一句话：提出感知契约，用于刻画神经感知误差并保障基于视觉感知的控制系统安全。
论文提出感知契约（perception contracts）这一新概念，用于推理通过神经感知与环境交互的控制器的安全性。感知契约刻画 ground-truth 估计中的误差，使得系统在基于这些估计行动时仍能保持不变量。作者建立了感知契约理论，并设计了从有限图像集合中合成感知契约的符号学习算法。他们实现了该算法，并针对两个真实的视觉控制系统评估合成出的感知契约：一个电动汽车车道保持系统和一个沿作物行行进的农业机器人。评估表明，该方法能够有效合成感知契约，并且在系统运行时监测所获得的测试图像上具有良好的泛化能力。
We introduce a novel notion of perception contracts to reason about the safety of controllers that interact with an environment using neural perception. Perception contracts capture errors in ground-truth estimations that preserve invariants when systems act upon them. We develop a theory of perception contracts and design symbolic learning algorithms for synthesizing them from a finite set of images. We implement our algorithms and evaluate synthesized perception contracts for two realistic vision-based control systems, a lane tracking system for an electric vehicle and an agricultural robot that follows crop rows. Our evaluation shows that our approach is effective in synthesizing perception contracts and generalizes well when evaluated over test images obtained during runtime monitoring of the systems.
@article{paperbot1869,
title = {Perception Contracts for Safety of ML-Enabled Systems},
author = {Angello Astorga and Chiao Hsieh and P. Madhusudan and Sayan Mitra},
journal = {Proceedings of the ACM on Programming Languages},
volume = {7},
number = {OOPSLA2},
year = {2023},
doi = {10.1145/3622875}
}