Explore the vast range of titles available.

A challenge still to be overcome in the field of visual perception for vehicle and robotic navigation on heavily damaged and unpaved roads is the task of reliable path and obstacle detection. The vast majority of the researches have scenario roads in good condition, from developed countries. These works cope with few situations of variation on the road surface and even fewer situations presenting surface damages. In this paper we present an approach for road detection considering variation in surface types, identifying paved and unpaved surfaces and also detecting damage and other information on other road surfaces that may be relevant to driving safety. Our approach makes use of Convolutional Neural Networks (CNN) to perform semantic segmentation, we use the U-NET architecture with ResNet34, in addition we use the technique known as Transfer Learning, where we first train a CNN model without using weights in the classes as a basis for a second CNN model where we use weights for each class. We also present a new Ground Truth with image segmentation, used in our approach and that allowed us to evaluate our results. Our results show that it is possible to use passive vision for these purposes, even using images captured with low cost cameras.

Anomalies in road surface not only impact road quality but also affect driver safety, mechanic structure of the vehicles, and fuel consumption. Several approaches have been proposed to automatic monitoring of the road surface condition in order to assess road roughness and to detect potholes. Some of these approaches adopt a crowdsensing perspective by using a built-in smartphone accelerometer to sense the road surface. Although the crowdsensing perspective has several advantages as ubiquitousness and low cost, it has certain sensibility to the false positives produced by man-made structures, driver actions, and road surface characteristics that cannot be considered as road anomalies. For this reason, we propose a deep learning approach that allows us (a) to automatically identify the different kinds of road surface, and (b) to automatically distinguish potholes from destabilizations produced by speed bumps or driver actions in the crowdsensing-based application context. In particular, we analyze and apply different deep learning models: convolutional neural networks, LSTM networks, and reservoir computing models. The experiments were carried out with real-world information, and the results showed a promising accuracy in solving both problems.

In order to identify the abnormal road surface condition efficiently and at low cost, a road surface condition recognition method is proposed based on the vibration acceleration generated by a smartphone when the vehicle passes through the abnormal road surface. The improved Gaussian background model is used to extract the features of the abnormal pavement, and the k-nearest neighbor (kNN) algorithm is used to distinguish the abnormal pavement types, including pothole and bump. Comparing with the existing works, the influence of vehicles with different suspension characteristics on the detection threshold is studied in this paper, and an adaptive adjustment mechanism based on vehicle speed is proposed. After comparing the field investigation results with the algorithm recognition results, the accuracy of the proposed algorithm is rigorously evaluated. The test results show that the vehicle vibration acceleration contains the road surface condition information, which can be used to identify the abnormal road conditions. The test result shows that the accuracy of the recognition of the road surface pothole is 96.03%, and the accuracy of the road surface bump is 94.12%. The proposed road surface recognition method can be utilized to replace the special patrol vehicle for timely and low-cost road maintenance.

The results of the road surface wear observations in different periods of the year on one of the highways are considered in the paper. Reducing the rate of wear of road surfaces by car tires is an urgent task for the Russian Federation, since the state incurs huge losses owing to this. A set of measures is necessary to reduce the wear of road surfaces, especially during the period when studded tires are used on the cars. Additional researches related to the specifics of our country are required for developing such activities. Foreign measures cannot be applied without significant modification, since each country has its own approach to solving this issue. It is necessary to fulfill a research of wear mechanisms in the “car tire – road surface” system and obtain quantitative dependences of the wear rate on some external factors to substantiate organizational and technical measures aimed at reducing road surface wear. The article presents the results of observations of the rate of increase in the track and the road surface roughness degradation are presented in the paper. The following quantitative indicators were determined as a result of observations: the rate of change in rut depth due to the road surface wear; spectral density of the microprofile of road surface roughness during its wear. Preliminary conclusions were drawn about the mechanism of road surface wear and proposals were formulated for the trend of further researches based on the results of field studies.

Automatic extraction of the road surface and road centerline from very high-resolution (VHR) remote sensing images has always been a challenging task in the field of feature extraction. Most existing road datasets are based on data with simple and clear backgrounds under ideal conditions, such as images derived from Google Earth. Therefore, the studies on road surface extraction and road centerline extraction under complex scenes are insufficient. Meanwhile, most existing efforts addressed these two tasks separately, without considering the possible joint extraction of road surface and centerline. With the introduction of multitask convolutional neural network models, it is possible to carry out these two tasks simultaneously by facilitating information sharing within a multitask deep learning model. In this study, we first design a challenging dataset using remote sensing images from the GF-2 satellite. The dataset contains complex road scenes with manually annotated images. We then propose a two-task and end-to-end convolution neural network, termed Multitask Road-related Extraction Network (MRENet), for road surface extraction and road centerline extraction. We take features extracted from the road as the condition of centerline extraction, and the information transmission and parameter sharing between the two tasks compensate for the potential problem of insufficient road centerline samples. In the network design, we use atrous convolutions and a pyramid scene parsing pooling module (PSP pooling), aiming to expand the network receptive field, integrate multilevel features, and obtain more abundant information. In addition, we use a weighted binary cross-entropy function to alleviate the background imbalance problem. Experimental results show that the proposed algorithm outperforms several comparative methods in the aspects of classification precision and visual interpretation.

