Automated pavement distress detection benefits road maintenance and operation by providing the condition and location of various distress rapidly. Existing work generally relies on manual labor or specific algorithms trained by dedicated datasets, which hinders the efficiency and applicable scenarios of methods. Street view map provides interactive panoramas of a large scale of urban roadway network, and is updated in a recurrent manner by the provider. This paper proposed a deep learning method based on a pre-trained neural network architecture to identify and locate different distress in real-time. About 20,000 street view images were collected and labeled as the training dataset using the Baidu e-map. Eight types of distress are notated using Yolov3 deep learning architecture. The scale-invariant feature transform (SIFT) descriptors combined with GPS and bounding boxes were applied to judge the deterioration of the distress. A decision tree was designed to evaluate the change of the distress over some time. A typical road in Shanghai was selected to verify the effectiveness of the proposed model. The images of the road from 2015 to 2017 were collected from the street view map. The results showed that the mean average precision of the proposed algorithm is 88.37%, demonstrating the vast potential of applying this method to detect pavement distress. 43 distress were newly generated, and 49 previous distress were patched in the two years. The proposed method can assist the authorities to schedule the maintenance activities more effectively.

Vehicle detection is essential for driverless systems. However, the current single sensor detection mode is no longer sufficient in complex and changing traffic environments. Therefore, this paper combines camera and light detection and ranging (LiDAR) to build a vehicle-detection framework that has the characteristics of multi adaptability, high real-time capacity, and robustness. First, a multi-adaptive high-precision depth-completion method was proposed to convert the 2D LiDAR sparse depth map into a dense depth map, so that the two sensors are aligned with each other at the data level. Then, the You Only Look Once Version 3 (YOLOv3) real-time object detection model was used to detect the color image and the dense depth map. Finally, a decision-level fusion method based on bounding box fusion and improved Dempster–Shafer (D–S) evidence theory was proposed to merge the two results of the previous step and obtain the final vehicle position and distance information, which not only improves the detection accuracy but also improves the robustness of the whole framework. We evaluated our method using the KITTI dataset and the Waymo Open Dataset, and the results show the effectiveness of the proposed depth completion method and multi-sensor fusion strategy.

The autonomous navigation and environment exploration of mobile robots are carried out on the premise of the ability of environment sensing. Simultaneous localisation and mapping (SLAM) is the key algorithm in perceiving and mapping an environment in real time. FastSLAM has played an increasingly significant role in the SLAM problem. In order to enhance the performance of FastSLAM, a novel framework called IFastSLAM is proposed, based on particle swarm optimisation (PSO). In this framework, an adaptive resampling strategy is proposed that uses the genetic algorithm to increase the diversity of particles, and the principles of fractional differential theory and chaotic optimisation are combined into the algorithm to improve the conventional PSO approach. We observe that the fractional differential approach speeds up the iteration of the algorithm and chaotic optimisation prevents premature convergence. A new idea of a virtual particle is put forward as the global optimisation target for the improved PSO scheme. This approach is more accurate in terms of determining the optimisation target based on the geometric position of the particle, compared to an approach based on the maximum weight value of the particle. The proposed IFastSLAM method is compared with conventional FastSLAM, PSO-FastSLAM, and an adaptive generic FastSLAM algorithm (AGA-FastSLAM). The superiority of IFastSLAM is verified by simulations, experiments with a real-world dataset, and field experiments.

The battery state of charge (SOC) and state of power (SOP) are two essential parameters in the battery management system. For power lithium-ion batteries, temperature variation and the hysteresis effect are two of the main negative contributions to the accuracy of model-based SOC and SOP estimation. Thereby, a reliable circuit model is established herein to accurately estimate the working state of batteries. Considering the effect that temperature and hysteresis have on the electrical system, a unique fully-coupled temperature–hysteresis model is proposed to describe the interrelationship among capacity, hysteresis voltage, and temperature comprehensively. The key parameters of the proposed model are identified by experiments operated on lithium-ion batteries under varying ambient temperatures. Then we build a multi-state joint estimator to calculate the SOC and SOP on the basis of the temperature–hysteresis model. The effectiveness of the advanced model is verified by experiments at different temperatures. Moreover, the proposed joint estimator is verified by the improved dynamic stress test. The experimental results indicate that the proposed estimator making use of the temperature–hysteresis model can estimate SOC and SOP accurately and robustly. Our results also prove invaluable in terms of the construction of a flexible battery management system for applications in the actual industrial field.

Accurately predicting the remaining useful life (RUL) of lithium-ion batteries (LIBs) not only prevents battery system failure but also promotes the sustainable development of the energy storage industry and solves the pressing problems of industrial and energy crises. Because of the capacity regeneration phenomenon and random interference during the operation of lithium-ion batteries, the prediction precision and generalization performance of a single model can be poor. This article proposes a novel RUL prediction based on data pre-processing methods and the CNN-LSTM-ASAN framework. The model is based on a fusion technique for optimizing the tandem fusion of the Convolutional Neural Network (CNN) and the Long Short-Term Memory Network (LSTM). Firstly, the improved adaptive noise fully integrates empirical mode decomposition (ICEEMDAN) and the Pearson correlation coefficient (PCC), which are used to estimate the global deterioration tendency component and the local capacity restoration component, to reconstruct the dataset and eliminate the noise. Then, the Adaptive Sparse Attention Network (ASAN) is added in the model construction stage to improve the training efficiency of the model. The reconstructed degraded data are features extracted by the CNN-LSTM-ASAN model. Finally, the proposed method is validated against models such as DCLA, using the NASA public datasets, the CALCE public datasets, and the self-use datasets. And the results show that the root mean square error (RMSE) of the model is below 1.5%.