Zhuyi: Perception Processing Rate Estimation for Safety in Autonomous Vehicles
This addresses safety and efficiency issues for autonomous vehicles by optimizing resource use, though it is incremental as it builds on existing perception systems.
The paper tackles the problem of autonomous vehicles' perception processing exceeding computational resources, proposing Zhuyi to estimate the minimum safe frame processing rate, which reduces processing to 36% or fewer frames compared to a default system while maintaining safety.
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.