Alejandro G. Tuero

An Architecture for a Learning Analytics System Applied to Efficient Driving

Transport companies are probably one of the greatest sources of pollution nowadays. Perhaps because these companies would like to improve this situation, or perhaps because they simply would like to reduce the petrol they consume, they are more than ever deploying plans in order to increase the efficiency of their fleets. One of the easiest and cheapest ways to achieve this is to teach their drivers how to be more efficient. Nevertheless, traditional learning approaches were only successful in the short term, according to the previous work. In order to achieve long-term results, new learning paradigms must be taken into account. Furthermore, if we combine these paradigms with a learning analytics system, optimal results may be reached for both the company and the drivers. In this paper, we present a learning analytics system applied to the efficient driving context. This learning analytics system is used as a fundamental piece in the deployment of the blended learning methodology for efficient professional driving designed by our research group. We describe the design and the integration of this system with a real product currently being used in many transport fleets. With a technical approach, we also describe the main problems found during the deployment of this system and the solutions designed to cope with these problems.

Adaptive learning for efficient driving in urban public transport

Concerns about global warming and energy costs have induced transport companies to take measures to reduce fuel consumption. Among the different options available, efficient driving is widely used, allowing a reduction in fuel consumption of around 10%. However, changing the drivers behavior is not exempt of problems. The success of efficient driving techniques in the long term is related to the motivation of the driver and, for that reason, an adaptive training system according to the drivers needs can prove much more successful than giving general instructions that do not solve their inefficiencies. Therefore, a properly description of the drivers behavior and the adaptation of the evaluation analysis to the context is a key factor for the learning process in efficient driving. In this paper we propose an adaptive learning system for efficient driving, which allows the evaluation of professional drivers of urban public transport in their work environment. With the proposed system, we can identify failure points relating to the context, making a focused evaluation. The first evaluation results show that the set of patterns designed to evaluate the application of efficient driving techniques can identify the incorrect actions of the drivers. Based on the results, it is possible to make personalized recommendations to improve driver performance.

Optimización de rutas para mejora de la eficiencia en la conducción

Este trabajo ha sido financiado por la Comision Europea (proyecto GlobalBLED SMEInst-10-2016- 2017), el Plan Nacional de Investigacion (proyecto MINECO-13-TIN2013-41749-R) y el Plan PCTI del Principado de Asturias (proyecto GRUPIN-14-065).

Desarrollo de un laboratorio abierto de enjambres de robots autónomos de limpieza

En el corto plazo, la industria del robot autonomo y de los drones sera un factor de desarrollo importante. Tanto la fabricacion de los propios dispositivos, como del desarrollo del software que los hace funcionar seran actividades empresariales de importancia en el sector TIC. No obstante, el futuro de los robots de trabajo autonomo es colaborar unos con otros y con el entorno que los rodea (adaptacion al contexto). Para ello, deben de ser capaces de interactuar con otros equipos mediante protocolos de comunicacion y sistemas de razonamiento. Por ello, en este trabajo se presenta una experiencia encaminada a la obtencion de un sistema de trabajo colaborativo para que un grupo/enjambre de robots autonomos de limpieza puedan trabajar de forma conjunta. La experiencia se basa en un laboratorio abierto que permite a los alumnos proponer y realizar sus propios desarrollos. En el trabajo se presentan tanto los aspectos metodologicos de la experiencia, como los avances que se han conseguido realizar hasta la fecha.

Incorporation of Head-Up Display Devices in Real-Vehicular Environments to Improve Efficiency in Driving

In the last years the number of devices that provide information about the car the driving process has increased considerably. This also implies an increased level of distraction and, thus, a decrease in safety. In this context, Head-Up Display devices (HUDs) may be considered adequate representation interfaces because they are transparent and they are located in the vision line of the driver. HUDs allow drivers to view what is behind the screen without looking away from the road. However, we must analyse the impact of these devices in order to fully consider them safe in a driving context. In this paper we present an evaluation of HUDs in a real driving context, analysing different kinds of information. Firstly, we assess the display of efficient driving data gathered from a mobile app. Next, we compare HUDs with conventional devices. Finally, we perform several tests using a GPS assistant, due to the current relevance of these services. A total of 20 non-professional drivers have participated in the experiments. They had to drive vehicles equipped with a HUD display. We evaluate the subjective opinion of the users using questionnaires in order to know whether HUDs are acceptable in a vehicle or not. Results show a positive feedback from users and a high sensation of safety.