7 papers
Statistical-Symbolic Verification of Perception-Based Autonomous Systems using State-Dependent Conformal Prediction
Yuang Geng, Thomas Waite, Trevor Turnquist +2
Reachability analysis has been a prominent way to provide safety guarantees for neurally controlled autonomous systems, but its direct application to neural perception components i…
MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection
Yuang Geng, Junkai Zhou, Kang Yang +5
In this paper, we address the challenging problem of single-scene, fully unsupervised video anomaly detection (VAD), where raw videos containing both normal and abnormal events are…
Deterministic World Models for Closed-loop Reachability Analysis of End-to-End Vision-based Control
Yuang Geng, Zhuoyang Zhou, Zhongzheng Zhang +6
End-to-end image controllers that map raw camera frames directly to control actions are increasingly deployed in safety-critical systems. However, formally verifying their closed-l…
Four Principles for Physically Interpretable World Models
Jordan Peper, Zhenjiang Mao, Yuang Geng +2
As autonomous systems are increasingly deployed in open and uncertain settings, there is a growing need for trustworthy world models that can reliably predict future high-dimension…
State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification of Autonomous Systems
Thomas Waite, Yuang Geng, Trevor Turnquist +2
It remains a challenge to provide safety guarantees for autonomous systems with neural perception and control. A typical approach obtains symbolic bounds on perception error (e.g.,…
Zero-shot Safety Prediction for Autonomous Robots with Foundation World Models
Zhenjiang Mao, Siqi Dai, Yuang Geng +1
A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems. However, the existing world models re…