Purpose

Autonomous driving depends on the collection, processing and analysis of environmental information and vehicle information. Environmental perception and processing are important prerequisite for the safety of self-driving of vehicles; it involves road boundary detection, vehicle detection, pedestrian detection using sensors such as laser rangefinder, video camera, vehicle borne radar, etc.

Design/methodology/approach

Subjected to various environmental factors, the data clock information is often out of sync because of different data acquisition frequency, which leads to the difficulty in data fusion. In this study, according to practical requirements, a multi-sensor environmental perception collaborative method was first proposed; then, based on the principle of target priority, large-scale priority, moving target priority and difference priority, a multi-sensor data fusion optimization algorithm based on convolutional neural network was proposed.

Findings

The average unload scheduling delay of the algorithm for test data before and after optimization under different network transmission rates. It can be seen that with the improvement of network transmission rate and processing capacity, the unload scheduling delay decreased after optimization and the performance of the test results is the closest to the optimal solution indicating the excellent performance of the optimization algorithm and its adaptivity to different environments.

Originality/value

In this paper, the results showed that the proposed method significantly improved the redundancy and fault tolerance of the system thus ensuring fast and correct decision-making during driving.

中文翻译：

---

自动驾驶汽车环境感知技术的协同处理和数据优化

目的

自动驾驶取决于环境信息和车辆信息的收集，处理和分析。环境感知和处理是确保车辆自动驾驶安全的重要前提；它涉及道路边界检测，车辆检测，使用激光测距仪，摄像机，车载雷达等传感器的行人检测。

设计/方法/方法

受各种环境因素的影响，由于数据采集频率的不同，数据时钟信息常常不同步，导致数据融合困难。本研究根据实际需要，首先提出了一种多传感器环境感知协同方法。然后，基于目标优先级，大规模优先级，移动目标优先级和差分优先级的原理，提出了一种基于卷积神经网络的多传感器数据融合优化算法。

发现

不同网络传输速率下优化前后测试数据算法的平均卸载调度延迟。可以看出，随着网络传输速率和处理能力的提高，优化后的卸载调度时延减小，测试结果的性能最接近最优解，表明优化算法的优越性能及其对不同算法的适应性。环境。

创意/价值

结果表明，该方法大大提高了系统的冗余性和容错性，从而确保了驾驶过程中快速，正确的决策。