitoring Skills of Users in a Multi-UAV Simulation Environment

© Springer International Publishing Switzerland 2015. The study of Unmanned Aerial Vehicles (UAVs) is currently a growing area. The accelerated expansion of these technologies is demanding the work of more and more qualified operators, able to supervise and control multiple UAVs at the same time. Unfortunately, the training process for this type of systems is still unstructured, and it is needed to define methods to assess and classify operators in the context of a specific skill, for both novice users and experts. This work is focused on analyzing the planning and monitoring skills of inexperienced users in a multi-UAV simulation environment, through the use of a set of metrics capturing the performance of a user and defining its profile. The user profiles will be clustered to extract shared behavioral patterns that help us to decide the planning and monitoring level for each group of users, and to select potential operators.