Management system and method for automatic-driving vehicle-mounted computing resources

Abstract

The invention discloses a management method for automatic-driving vehicle-mounted computing resources, and relates to the technical field of automatic driving. The management method includes the stepsthat hardware resources of a vehicle-mounted computing unit are uniformly managed with the container technology, and according to a real-time-collection data processing task and an automatic-drivingintelligent decision control task of a core sensor, physical hardware resources are dynamically distributed, and multiple container running environments mutually isolated are generated to independently execute the tasks of the container running environments; resources are dynamically adjusted according to the actual running condition, and intelligent cooperation of all automatic-driving business applications is achieved; multiple container management strategies are obtained through resource reservation, resource constraints and resource robbing, and safe driving of automatic-driving vehicles is completed. According to the management method, it is guaranteed that the execution environment of a computing task is isolated, the using rate of computing resources is increased, and hardware energy consumption is effectively reduced; compared with a single-host mode, risk brought by a single-host fault is reduced, and the whole safety of automatic driving is improved. The invention also provides a management system for the automatic-driving vehicle-mounted computing resources.

Description

technical field [0001] The present invention relates to the technical fields of edge computing, automatic driving and containers, and specifically relates to a system and method for managing computing resources on a vehicle for automatic driving. Background technique [0002] With the development of cloud computing, various application systems have gradually turned to the cloud. The cloud center aggregates a large number of physical hardware resources, such as servers, networks, memory and storage, etc., and uses virtualization technology to extract and transform them and present them in a unified manner. , realizing the unified allocation, scheduling and management of heterogeneous network computing resources, and the centralized construction of data centers greatly reduces the cost of computing and storage. As a resource management technology, virtualization technology effectively solves the problem of overcapacity and over-allocation of high-performance physical hardware ...

AI Technical Summary

Problems solved by technology

At the same time, limited by the volume and energy consumption requirements of the car, the on-board core computing unit cannot adopt the cloud center solution

Images