Search

Copyright of Automotive Digest is the property of Automotive Digest Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

It is very important for autonomous driving vehicles to accurately detect objects such as vehicles and pedestrians on the road in real time. Aiming at the problems of missed detection and poor detection effect of small targets in the autonomous driving scene, this paper proposes an automatic driving target detection algorithm that improves the YOLOv7 algorithm. Firstly, it modifies the modules in the network to expand the receptive field, reduces the size of the receptive field module, and improves the speed of the model and enhances the ability to extract image feature information. Secondly, the paper introduces the BRA attention mechanism at the output of the backbone network to improve the model's ability to small target objects. Finally, it replaces the original CIOU loss function of the algorithm with the EIOU loss function to minimize the difference between the height and width of the predicted frame and the real frame, and speeds up the convergence of the model while achieving better positioning results. The experimental results show that: on the KITTI dataset, when the improved YOLOv7 algorithm performs target detection, its mAP reaches 94.7%, which is 3.1 percentage points higher than the original YOLOv7 algorithm, and it has achieved higher detection accuracy in small target object detection. It effectively improves the model's detection effect on small targets. [ABSTRACT FROM AUTHOR]

This paper takes the autonomous driving scenario library as the research object,and by analyzing shortcomings of autonomous driving scenario library and industry demand, and formes a set of operation guidelines for autonomous driving scenarios construction based on real world traffic data. Firstly, the elements and formats of autonomous driving scenarios have been illustrated and standardized. Secondly, scenario datasets are generated by a three-step procedure, including scenario mining, automated annotating and data compliance desensitization. Finally, a set of safe, compliant, high-quality, and highvalue city level challenging autonomous driving scenarios was ultimately formed by risk assessment of real collection scenarios and standardized processing of abnormal events. [ABSTRACT FROM AUTHOR]

[Objective] With the rapid popularization of new energy vehicles and the vigorous development of autonomous driving technology, 3D object detection algorithms play a pivotal role in real road scenes. The LiDAR point clouds contain precise position and geometric structure information of the object, which can accurately describe the 3D space position of the target. Moreover, LiDAR makes environmental perception and route planning of unmanned vehicles a reality. However, cars in real scenes often fall into complex and difficult situations, such as occlusion and truncation of objects, which contribute to highly sparse clouds and incomplete contours. Therefore, the effective use of disordered and unevenly distributed point clouds for accurate 3D object detection has important research significance and practical value for the safety of autonomous driving. [Methods] This paper uses LiDAR point clouds in an autonomous driving scene to conduct in-depth research on a high-performance 3D object detection algorithm based on deep learning. The 3D object detection algorithm based on multibranch feature fusion (PSANet) is designed to improve the capacity and viability of autonomous driving technology. After the disordered point clouds are divided into regular voxels, the voxel feature coding module and convolutional neural network are used to learn the voxel features, and the sparse 3D data are compressed into a dense 2D bird's-eye view. Furthermore, the multiscale bird's-eye view features are deeply fused through the coarse and fine branches of the 2D backbone network. The splitting and aggregation feature pyramid module in the fine branch splits and aggregates the bird's-eye view features at different levels and realizes the deep fusion of semantic information, texture information, and context information of multiscale features to obtain more expressive features. The multiscale features in the coarse branch are fused after transposed convolution, and the precise original spatial location information is preserved. After the feature extraction of coarse and fine branches, the element-wise addition method can obtain more accurate and complete features for object classification, position regression, and orientation prediction. [Results] The experimental results on the KITTI dataset show that the average precision of PSANet in 3D object detection and bird's-eye view object detection tasks reach 81.72% and 88.25%, respectively. The inference speed on a single GTX 1080Ti GPU can reach 24 frames per second, and it shows strong robustness in complex scenes. Compared with the two-stage target detection algorithms MV3D, AVOD-FPN, F-PointNet, and IPOD, the average accuracy of 3D target detection of this algorithm increased by 18.21%, 5.89%, 8.94%, and 3.12%, respectively. Compared with the one-stage target detection algorithms VoxelNet, SECOND, PointPillars, and VoTr-SSD, the average accuracy of 3D target detection of this algorithm increased by 11.63%, 4.05%, 3.19%, 0.98%, 1.16%, and 0.7%, respectively. The detection speed of this algorithm improved by 14 frames per second compared with the two-stage algorithm PointRCNN with similar accuracy. [Conclusions] In comparison with other advanced algorithms, this algorithm exhibits strong performance, in which it can better balance the accuracy and speed of target detection in autonomous driving scenarios. Higher accuracy is required in the algorithm, whether one- or two-stage, for novel applications. The method with the highest efficiency must be used in an autonomous car. [ABSTRACT FROM AUTHOR]

