一句话：提出可解释自适应 XSA 愿景，并为机器人场景中成功或失败的自适应生成人类可理解的解释。
论文关注依赖机器学习黑盒模型进行决策的自适应系统：在不确定与未知环境中，自适应决策及其影响缺乏透明度，失败的自适应难以追溯到可理解的根因。作者提出“可解释自适应”（XSA）愿景，并在机器人领域的运行示例上实例化该愿景，设计自动化概念验证流程，为关键场景中成功与失败的自适应生成人类可理解的解释。评估以概念验证和示例演示为主，展示该流程能够解释自适应结果，但尚未报告大规模实证或用户研究。
Self-adaptive systems increasingly rely on machine learning techniques as black-box models to make decisions even when the target world of interest includes uncertainty and unknowns. Because of the lack of transparency, adaptation decisions, as well as their effect on the world, are hard to explain. This often hinders the ability to trace unsuccessful adaptations back to understandable root causes. In this paper, we introduce our vision of explainable self-adaptation. We demonstrate our vision by instantiating our ideas on a running example in the robotics domain and by showing an automated proof-of-concept process providing human-understandable explanations for successful and unsuccessful adaptations in critical scenarios.
DOI 原文 ·
@inproceedings{paperbot7196,
title = {XSA: eXplainable Self-Adaptation},
author = {Matteo Camilli and Raffaela Mirandola and Patrizia Scandurra},
booktitle = {ASE},
year = {2022},
doi = {10.1145/3551349.3559552}
}