We propose a speed-adaptive robot accurate path-tracking framework based on the soft actor–critic (SAC) and Stanley methods (STANLY_ASAC). First, the Lidar–Inertial Odometry Simultaneous Localization and Mapping (LIO-SLAM) method is used to map the environment and the LIO-localization framework is adopted to achieve real-time positioning and output the robot pose at 100 Hz. Next, the Rapidly exploring Random Tree (RRT) algorithm is employed for global path planning. On this basis, we integrate an improved A* algorithm for local obstacle avoidance and apply a gradient descent smoothing algorithm to generate a reference path that satisfies the robot’s kinematic constraints. Secondly, a network classification model based on U-Net is used to classify common road surfaces and generate classification results that significantly compensate for tracking accuracy errors caused by incorrect road surface coefficients. Next, we leverage the powerful learning capability of adaptive SAC (ASAC) to adaptively adjust the vehicle’s acceleration and lateral deviation gain according to the road and vehicle states. Vehicle acceleration is used to generate the real-time tracking speed, and the lateral deviation gain is used to calculate the front wheel angle via the Stanley tracking algorithm. Finally, we deploy the algorithm on a mobile robot and test its path-tracking performance in different scenarios. The results show that the proposed path-tracking algorithm can accurately follow the generated path.

Carrying out repair works, reconstruction, and construction of new road surfaces is a permanent element of urban space. The quality of the new pavement for the adopted traffic category directly impacts the road infrastructure's durability. The choice of road surface structure depends on the adopted traffic category. The aim of the article is to assess the works carried out on selected road surfaces within the city of Płock (Poland) in terms of the technical specification requirements and the durability of road infrastructure. The paper presents the tests of three road layers: base layer, binding layer and wearing course. The tests were carried out on 11 streets, and 29 samples were collected.

Most existing road extraction approaches apply learning models based on semantic segmentation networks and consider reduced study areas, featuring favorable scenarios. In this work, an end-to-end processing strategy to extract the road surface areas from aerial orthoimages at the scale of the national territory is proposed. The road mapping solution is based on the consecutive execution of deep learning (DL) models trained for ① road recognition, ② semantic segmentation of road surface areas, and ③ post-processing of the initial predictions with conditional generative learning, within the same processing environment. The workflow also involves steps such as checking if the aerial image is found within the country’s borders, performing the three mentioned DL operations, applying a p=0.5 decision limit to the class predictions, or considering only the central 75% of the image to reduce prediction errors near the image boundaries. Applying the proposed road mapping solution translates to operations aimed at checking if the latest existing cartographic support (aerial orthophotos divided into tiles of 256 × 256 pixels) contains the continuous geospatial element, to obtain a linear approximation of its geometry using supervised learning, and to improve the initial semantic segmentation results with post-processing based on image-to-image translation. The proposed approach was implemented and tested on the openly available benchmarking SROADEX dataset (containing more than 527,000 tiles covering approximately 8650 km2 of the Spanish territory) and delivered a maximum increase in performance metrics of 10.6% on unseen, testing data. The predictions on new areas displayed clearly higher quality when compared to existing state-of-the-art implementations trained for the same task.

The rapid advancement of hub-motor electric vehicle (HMEV) is propelled by its capacity to significantly improve energy efficiency, handling dynamics, and space utilization while minimizing mechanical losses and maintenance costs. A significant challenge in HMEV is mitigating the performance degradation caused by unbalanced electromagnetic force (UEMF), which result from the interaction between the hub motor and road-induced vibrations. This study introduces an Adaptive Distributed Explicit Model Predictive Control (ADEMPC) strategy for hub-motor electric vehicles equipped with air suspension (HM-AS), aiming to enhance ride comfort, handling stability, and reduce eccentricity between the stator and rotor. A full-vehicle dynamic model considering vertical-longitudinal coupling is established and validated. A road surface identification system based on a BP neural network is designed. The Whale Optimization Algorithm (WOA) is used to optimize weight coefficients on 16 conditions, which are then saved as tables for ADEMPC. An ADEMPC controller is designed based on distributed prediction model, which decompose the entire vehicle into four subsystems and consider the coupling of roll and pitch. Simulation results demonstrated that ADEMPC achieved improvements of 24.44% in body acceleration, 21.43% in eccentricity, 14% in tire dynamic load, 25% in roll, and 21.74% in pitch. It showcases its effectiveness in enhancing ride comfort and vehicle stability.

Poor road-surface conditions pose a significant safety risk to vehicle operation, especially in the case of autonomous vehicles. Hence, maintenance of road surfaces will become even more important in the future. With the development of deep learning-based computer image processing technology, artificial intelligence models that evaluate road conditions are being actively researched. However, as the lighting conditions of the road surface vary depending on the weather, the model performance may degrade for an image whose brightness falls outside the range of the learned image, even for the same road. In this study, a semantic segmentation model with an autoencoder structure was developed for detecting road surface along with a CNN-based image preprocessing model. This setup ensures better road-surface crack detection by adjusting the image brightness before it is input into the road-crack detection model. When the preprocessing model was applied, the road-crack segmentation model exhibited consistent performance even under varying brightness values.