What is it about?
PerceptiSync helps people trust the information shared between self-driving cars and similar systems by combining human judgment with artificial intelligence. The framework looks at how humans and AI can work together to check whether an object is detected correctly, so that mistakes or false alarms are caught early. By bringing in human feedback, PerceptiSync makes it easier for people to feel confident in the decisions made by smart vehicles and other connected systems.
Featured Image
Photo by Remy Gieling on Unsplash
Why is it important?
This work is important because as self-driving cars and smart systems become more common, people need to trust what these systems see and decide. PerceptiSync is one of the first frameworks to combine human feedback with artificial intelligence to improve that trust in real time. Its ability to adapt trust levels based on user input makes it a unique and timely solution for safer and more reliable connected vehicles and other advanced technologies.
Perspectives
From my perspective, PerceptiSync represents a step toward more human-centered AI, where trust is not only measured statistically but shaped by people’s ongoing perceptions and input. As connected autonomous systems become more common, I believe frameworks like PerceptiSync will be crucial to bridging the gap between technical performance and human confidence. It has been rewarding to explore how trust can adapt over time through human involvement, and I hope this work sparks further research in trustworthy AI for cyber-physical systems.
Matthew Wilchek
Virginia Polytechnic Institute and State University
Read the Original
This page is a summary of: PerceptiSync: Trustworthy Object Detection using Crowds-in-the-Loop for Cyber-Physical Systems, ACM Transactions on Cyber-Physical Systems, July 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3746644.
You can read the full text:
Contributors
The following have contributed to this page
