无人驾驶车辆控制方法、装置、计算机设备和存储介质
By collecting ambient sound and images from behind the vehicle, a discrimination model is used to identify special vehicles and control the unmanned vehicle to pull over, solving the problem of low accuracy in identifying special vehicles by unmanned vehicles and achieving automatic coordination and high accuracy.
CN116653928BActive Publication Date: 2026-07-17GUANGZHOU WERIDE TECH LTD CO
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGZHOU WERIDE TECH LTD CO
- Filing Date
- 2023-06-30
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing autonomous vehicles have low accuracy in identifying special vehicles, making it difficult to make correct decisions when faced with such vehicles.
Method used
By collecting ambient sound and images behind the vehicle, a discrimination model is used to obtain the first and second judgment results, respectively. The confidence level is then combined to determine whether the parking trigger condition is met, and if the condition is met, the driverless vehicle is controlled to pull over to the side of the road.
Benefits of technology
It enables autonomous vehicles to automatically coordinate with special vehicles in the absence of an unmanned cabin, improving judgment accuracy, reducing false parking logic, and enhancing adaptability in complex traffic environments.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116653928B_ABST
Abstract
本申请提供了一种无人驾驶车辆控制方法、装置、计算机设备和存储介质，该方法包括：采集环境声音和车辆后方图像；基于环境声音，得到第一判定结果；基于车辆后方图像，得到第二判定结果；根据第一判定结果和第二判定结果，判断是否满足停车触发条件；停车触发条件包括第一判定结果反映检测到警笛声、第二判定结果反映检测到特种车辆跟随，且第一判定结果和第二判定结果的置信度均大于对应的置信度阈值；在满足停车触发条件的情况下，控制无人驾驶车辆进行靠边停车。该方法在无人驾驶车辆的运行过程中可在主驾驶仓无人的前提下实现对特种车辆的自动配合，且判断准确性高，减少无人驾驶车辆误停车逻辑的出现，提高了无人驾驶车辆的适应能力。
Need to check novelty before this filing date? Find Prior Art