Scalable Remote Operation for Autonomous Vehicles: Integration of Cooperative Perception and Open Source Communication

As autonomous vehicles become increasingly preva-lent, robust remote operation systems are imperative to ensure safety and reliability in unpredictable scenarios. Current remote operation systems in research often lack scalability and adaptability, hindering their integration into diverse autonomous driving platforms. This paper addresses these challenges by introducing a scalable remote operation system that leverages cooperative perception and an open-source communication module. Field tests conducted with an SAE Level 3 autonomous shuttle have validated the effectiveness of our system in real-world scenarios. The code for a key component of this system, the communication module, is available online¹.

I. Introduction

The field of autonomous driving has made remarkable strides, with various companies, such as Waymo [1], Cruise [2] and others [3], [4], [5], pushing the boundaries of Autonomous Driving Systems (ADS). While the technical intricacies of these systems remain proprietary, a common thread is the reliance on human remote support. The dependence on human remote support in autonomous driving is primarily driven by the imperative of ensuring safety, allowing immediate human intervention for unpredictable scenarios and serving as a safety net to navigate complex situations on the road. This is particularly highlighted in the article [6], disclosing that Cruise requires remote assistance every four to five miles to maintain their operation of autonomous systems. In the pursuit of fully autonomous vehicles, the necessity of remote operation becomes evident for the mid to long-term future. The widespread deployment of autonomous driving requires developing scalable remote operation systems that can effectively manage an expanding fleet and maintain robust communication despite increasing complexity.