Jose Eugenio Naranjo

The introduction of vehicles with a higher level of automation is proving to be a challenge, especially when dealing with complex scenarios in which sensory perception does not allow for complete and robust situational awareness, but in which the system must be able to make decisions

Autonomous driving is a topic of great interest for developers, researchers, and even automotive integrators and manufacturers

Recent advancements in computer science include some optimization models that have been developed and used in real applications. Some metaheuristic search/optimization algorithms have been tested to obtain optimal solutions to speed controller applications in self-driving cars. Some metaheuristic algorithms are based on social behaviour, resulting in several search models, functions, and parameters, and thus algorithm-specific strengths and weaknesses. The present paper proposes a fitness function on the basis of the mathematical description of proportional integrative derivate controllers showing that mean square error is not always the best measure when looking for a solution to the problem. The fitness developed in this paper contains features and equations from the mathematical background of proportional integrative derivative controllers to calculate the best performance of the system. Such results are applied to quantitatively evaluate the performance of twenty-one optimization algorithms. Furthermore, improved versions of the fitness function are considered, in order to investigate which aspects are enhanced by applying the optimization algorithms. Results show that the right fitness function is a key point to get a good performance, regardless of the chosen algorithm. The aim of this paper is to present a novel objective function to carry out optimizations of the gains of a PID controller, using several computational intelligence techniques to perform the optimizations. The result of these optimizations will demonstrate the improved efficiency of the selected control schema.

One of the technologies widely considered to be the most promising for reducing a number of traffic-related problems, including traffic jams, safety within and outside of cities, among others, is the autonomous vehicle

The synthesis of electric motor control systems, seeking optimal performance, is a well-known and studied field of automation to date. However, the solutions often use very elaborate mathematical foundations and sometimes require considerable algorithmic complexity. Another approach to the same problem, which offers very interesting results, is the use of artificial intelligence methods to generate controllers. Intelligent methods allow the use of bio-inspired approaches to solve complex problems. This article presents a method to adjust the parameters of a controller for DC motors based on two components in the objective function: High productivity and efficiency. This can be achieved using well-known and low algorithmic complexity PID controllers, and metaheuristic artificial intelligence techniques to adjust a controller to obtain optimal behavior. To validate the benefits of the methodological proposal, a simulator of a DC motor has been rigorously constructed, respecting fundamental physical principles. The adjustment system based on metaheuristics (genetics algorithms) has been designed to work on the simulator and constitutes the central contribution of the paper. This system has been designed to establish the parameters of a PID controller, optimizing its behavior in relation to two variables of interest, such as performance and energy efficiency (a non-trivial problem). The results obtained confirm the benefits of the approach.

Object detection, one of the most fundamental and challenging problems in computer vision. Nowadays some dedicated embedded systems have emerged as a powerful strategy for deliver high processing capabilities including the NVIDIA Jetson family. The aim of the present work is the recognition of objects in complex rural areas through an embedded system, as well as the verification of accuracy and processing time. For this purpose, a low power embedded Graphics Processing Unit (Jetson Nano) has been selected, which allows multiple neural networks to be run in simultaneous and a computer vision algorithm to be applied for image recognition. As well, the performance of these deep learning neural networks such as ssd-mobilenet v1 and v2, pednet, multiped and ssd-inception v2 has been tested. Moreover, it was found that the accuracy and processing time were in some cases improved when all the models suggested in the research were applied. The pednet network model provides a high performance in pedestrian recognition, however, the sdd-mobilenet v2 and ssd-inception v2 models are better at detecting other objects such as vehicles in complex scenarios.

The development of speed controllers under execution in autonomous vehicles within their dynamic driving task (DDT) is a traditional research area from the point of view of control techniques. In this regard, Proportional – Integral – Derivative (PID) controllers are the most widely used in order to meet the requirements of cruise control. However, fine tuning of the parameters associated with this type of controller can be complex, especially if it is intended to optimize them and reduce their characteristic errors. The objective of the work described in this paper is to evaluate the capacity of several metaheuristics for the adjustment of the parameters Kp, 1/Ti, and 1/Td of a PID controller to regulate the speed of a vehicle. To do this, an adjustment error function has been established from a linear combination of classic estimators of the goodness of the controller, such as overshoot, settling time (ts), steady-state error (ess), and the number of changes of sign of the signal (d). The error obtained when applying the controller has also been compared to a computational model of the vehicle after estimating the parameters Kp, Ki, and Kd, both for a setpoint sequence used in the adjustment of the system parameters and for a sequence not used during the adjustment, and therefore unknown by the system. The main novelty of the paper is to propose a new global error function, a function that enables the use of heuristic optimization methods for PID tuning. This optimization has been carried out by using three methods: genetic algorithms (GA), memetics algorithms (MA), and mesh adaptive direct search (MADS). The results of the application of the optimization methods using the proposed metric show that the accuracy of the PID controller is improved, compared with the classical optimization based on classical methods like the integral absolute error (IAE) or similar metrics, reducing oscillatory behaviours as well as minimizing the analysed performance indexes.

Identifying driving styles using classification models with in-vehicle data can provide automated feedback to drivers on their driving behavior, particularly if they are driving safely. Although several classification models have been developed for this purpose, there is no consensus on which classifier performs better at identifying driving styles. Therefore, more research is needed to evaluate classification models by comparing performance metrics. In this paper, a data-driven machine-learning methodology for classifying driving styles is introduced. This methodology is grounded in well-established machine-learning (ML) methods and literature related to driving-styles research. The methodology is illustrated through a study involving data collected from 50 drivers from two different cities in a naturalistic setting. Five features were extracted from the raw data. Fifteen experts were involved in the data labeling to derive the ground truth of the dataset. The dataset fed five different models (Support Vector Machines (SVM), Artificial Neural Networks (ANN), fuzzy logic, k-Nearest Neighbor (kNN), and Random Forests (RF)). These models were evaluated in terms of a set of performance metrics and statistical tests. The experimental results from performance metrics showed that SVM outperformed the other four models, achieving an average accuracy of 0.96, F1-Score of 0.9595, Area Under the Curve (AUC) of 0.9730, and Kappa of 0.9375. In addition, Wilcoxon tests indicated that ANN predicts differently to the other four models. These promising results demonstrate that the proposed methodology may support researchers in making informed decisions about which ML model performs better for driving-styles classification.

There are different proposals in the literature on how to protect pedestrians using warning systems to alert drivers of their presence. They can be based on onboard perception systems or wireless communications. The evaluation of these systems has been focused on testing their ability to detect pedestrians. A problem that has received much less attention is the possibility of generating too many alerts in the warning systems. In this paper, we propose and analyze four different algorithms to take the decision on generating alerts in a warning system that is based on direct wireless communications between vehicles and pedestrians. With the algorithms, we explore different strategies to reduce unnecessary alerts. The feasibility of the implementation of the algorithms was evaluated with a deployment using real equipment, and tests were carried out to verify their behavior in real scenarios. The ability of each algorithm to reduce unnecessary alerts was evaluated with realistic simulations in an urban scenario, using a traffic simulator with vehicular and pedestrian flows. The results show the importance of tackling the problem of driver overload in warning systems, and that it is not straightforward to predict the load of alerts generated by an algorithm in a large-scale deployment, in which there are multiple interactions between vehicles and pedestrians.