1. [Publications](/publications)
2. Zhuyi: Perception Processing Rate Estimation for Safety in Autonomous Vehicles
 
 # Zhuyi: Perception Processing Rate Estimation for Safety in Autonomous Vehicles

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 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.



 ## Authors



Yu-Shun Hsiao ( Harvard University)

[Siva Hari](/person/siva-hari)

Michał Filipiuk (NVIDIA)

Timothy Tsai (NVIDIA)

[Michael B. Sullivan](/person/mike-sullivan)

Vijay Janapa Reddi (Harvard University)

Vasu Singh (NVIDIA)

[Steve Keckler](/person/stephen-keckler)

 

 

 ## Publication Date



Friday, May 6, 2022

 

 ## Published in



[arXiv](https://arxiv.org/abs/2205.03347)

 

 ## Research Area



[Autonomous Vehicles](/research-area/autonomous-vehicles)

[Computer Architecture](/research-area/computer-architecture)

[Resilience and Safety](/research-area/resilience)