Zhuyi: Perception Processing Rate Estimation for Safety in Autonomous Vehicles

TL;DR

Zhuyi is a model that estimates the minimum safe perception processing rate in autonomous vehicles, enabling safety checks and resource prioritization to maintain safety with reduced processing load.

Contribution

The paper introduces Zhuyi, a novel sensor frame processing rate estimation model for autonomous vehicles to ensure safety under resource constraints.

Findings

Zhuyi's estimates are conservative, ensuring safety.

The system can operate safely with 36% fewer frames processed.

It effectively prioritizes perception tasks to maintain safety.

Abstract

The processing requirement of autonomous vehicles (AVs) for high-accuracy perception in complex scenarios can exceed the resources offered by the in-vehicle computer, degrading safety and comfort. This paper proposes a sensor frame processing rate (FPR) estimation model, Zhuyi, that quantifies the minimum safe FPR continuously in a driving scenario. Zhuyi can be employed post-deployment as an online safety check and to prioritize work. Experiments conducted using a multi-camera state-of-the-art industry AV system show that Zhuyi's estimated FPRs are conservative, yet the system can maintain safety by processing only 36% or fewer frames compared to a default 30-FPR system in the tested scenarios.