交通信息与安全2026，Vol.44Issue(1)：26-36,11.DOI:10.3963/j.jssn.1674-4861.2026.01.003
基于可解释机器学习的自动驾驶ODD拓展优先级量化评估方法
A Quantitative Prioritization Assessment Method for Autonomous Vehicle ODD Extension Based on Interpretable Machine Learning
摘要
Abstract
To solve the path ambiguity and decision subjectivity in operational design domain(ODD)extension,a crash data-driven quantitative prioritization assessment framework is investigated.Data support and decision bases for safety capability iterations of autonomous driving systems in complex environments are provided by this frame-work.To address the long-tail distribution defect of severe crash samples,random forest and extreme gradient boost-ing(XGBoost)classification models are constructed.The synthetic minority over-sampling technique(SMOTE)is introduced to optimize the sample distribution.The dataset is rebalanced at a 1:20 classification weight ratio to en-sure the identification capability for critical minority samples like severe crashes.To break the"black box"limita-tion of traditional models,the Shapley additive explanations(SHAP)method is employed to deconstruct internal de-cision-making mechanisms.Furthermore,the nonlinear effect thresholds of environmental feature variables on crash severity are quantified.A marginal effect model for ODD extension is established based on the control variates meth-od and principal component analysis(PCA).By simulating the boundary expansion of a single ODD variable,the improvement in theoretical crash coverage under various extension strategies is calculated.The results indicate that the identification performance of classification models for critical severe crash samples is significantly enhanced af-ter SMOTE processing.While an 83.4%overall accuracy is maintained,the sensitivity of the random forest model is increased from 17.8%to 90.5%.The area under the receiver operating characteristic(ROC)curve(AUC)is in-creased to 0.922,and high-risk features are captured more precisely.The highest marginal safety benefit among can-didate dimensions is yielded by extending to unstructured road grades,as revealed by quantitative data.Theoretical coverage of ordinary and severe crashes is significantly increased by 15.7%and 13.0%,respectively,when expand-ing ODD from structured highways to state and county roads.Vehicle collision rates under emergency braking in ex-tended scenarios like low road friction and low illumination are verified by CARLA simulation experiments.It is ob-served that collision rates are increased from 5.0%in the baseline group to 45.0%and 20.0%,respectively.Mean-while,the average time to collision(TTC)is shortened by 1.3 seconds.The physical safety performance degradation trend is highly consistent with the high-risk feature ranking derived from the quantitative assessment model.It is proven by these quantitative indicators that the priority ODD extension direction with the greatest safety value is re-liably identified by the proposed framework.关键词
自动驾驶/设计运行范围/量化评估模型/可解释机器学习/事故数据/随机森林/XGBoost/SHAPKey words
autonomous driving/operational design domain/quantitative assessment model/interpretable machine learning/crash data/random forest/XGBoost/SHAP分类
交通工程引用本文复制引用
李烨,黄启俊,金杰灵,田珊,李继朴..基于可解释机器学习的自动驾驶ODD拓展优先级量化评估方法[J].交通信息与安全,2026,44(1):26-36,11.基金项目
国家重点研发计划项目(2023YFB2504700)、国家自然科学基金面上项目(52472371)资助 （2023YFB2504700）
