Study on State-of-the-art Cloud Services Integration Capabilities with Autonomous Ground Vehicles

TL;DR

This study evaluates the integration of leading cloud services with autonomous ground vehicles, highlighting their capabilities, limitations, and the need for clear separation of computing tasks for effective real-time operation.

Contribution

It provides a qualitative analysis of top cloud providers' applicability to AGV architectures, emphasizing performance and manageability considerations.

Findings

Cloud services can support generalized AGV architectures.

Significant latency issues hinder real-time AGV operations.

Clear separation of primary and secondary computing is necessary.

Abstract

Computing and intelligence are substantial requirements for the accurate performance of autonomous ground vehicles (AGVs). In this context, the use of cloud services in addition to onboard computers enhances computing and intelligence capabilities of AGVs. In addition, the vast amount of data processed in a cloud system contributes to overall performance and capabilities of the onboard system. This research study entails a qualitative analysis to gather insights on the applicability of the leading cloud service providers in AGV operations. These services include Google Cloud, Microsoft Azure, Amazon AWS, and IBM Cloud. The study begins with a brief review of AGV technical requirements that are necessary to determine the rationale for identifying the most suitable cloud service. The qualitative analysis studies and addresses the applicability of the cloud service over the proposed generalized AGV's architecture integration, performance, and manageability. Our findings conclude that a generalized AGV architecture can be supported by state-of-the-art cloud service, but there should be a clear line of separation between the primary and secondary computing needs. Moreover, our results show significant lags while using cloud services and preventing their use in real-time AGV operation.