To address the high computational demands and slow convergence faced by DRL in the field of autonomous driving, this paper integrated VAE with PPO algorithm. By adopting VAE's feature encoding technology, it effectively transformed semantic images obtained from the Carla simulator into state inputs, thus tackling the high computational load of DRL in handling complex autonomous driving tasks. To solve the issues of local optima and slow convergence in DRL training, it introduced a driving intervention mechanism and a driver-guided experience replay mechanism. These mechanisms applied driving interventions during the initial training phase and when the model encounters local optima, so as to enhance the model's learning efficiency and generalization capability. Experimental validation, conducted in left-turn scenarios at intersections, shows that with the aid of the driving intervention mechanism, the model's performance improves more rapidly in the initial training phase. Moreover, driving interventions when encountering local optima further enhance the model's performance, with even more significant improvements observed in complex scenarios. [ABSTRACT FROM AUTHOR]

Camera pose estimation plays a crucial role in tasks such as autonomous driving and robotics, elucidating the direction and position of the camera in relation to a given scene through the estimation of its positional coordinates and angular deviations around the three coordinate axes. To facilitate the understanding of researchers in the realm of camera pose estimation, this paper comprehensively reviewed the current research status and latest progress in this field will. Firstly, it introduced the fundamental principles, evaluation indicators, and pertinent datasets associated with camera pose estimation. Subsequently, the review elaborated and summarized the two-stage model structure method and single-channel model structure method from the two key technologies of scene relationship construction and camera pose calculation. It conducted classification and analysis based on the diverse core algorithms and scene information employed, with performance comparisons drawn from indoor and outdoor public datasets. Lastly, it expounded the current challenges in the field and future development trends. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Autonomous vehicle can calculate the movement track of surrounding vehicles according to the track prediction algorithm, and make response to reduce driving risk, while the traditional track prediction model will produce large errors in the case of long-term series prediction. To address this issue, this paper proposed a trajectory prediction model based on the Informer algorithm, and used the publicly available dataset NGSIM to conduct experimental analysison. Firstly, it filtered the original data by using symmetric exponential moving average method(sEMA), and added a joint normalization layer to the original Informer encoder to extract features from different vehicles, reducing the motion error between different vehicles, and improving the prediction accuracy by considering the speed information of the vehicle itself and the vehicle movement information of the surrounding environment. Finally, it got the vehicle trajectory distribution at the future time through the decoder. The results show that the trajectory prediction error of the model is less than 0.5 m. Through the analysis of MAE and MSE results of trajectory prediction, when the prediction time exceeds 0.3 s, the trajectory prediction effect of Informer model is obviously better than other algorithms, which verifies the effectiveness of the model and algorithm. [ABSTRACT FROM AUTHOR]

Copyright of Automotive Digest is the property of Automotive Digest Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In response to the problem of typical end-to-end communication strategies that cannot determine the communication interval and can only communicate at fixed frequencies, an event-triggered communication strategy is proposed based on deep reinforcement learning to solve the minimal communication problem in multi-unmanned ground vehicles collaboration. Firstly, an event-triggered architecture is established, which mainly includes a communication controller and provides trigger conditions. This ensures that communication occurs among multiple unmanned ground vehicle only when the conditions are met, significantly reducing the overall communication volume. Secondly, the trigger mechanism is optimized using the multiple agent deep deterministic policy gradient (MADDPG) algorithm, which improves the convergence speed of the algorithm. Simulation and real vehicle experiments show that with increasing iterations, the amount of communication data in the multiple unmanned ground vehicle system is reduced by 55. 74% while still accomplishing the collaborative tasks, thus validating the effectiveness of the proposed strategy. [ABSTRACT FROM AUTHOR]

The area where vehicles conduct interchanges is designated as the on-ramp merging area. The traffic efficiency in the ramp merging area drastically decreases if the mainline and ramp traffic flow density reaches saturation. As a current research hotspot in transportation, intelligent network technology, relying on the high- precision motion control and high-efficiency communication of connected-automated vehicle (CAV), can significantly improve the traffic efficiency in the merging area. The fusion strategies used by CAV are assessed in this research utilizing three different control paradigms: feedback control, optimal control, and reinforcement learning. The shortcomings of the three methods in this scenario are summarized, and specific improvement measures are given by reviewing existing research. Also, it offers a thorough summary of the most recent developments and trends in this particular scientific field. [ABSTRACT FROM AUTHOR]