The high rate of vehicle-crash victims has a fatal economic and social impact in today’s societies. In particular, road crashes where heavy vehicles are involved cause more severe damage because they are prone to rollover. For this reason, many researches are focused on developing RSC Roll Stability Control (RSC) systems. Concerning the design of RSC systems with an adequate performance, it is mandatory to know the dynamics of the vehicle. The main problem arises from the lack of ability to directly capture several required dynamic vehicle variables, such as roll angle, from low-cost sensors. Previous studies demonstrate that low-cost sensors can provide data in real-time with the required precision and reliability. Even more, other research works indicate that neural networks are efficient mechanisms to estimate roll angle. Nevertheless, it is necessary to assess that the fusion of data coming from low-cost devices and estimations provided by neural networks can fulfill hard real-time processing constraints, achieving high level of accuracy during circulation of a vehicle in real situations. In order to address this issue, this study has two main goals: (1) Design and develop an IoT based architecture, integrating ANN in low cost kits with different hardware architectures in order to estimate under real-time constraints the vehicle roll angle. This architecture is able to work under high dynamic conditions, by following specific best practices and considerations during its design; (2) assess that the IoT architecture deployed in low-cost experimental kits achieve the hard real-time performance constraints estimating the roll angle with the required calculation accuracy. To fulfil these objectives, an experimental environment was set up, composed of a van with two set of low-cost kits, one including a Raspberry Pi 3 Model Band the other having an Intel Edison System on Chip linked to a SparkFun 9 Degrees of Freedom module. This experimental environment be tested in different maneuvers for comparison purposes. Neural networks embedded in low-cost sensor kits provide roll angle estimations highly approximated to real values. Even more, Intel Edison and Raspberry Pi 3 Model B have enough computing capabilities to successfully run roll angle estimation based on neural networks to determine rollover risk situations, fulfilling real-time operation restrictions stated for this problem.

No abstract