In order to improve the recognition accuracy and pre-judgment ability of autonomous vehicles in high-speed dynamic complex traffic scenarios, The lane-changing intention recognition model based on convolutional residual Bidirectional Long Short-Term Memory (BiLSTM) with fusion attention mechanism is proposed. It uses the one-dimensional Convolutional Neural Network (CNN) to extract the vehicle’s motion state features. The constructed feature vector is used as the input information of BiLSTM network. The residual connection is used to solve the problems of optimization bottlenecks and gradient disappearance in multi-layer BiLSTM network. It’s achieved to a adjust the weight of the output of the residual BiLSTM network at different moments with the attention mechanism. And the driving intent probability can be calculated by the Softmax function. The validity of the model is verified by using the expressway data set in NGSIM, the performance and effect of the other 4 models are compared with the model. The results show that the recognition accuracy of the lane-changing intention is the highest, which reaches 97.44%, and prediction accuracy of the vehicle’s lane-changing intention is 90% and higher within 2.5 s before the changing lanes, it shows that the model has better intent recognition accuracy and prediction ability.

In order to accurately reflect the driving motion characteristics of vehicles on the real road, this paper proposes a vehicle driving cycle construction method based on Markov fusion online map information. In this paper, the actual collected vehicle driving data were cleaned and segmented that were clustered and analyzed by Principal Component Analysis (PCA) method and K-Means clustering method, and a typical working condition fragment library based on Markov was established. The road information of the planned path on the online map was integrated in the fragment database, and the road driving condition of the vehicle was constructed. An electric vehicle was taken as the research object for simulation and analysis, the results show that the energy consumption of online map planning driving condition based on Markov fragment library is closer to the actual road condition than that of online map basic planning condition. The error of characteristic parameters is only 4.29%, and the error of energy consumption is only 4.09%.

This paper presentes a deep reinforcement learning based energy management strategy for Plug-in Hybrid Electric Vehicle (PHEV) of the THS-III platform. Firstly, a forward simulation model of the vehicle was built using MATLAB/Simulink. Secondly, a Markov process for vehicle energy management and a deep reinforcement learning algorithm were built. Finally, simulation and verification were carried out using WLTC-Class3 and ACC-60. The simulation results indicate that compared with the rule-based energy management strategy, the deep reinforcement learning-based energy management strategy saves 16.51% in cost and 15.56% in fuel consumption under WLTC-Class3, and saves 31.95% in cost and 29.96% in fuel consumption under ACC-60.

In order to solve the problem of low accuracy of oil stirring loss calculation caused by turbulence in the complex multi-pair gearing reducer, based on the Moving Particle Semi-implicit (MPS) method of Lagrangian system, and combined with Smagorinsky turbulence model and the calculation method of turbulent shear stress on polyhedral wall, the calculation accuracy of stirring loss was improved, which was verified by simulation and test. Finally, the influence of different oil stirring loss on the efficiency of recirculating conditions was analyzed. Research results show that the method can effectively improve the calculation accuracy from 47% to 91% on average of the oil stirring loss of the reducer, and the improvement effect is especially obvious in high-speed conditions. In the recirculating condition, the oil stirring loss has a significant impact on the reducer efficiency, and reducing the oil stirring loss can effectively improve the reducer efficiency in the recirculating condition.

In order to realize the torque control accuracy of the electric drive system under the influence of the deviation of permanent magnet supply, the temperature deviation of permanent magnet, the current sensor accuracy deviation, the voltage sensor accuracy deviation, the calibration temperature management deviation and the initial angle detection influence deviation, simulation and test were conducted to obtain the influence factors under the independent action of the above factors, and statistical principle was used to obtain the torque control accuracy range of the comprehensive influence factors, which was tested and verified on the prototype. Test results show that the accuracy of the torque value calculated by this method is within the range of -1.1%~2.8%, which meets the product requirements.

This paper overviewed comprehensively the typical Active Collision Avoidance (ACA) systems and technological development, it firstly introduced the categories of ACA systems and its technical principle, then summed up the core key technologies of ACA system and technological level and summarized the mass-produced ACA products. The paper finally analyzed and predicted the development trend of ACA products.

For the defects of traditional A* algorithm in unmanned vehicle path planning in structured road scene, such as multiple twists and turns of search path, close to obstacle boundary, unsmooth and exponential growth trend of search time with the increase of grid scale, this paper proposed an improved A* algorithm. Firstly, the map preview module was used to extract the key nodes in the grid map, then the collision field model based on the safe distance was introduced to adjust the cost function. The algorithm conducted incremental extended search based on the information of key nodes until the target node was identified. Finally, the generated path was smoothed by quasi uniform cubic B-spline curve to obtain the final planned path. The simulation results show that compared with the traditional A* and weighted-A* algorithm, the improved A* algorithm proposed in this paper improves the search efficiency, path security and feasibility.

In order to effectively solve the problem of limited amount of downloaded data due to the short travel time of vehicles in the coverage of Road Side Unit (RSU) during high-speed movement, this paper proposed a message transmission strategy of vehicle road cooperation mode based on ant colony algorithm. According to the characteristics that information such as vehicle data can be shared between RSUs, the corresponding heuristic function and the corresponding path pheromone update principle were designed to form multiple vehicle road cooperation communication groups, which increased the amount and types of data transmission in the network and avoid falling into the local optimal solution. SUMO simulation platform was utilized for experimental verification. The results show that, compared with the non-cooperation, Coalition Formation Games (CGS) and Multilevel Hyper-graph Partitioning Based on Heavy Edge Matching Scheme (MHEMs), the proposed strategy is better than the above strategies in terms of information transmission volume, road network revenue and operating time, which proves the effectiveness of this strategy.

To solve the problems of matching omission and poor real-time performance of existing visual place recognition methods in scenes with changing viewpoints and environments, this paper proposed visual place recognition method based on one level feature fused with coordinate attention. Firstly, the relative place information of features was captured by coordinate attention. Secondly, an encoder for multi-scale feature fusion was constructed using dilated convolution and NetVLAD. Finally, the network was trained based on triplet loss. Validated by Pitts30k and Nordland datasets, the proposed method achieves the same recall accuracy and 19% faster retrieval speed compared with the state-of-the-art method Patch-NetVLAD of the same baseline in the test of position recognition. In the test of loop detection, the proposed method achieves a reasonable balance between robustness and retrieval speed.

Based on the actual operating data of electric vehicles, this paper proposed an analysis method of in-service power battery usage behaviors, so as to quantitatively evaluate the charging behaviors and driving behaviors of vehicles, and provide effective support for battery fault diagnosis. Firstly, characteristic parameters of power battery use behaviors based on membership function were extracted, and then the accumulative risk score of using behaviors was defined and calculated. Finally, the battery use behavior differences between vehicles and vehicles in different time dimensions were quantitatively analyzed by using the idea of horizontal and vertical comparison. Experimental results show that there is a strong positive correlation between the battery using behavior score quantified in this paper and battery pack consistency, which can fully evaluate the using behavior of power battery, and provide data support for battery fault diagnosis.