Search

Arrow signs found on roadway pavement are an important component of modern transportation systems. Given the rise in autonomous vehicles, public agencies are increasingly interested in accurately identifying and analysing detailed road pavement information to generate comprehensive road maps and decision support systems that can optimise traffic flow, enhance road safety, and provide complete official road cartographic support (that can be used in autonomous driving tasks). As arrow signs are a fundamental component of traffic guidance, this paper aims to present a novel deep learning-based approach to identify the orientation and direction of arrow signs on marked roadway pavements using high-resolution aerial orthoimages. The approach is based on convolutional neural network architectures (VGGNet, ResNet, Xception, and DenseNet) that are modified and adapted for regression tasks with a proposed learning structure, together with an ad hoc model, specially introduced for this task. Although the best-performing artificial neural network was based on VGGNet (VGG-19 variant), it only slightly surpassed the proposed ad hoc model in the average values of the R2 score, mean squared error, and angular error by 0.005, 0.001, and 0.036, respectively, using the training set (the ad hoc model delivered an average R2 score, mean squared error, and angular error of 0.9874, 0.001, and 2.516, respectively). Furthermore, the ad hoc model's predictions using the test set were the most consistent (a standard deviation of the R2 score of 0.033 compared with the score of 0.042 achieved using VGG19), while being almost eight times more computationally efficient when compared with the VGG19 model (2,673,729 parameters vs VGG19′s 20,321,985 parameters). [ABSTRACT FROM AUTHOR]

The problem of simultaneous localization and mapping (SLAM) in mobile robotics currently remains a crucial issue to ensure the safety of autonomous vehicles' navigation. One approach addressing the SLAM problem and odometry estimation has been through perception sensors, leading to V-SLAM and visual odometry solutions. Furthermore, for these purposes, computer vision approaches are quite widespread, but LiDAR is a more reliable technology for obstacles detection and its application could be broadened. However, in most cases, definitive results are not achieved, or they suffer from a high computational load that limits their operation in real time. Deep Learning techniques have proven their validity in many different fields, one of them being the perception of the environment of autonomous vehicles. This paper proposes an approach to address the estimation of the ego-vehicle positioning from 3D LiDAR data, taking advantage of the capabilities of a system based on Machine Learning models, analyzing possible limitations. Models have been used with two real datasets. Results provide the conclusion that CNN-based odometry could guarantee local consistency, whereas it loses accuracy due to cumulative errors in the evaluation of the global trajectory, so global consistency is not guaranteed. [ABSTRACT FROM AUTHOR]

Secondary roads represent the largest part of the road network. However, due to the absence of clearly defined edges, presence of occlusions, and differences in widths, monitoring and mapping them represents a great effort for public administration. We believe that recent advancements in machine vision allow the extraction of these types of roads from high-resolution remotely sensed imagery and can enable the automation of the mapping operation. In this work, we leverage these advances and propose a deep learning-based solution capable of efficiently extracting the surface area of secondary roads at a large scale. The solution is based on hybrid segmentation models trained with high-resolution remote sensing imagery divided in tiles of 256 × 256 pixels and their correspondent segmentation masks, resulting in increases in performance metrics of 2.7–3.5% when compared to the original architectures. The best performing model achieved Intersection over Union and F1 scores of maximum 0.5790 and 0.7120, respectively, with a minimum loss of 0.4985 and was integrated on a web platform which handles the evaluation of large areas, the association of the semantic predictions with geographical coordinates, the conversion of the tiles' format and the generation of geotiff results compatible with geospatial databases. [ABSTRACT FROM AUTHOR]

Inappropriate speed is a relevant concurrent factor in many traffic accidents. Moreover, in recent years, traffic accidents numbers in Spain have fallen sharply, but this reduction has not been so significant on single carriageway roads. These infrastructures have less equipment than high-capacity roads, therefore measures to reduce accidents on them should be implemented in vehicles. This article describes the development and analysis of the impact on the driver of a warning system for the safe speed on each road section in terms of geometry, the presence of traffic jams, weather conditions, type of vehicle and actual driving conditions. This system is based on an application for smartphones and includes knowledge of the vehicle position via Ground Positioning System (GPS), access to intravehicular information from onboard sensors through the Controller Area Network (CAN) bus, vehicle data entry by the driver, access to roadside information (short-range communications) and access to a centralized server with information about the road in the current and following sections of the route (long-range communications). Using this information, the system calculates the safe speed, recommends the appropriate speed in advance in the following sections and provides warnings to the driver. Finally, data are sent from vehicles to a server to generate new information to disseminate to other users or to supervise drivers' behaviour. Tests in a driving simulator have been used to define the system warnings and Human Machine Interface (HMI) and final tests have been performed on real roads in order to analyze the effect of the system on driver behavior. [ABSTRACT FROM AUTHOR]

