Validating the Impact on Reducing Fuel Consumption by Using an EcoDriving Assistant Based on Traffic Sign Detection and Optimal Deceleration Patterns

This paper implements and validates an expert system that, based on the detection or previous knowledge of certain types of traffic signals, proposes a method to reduce fuel consumption by calculating optimal deceleration patterns, minimizing the use of braking. The expert system uses a mobile device's embedded camera to monitor the environment and to recognize certain types of static traffic signals that force or can force a vehicle to stop. The system uses an adaptation of the algorithm proposed by Viola and Jones for the recognition of faces in real time, adapted to the detection of traffic signals. Detected signals are also incorporated into a central database for future use. When the vehicle approaches an upcoming traffic signal, the algorithm estimates the distance required to stop the vehicle without using the brakes, taking into account the rolling resistance coefficient and the road slope angle. Appropriate advice and feedback are provided to the driver to release the accelerator pedal. The expert system is implemented on Android mobile devices and has been validated using a data set of 180 tests with five different models of vehicles and nine different drivers. The main contribution of this paper is the proposal of an assistant that uses information from the environment and from the vehicle to calculate optimal deceleration patterns when approaching traffic signals that force or may force the vehicle to stop. In addition, the proposed solution does not require the installation of infrastructure on the road, and it can be installed into any vehicle.