Abstract

Proceedings of 7th International Symposium on Ambient Intelligence (ISAmI 2016), Seville, Spain on June 1st–3rd Stress is one of the most important factors in car accidents. When the driver is in this mental state, their skills and abilities are reduced. In this paper, we propose an algorithm to predict stress level on a road. Prediction model is based on deep learning. The stress level estimation considers the previous driver's driving behavior before reaching the road section, the road state (weather and traffic), and the previous driving made by the driver. We employ this algorithm to build a speed assistant. The solution provides an optimum average speed for each road stage that minimizes the stress. Validation experiment has been conducted using five different datasets with 100 samples. The proposal is able to predict the stress level given the average speed by 84.20% on average. The system reduces the heart rate (15.22%) and the aggressiveness of driving. The proposed solution is implemented on Android mobile devices and uses a heart rate chest strap. The research leading to these results has received funding from the “HERMES-SMART DRIVER/CITIZEN” projects TIN2013-46801-C4-2-R /1-R funded by the Spanish MINECO, from the grant PRX15/00036 from the Ministerio de Educación Cultura y Deporte. Document type: Part of book or chapter of book

Abstract

In this paper, we propose a solution to reduce the stress level of the driver, minimize fuel consumption and improve safety. The system analyzes the driving style and the driver's workload during the trip while driving. If it discovers an area where the stress increases and the driving style is not appropriate from the point of view of energy efficiency and safety for a particular driver, the location of this area is saved in a shared database. On the other hand, the implemented solution warns a particular user when approaching a region where the driving is difficult (high fuel consumption and stress) using the shared database based on previous recorded knowledge of similar drivers in that area. In this case, the proposal provides an optimal deceleration profile if the vehicle speed is not adequate. Therefore, he or she may adjust the vehicle speed with both a positive impact on the driver workload and fuel consumption. The Data Envelopment Analysis algorithm is used to estimate the efficiency of driving and the driver's workload in in each area. We employ this method because there is no preconceived form on the data in order to calculate the efficiency and stress level. A validation experiment has been conducted using both a driving simulator and a real environment with 12 participants who made 168 driving tests. The system reduced the slowdowns (38%), heart rate (4.70%), and fuel consumption (12.41%) in the real environment. The proposed solution is implemented on Android mobile devices and does not require the installation of infrastructure on the road. It can be installed on any model of vehicle. The research leading to these results has received funding from the “HERMES-SMART DRIVER” project TIN2013- 46801-C4-2-R within the Spanish "Plan Nacional de I+D+I" under the Spanish Ministerio de Economía y Competitividad and from the Spanish Ministerio de Economía y Competitividad funded projects (co-financed by the Fondo Europeo de Desarrollo Regional (FEDER)) IRENE (PT-2012-1036-370000), COMINN (IPT-2012-0883-430000) and REMEDISS (IPT-2012-0882-430000) within the INNPACTO program. Document type: Part of book or chapter of book

Abstract

Proceedings of 2014 International Conference on Connected Vehicles and Expo (ICCVE,IEEE), took place 2014, November, 03-07, in Viena (Austria). In this paper, we propose a learning method for eco-driving based on imitation. The system uses Data Envelopment Analysis (DEA) in order to calculate the driving efficiency from the point of view of the fuel consumption. The input and output parameters have been selected taking into account the Longitudinal Vehicle Dynamics Model. This technique allows us to notify the user about who is the most efficient driver close to him or her and to suggest the imitation of the behavior of such driver. The proposed method promotes learning by observation and imitation of efficient drivers in a practical rather than theoretical way such as attending eco-driving lessons. The DEA algorithm does not depend on the definition of a preconceived form of the data in order to calculate the efficiency. The DEA algorithm estimates the inefficiency of a particular DMU by comparing it to similar DMUs considered as efficient. This is very important due to the dynamic nature of the traffic. A validation experiment has been conducted with 10 participants who made 500 driving tests in Spain. The results show that combining eco-driving lessons with the proposed learning system, drivers achieve a very significant improvement on fuel saving (15.82%) The research leading to these results has received funding from the “HERMES-SMART DRIVER” project TIN2013-46801-C4-2-R within the Spanish "Plan Nacional de I+D+I" under the Spanish Ministerio de Economía y Competitividad and from the Spanish Ministerio de Economía y Competitividad funded projects (co-financed by the Fondo Europeo de Desarrollo Regional (FEDER)) IRENE (PT-2012-1036-370000), COMINN (IPT-2012-0883-430000) and REMEDISS (IPT-2012-0882-430000) within the INNPACTO program. Publicado

Abstract

Through the application of intelligent systems in driver assistance systems, the experience of traveling by road has become much more comfortable and safe. In this sense, this paper then reports the development of an intelligent driving assistant, based on vehicle telemetry and road accident risk map analysis, whose responsibility is to alert the driver in order to avoid risky situations that may cause traffic accidents. In performance evaluations using real cars in a real environment, the on-board intelligent assistant reproduced real-time audio-visual alerts according to information obtained from both telemetry and road accident risk map analysis. As a result, an intelligent assistance agent based on fuzzy reasoning was obtained, which supported the driver correctly in real-time according to the telemetry data, the vehicle environment and the principles of secure driving practices and transportation regulation laws. Experimental results and conclusions emphasizing the advantages of the proposed intelligent driving assistant in the improvement of the driving task are presented. Document type: Article