Taxonomy and Survey on Remote Human Input Systems for Driving Automation Systems

Abstract

Corner cases for driving automation systems can often be detected by the system itself and subsequently resolved by remote humans. There exists a wide variety of approaches on how remote humans can resolve such issues. Over multiple domains, no common taxonomy on those approaches has developed yet. As the scaling of automated driving systems continues to increase, a uniform taxonomy is desirable to improve communication within the scientific community, but also beyond to policymakers and the general public. In this paper, we provide a survey on recent terminologies and propose a taxonomy for remote human input systems, classifying the different approaches based on their complexity.

Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models

“…However, in such complex environments as road traffic, AVs will not be able to operate without failures in the foreseeable future. Remote assistance [9] allows remote operators to resolve situations, where AVs face problems they cannot resolve on their own by granting a remote operator access to the vehicle's state and sensor data [17]. Depending on the specific situation and the implementation of the remote assistance, the remote operators can either provide the vehicle information that enable it to continue the operation, or take over manual control.…”