Grouping urban bus routes is necessary when there are evidences of significant differences among them. In Jiménez et al. (2013), a reduced sample of routes was grouped into clusters utilizing kinematic measured data. As a further step, in this paper, the remaining urban bus routes of a city, for which no kinematic measurements are available, are classified. For such purpose we use macroscopic geographical and functional variables to describe each route, while the clustering process is performed by means of a neural network. Limitations caused by reduced training samples are solved using the bootstrap method. [ABSTRACT FROM AUTHOR]

The development of new-generation intelligent vehicle technologies will lead to a better level of road safety and \CO2 emission reductions. However, the weak point of all these systems is their need for comprehensive and reliable data. For traffic data acquisition, two sources are currently available: 1) infrastructure sensors and 2) floating vehicles. The former consists of a set of fixed point detectors installed in the roads, and the latter consists of the use of mobile probe vehicles as mobile sensors. However, both systems still have some deficiencies. The infrastructure sensors retrieve information from static points of the road, which are spaced, in some cases, kilometers apart. This means that the picture of the actual traffic situation is not a real one. This deficiency is corrected by floating cars, which retrieve dynamic information on the traffic situation. Unfortunately, the number of floating data vehicles currently available is too small and insufficient to give a complete picture of the road traffic. In this paper, we present a floating car data (FCD) augmentation system that combines information from floating data vehicles and infrastructure sensors, and that, by using neural networks, is capable of incrementing the amount of FCD with virtual information. This system has been implemented and tested on actual roads, and the results show little difference between the data supplied by the floating vehicles and the virtual vehicles. [ABSTRACT FROM PUBLISHER]

Most of the tactic manoeuvres during driving require a certain understanding of the surrounding environment from which to devise our future behaviour. In this paper, a Convolutional Neural Network (CNN) approach is used to model the lane change behaviour to identify when a driver is going to perform this manoeuvre. To that end, a slightly modified CNN architecture adapted to both spatial (i.e., surrounding environment) and non-spatial (i.e., rest of variables such as relative speed to the front vehicle) input variables. Anticipating a driver's lane change intention means it is possible to use this information as a new source of data in wide range of different scenarios. One example of such scenarios might be the decision making process support for human drivers through Advanced Driver Assistance Systems (ADAS) fed with the data of the surrounding cars in an inter-vehicular network. Another example might even be its use in autonomous vehicles by using the data of a specific driver profile to make automated driving more human-like. Several CNN architectures have been tested on a simulation environment to assess their performance. Results show that the selected architecture provides a higher degree of accuracy than random guessing (i.e., assigning a class randomly for each observation in the data set), and it can capture subtle differences in behaviour between different driving profiles. [ABSTRACT FROM AUTHOR]

The objective of this research is to improve the hydrogen production and total profit of a real Steam Reforming plant. Given the impossibility of tuning the real factory to optimize its operation, we propose modelling the plant using Artificial Neural Networks (ANNs). Particularly, we combine a set of independent ANNs into a single model. Each ANN uses different sets of inputs depending on the physical processes simulated. The model is then optimized as a black-box system using metaheuristics (Genetic and Memetic Algorithms). We demonstrate that the proposed ANN model presents a high correlation between the real output and the predicted one. Additionally, the performance of the proposed optimization techniques has been validated by the engineers of the plant, who reported a significant increase in the benefit that was obtained after optimization. Furthermore, this approach has been favorably compared with the results that were provided by a general black-box solver. All methods were tested over real data that were provided by the factory. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Remote sensing imagery combined with deep learning strategies is often regarded as an ideal solution for interpreting scenes and monitoring infrastructures with remarkable performance levels. In addition, the road network plays an important part in transportation, and currently one of the main related challenges is detecting and monitoring the occurring changes in order to update the existent cartography. This task is challenging due to the nature of the object (continuous and often with no clearly defined borders) and the nature of remotely sensed images (noise, obstructions). In this paper, we propose a novel framework based on convolutional neural networks (CNNs) to classify secondary roads in high-resolution aerial orthoimages divided in tiles of 256 × 256 pixels. We will evaluate the framework's performance on unseen test data and compare the results with those obtained by other popular CNNs trained from scratch. [ABSTRACT FROM AUTHOR]

Road vehicles include more and more assistance systems that perform tasks to facilitate driving and make it safer and more efficient. However, the automated vehicles currently on the market do not exceed SAE level 2 and only in some cases reach level 3. Nevertheless, the qualitative and technological leap needed to reach level 4 is significant and numerous uncertainties remain. In this sense, a greater knowledge of the environment is needed for better decision making and the role of the driver changes substantially. This paper proposes the combination of cooperative systems with automated driving to offer a wider range of information to the vehicle than on-board sensors currently provide. This includes the actual deployment of a cooperative corridor on a highway. It also takes into account that in some circumstances or scenarios, pre-set or detected by on-board sensors or previous communications, the vehicle must hand back control to the driver, who may have been performing other tasks completely unrelated to supervising the driving. It is thus necessary to assess the driver's condition as regards retaking control and to provide assistance for a safe transition. [ABSTRACT FROM AUTHOR]