一种基于车云协同的自动驾驶全局速度规划方法及系统

By using vehicle-cloud collaboration technology and combining global route gradient and historical vehicle speed data, the vehicle speed can be adjusted in real time, solving the problem of the inability to globally optimize fuel consumption and timeliness in commercial vehicle autonomous driving, and improving the economy and timeliness of global speed planning.

CN118850108BActive Publication Date: 2026-07-17DONGFENG COMML VEHICLE CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
DONGFENG COMML VEHICLE CO LTD
Filing Date
2024-06-28
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing speed planning methods for autonomous driving in commercial vehicles mainly focus on micro-control strategy planning for a specific driving segment and traffic conditions, and cannot achieve fuel consumption or time efficiency optimization for the entire driving route.

Method used

By using vehicle-cloud collaboration technology and combining the gradient of the global route to slice the data, the historical optimal speed data of vehicles is obtained. Combined with the global slice road information, the vehicle speed is adjusted in real time to optimize fuel consumption. With the instructions of the upstream behavior planning module, global speed planning is achieved.

Benefits of technology

Optimize fuel consumption from a holistic perspective to improve economy, ensure travel timeliness, and obtain the best driving experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118850108B_ABST
    Figure CN118850108B_ABST
Patent Text Reader

Abstract

一种基于车云协同的自动驾驶全局速度规划方法及系统,根据全局路线的坡度情况进行切片,以得到包括多段分片道路的全局切片道路信息,然后将在相同全局路线中行驶油耗表现最佳的相同的历史车辆的的历史最优车速数据结合全局切片道路信息可以得到每段分片道路对应最佳油耗的建议车速,然后实时获取当前车辆的所在位置,然后根据实时的位置得到此时所在的切片道路,按照此时所在的切片道路对应的建议车速进行行驶,从全局角度进行速度规划,以减少行驶完整个全局路线所需的油耗,提高经济性,解决了相关技术中存在的速度规划方式是针对某一行驶路段和某一交通路况进行微观上的控策规划,无法做到整个行驶路线的油耗或时效进行优化减少技术问题。
Need to check novelty before this filing date? Find Prior Art