Radar and camera information fusion sensing methods are used to solve the inherent shortcomings of the single sensor in severe weather. Our fusion scheme uses radar as the main hardware and camera as the auxiliary hardware framework. At the same time, the Mahalanobis distance is used to match the observed values of the target sequence. Data fusion based on the joint probability function method. Moreover, the algorithm was tested using actual sensor data collected from a vehicle, performing real-time environment perception. The test results show that radar and camera fusion algorithms perform better than single sensor environmental perception in severe weather, which can effectively reduce the missed detection rate of autonomous vehicle environment perception in severe weather. The fusion algorithm improves the robustness of the environment perception system and provides accurate environment perception information for the decision-making system and control system of autonomous vehicles.

The use of object detection algorithms has become extremely important in autonomous vehicles. Object detection at high accuracy and a fast inference speed is essential for safe autonomous driving. Therefore, the balance between the effectiveness and efficiency of the object detector must be considered. This article proposes a one-stage object detection framework for improving the detection accuracy while supporting a true real-time operation based on the YOLOv4. The backbone network in the proposed framework is the CSPDarknet53_dcn(P). The last output layer in the CSPDarknet53 is replaced with deformable convolution to improve the detection accuracy. In order to perform feature fusion, a new feature fusion module PAN++ is designed and five scales detection layers are used to improve the detection accuracy of small objects. In addition, this article proposes an optimized network pruning algorithm to solve the problem that the real-time performance of the algorithm cannot be satisfied due to the limited computing resources of the vehicle-mounted computing platform. The method of sparse scaling factor is used to improve the existing channel pruning algorithm. Compared to the YOLOv4, the YOLOV4-5D improves the mean average precision by 4.23% on the BDD data sets and 1.68% on the KITTI data sets. Finally, by pruning the model, the inference speed of YOLOV4-5D is increased 31.3% and the memory is only 98.1 MB when the detection accuracy is almost unchanged. Nevertheless, the proposed algorithm is capable of real-time detection at faster than 66 frames/s (fps) and shows higher accuracy than the previous approaches with a similar fps.

In recent years, considerable progress has been made in semantic segmentation of images with favorable environments. However, the environmental perception of autonomous driving under adverse weather conditions is still very challenging. In particular, the low visibility at nighttime greatly affects driving safety. In this paper, we aim to explore image segmentation in low-light scenarios, thereby expanding the application range of autonomous vehicles. The segmentation algorithms for road scenes based on deep learning are highly dependent on the volume of images with pixel-level annotations. Considering the scarcity of labeled large-scale nighttime data, we performed synthetic data collection and data style transfer using images acquired in daytime based on the autonomous driving simulation platform and generative adversarial network, respectively. In addition, we also proposed a novel nighttime segmentation framework (SFNET-N) to effectively recognize objects in dark environments, aiming at the boundary blurring caused by low semantic contrast in low-illumination images. Specifically, the framework comprises a light enhancement network which introduces semantic information for the first time and a segmentation network with strong feature extraction capability. Extensive experiments with Dark Zurich-test and Nighttime Driving-test datasets show the effectiveness of our method compared with existing state-of-the art approaches, with 56.9% and 57.4% mIoU (mean of category-wise intersection-over-union) respectively. Finally, we also performed real-vehicle verification of the proposed models in road scenes of Zhenjiang city with poor lighting. The datasets are available at https://github.com/pupu-chenyanyan/semantic-segmentation-on-nightime.

As self-driving vehicles become more prevalent, the speed and accuracy of detecting surrounding objects through onboard sensing technology have become increasingly important. The YOLOv8-QSD network is a novel anchor-free driving scene detection network that builds on YOLOv8 and ensures detection accuracy while maintaining efficiency. The network’s backbone employs structural reparameterization techniques to transform the Diverse Branch Block based model. To accurately detect small objects, it integrates features of different scales and implements a bifpn-based feature pyramid after the backbone. To address the challenge of long-range detection in driving scenarios, a query-based model with a new pipeline structure is introduced. The test results demonstrate that this algorithm outperforms YOLOv8 on the soda-a dataset in terms of both speed and accuracy. With an accuracy rate of 64.5% and reduced computational requirements of 7.1 GFLOPs, it satisfies the speed, precision, and cost-effectiveness requirements for commercial vehicles in high-speed road driving scenarios.

The electrical drive system is crucial to the drive performance and safety of electric vehicles (EVs). In contrast to the traditional two-wheel driven EVs, the hub motor four-wheel-drive system can steer the vehicle by controlling the torque and speed of each wheel independently, yielding a very simple distributed drivetrain with high efficiency and reliability. This paper presents a system-level design optimization method for a permanent magnet hub motor drive system for a campus patrol EV based on a practical driving cycle. An outer rotor permanent-magnet synchronous hub motor (PMSHM) and an improved model predicate current control are proposed for the drive system. Due to the lack of reducers, the direct-drive PMSHM needs to face more complex working conditions and design constraints. In the implementation, the motor design requirements are obtained through the collection of practical EV driving cycles in the campus. Based on these requirements, two models are proposed as the preliminary designs for the PMSHM. To improve their performance, an efficient multi-objective optimization method is employed to the motor considering different operational conditions. The finite-element model and thermal network model are employed to verify the performance of the optimized PMSHM. An optimal design scheme is selected by comparing the comprehensive performance of the two optimized motors. In addition, a duty-cycle model predictive current control is adopted to drive the motor. Finally, a prototype is developed and tested, and the experimental results are presented.

This paper investigates the efficient robust design optimization of a five-phase permanent magnet (PM) hub motor for electric vehicles. Besides the requirement of high-performance, like high torque density, low torque ripple and efficiency, fault-tolerant operation capability is also considered in the design optimization. To ensure that the motor performance is not sensitive to the variations of manufacturing tolerances, robust design optimization is employed to the investigated motor. To improve the fault tolerant capability of the motor, the motor performances under fault operation is also considered in the optimization. A Fuzzy-based sequential Taguchi robust optimization method is proposed to improve the comprehensive performance and save computing time. The proposed method is efficient because it holds the advantages of Taguchi method, fuzzy theory, and sequential optimization strategy. The motor performance is improved significantly by using the proposed method. Experimental results verify the accuracy of the model used in this study.