No abstract

In recent years, there have been many advances in vehicle technologies based on the efficient use of real-time data provided by embedded sensors. Some of these technologies can help you avoid or reduce the severity of a crash such as the Roll Stability Control (RSC) systems for commercial vehicles. In RSC, several critical variables to consider such as sideslip or roll angle can only be directly measured using expensive equipment. These kind of devices would increase the price of commercial vehicles. Nevertheless, sideslip or roll angle or values can be estimated using MEMS sensors in combination with data fusion algorithms. The objectives stated for this research work consist of integrating roll angle estimators based on Linear and Unscented Kalman filters to evaluate the precision of the results obtained and determining the fulfillment of the hard real-time processing constraints to embed this kind of estimators in IoT architectures based on low-cost equipment able to be deployed in commercial vehicles. An experimental testbed composed of a van with two sets of low-cost kits was set up, the first one including a Raspberry Pi 3 Model B, and the other having an Intel Edison System on Chip. This experimental environment was tested under different conditions for comparison. The results obtained from low-cost experimental kits, based on IoT architectures and including estimators based on Kalman filters, provide accurate roll angle estimation. Also, these results show that the processing time to get the data and execute the estimations based on Kalman Filters fulfill hard real time constraints.

Presently, autonomous vehicles are on the rise and are expected to be on the roads in the coming years. In this sense, it becomes necessary to have adequate knowledge about its states to design controllers capable of providing adequate performance in all driving scenarios. Sideslip and roll angles are critical parameters in vehicular lateral stability. The later has a high impact on vehicles with an elevated center of gravity, such as trucks, buses, and industrial vehicles, among others, as they are prone to rollover. Due to the high cost of the current sensors used to measure these angles directly, much of the research is focused on estimating them. One of the drawbacks is that vehicles are strong non-linear systems that require specific methods able to tackle this feature. The evolution in Artificial Intelligence models, such as the complex Artificial Neural Network architectures that compose the Deep Learning paradigm, has shown to provide excellent performance for complex and non-linear control problems. In this paper, the authors propose an inexpensive but powerful model based on Deep Learning to estimate the roll and sideslip angles simultaneously in mass production vehicles. The model uses input signals which can be obtained directly from onboard vehicle sensors such as the longitudinal and lateral accelerations, steering angle and roll and yaw rates. The model was trained using hundreds of thousands of data provided by Trucksim® and validated using data captured from real driving maneuvers using a calibrated ground truth device such as VBOX3i dual-antenna GPS from Racelogic®. The use of both Trucksim® software and the VBOX measuring equipment is recognized and widely used in the automotive sector, providing robust data for the research shown in this article.

No abstract

No abstract