面向校园复杂环境的无人驾驶场景库生成方法  

Generation method of unmanned driving scenario library for complex campus environment

作　　者：向巍 吴绍斌[2,3] 林绪泽 闫泽新 张明 XIANG Wei;WU Shaobin;LIN Xuze;YAN Zexin;ZHANG Ming(Department of Automotive Engineering,Guizhou Communications Polytechnic,Guiyang Guizhou 550008,China;School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081,China;Beijing Institute of Technology of Zhengzhou Academy of Intelligent Technology,Zhengzhou Henan 450046,China;HanKaiSi Intelligent Technology Co.,Ltd.,Guiyang Guizhou 550008,China)

机构地区：[1]贵州交通职业技术大学汽车系,贵州贵阳550008 [2]北京理工大学机械与车辆学院,北京100081 [3]北理工郑州智能科技研究院,河南郑州450046 [4]翰凯斯智能技术有限公司,贵州贵阳550008

出　　处：《中国安全科学学报》2024年第7期170-177,共8页China Safety Science Journal

基　　金：贵州省交通运输厅科技项目(2022-121-012)。

摘　　要：为加快无人驾驶系统测试的速度和效率,提出校园环境无人驾驶场景库的生成方法。首先,将校园道路场景简化为路网结构、地面属性、交互成员、环境因素的组合,分析校园复杂环境的仿真测试场景;其次,针对测试场景库局限性较强的问题,提出基于重要性指标的场景库生成方法;然后,采用复杂度指标和兴趣概率指标描述场景重要性指标,应用模糊层次分析法(FAHP)评估场景复杂度,并结合核密度估计方法和感兴趣权重计算场景兴趣概率;再次,分割参数空间获取相似场景集合,并按照测试优先度和重要性指标对场景集合排序,逐步添加筛选出的场景到测试场景库中,生成带有测试序列的场景库;最后,在基于真实环境下的校园环境道路数据生成的测试场景库中进行测试评价,验证场景库生成方法的有效性。结果表明:采用4种场景要素和树形结构能够有效描述校园测试场景,基于重要性指标的校园场景库生成方法能够生成高测试效率、高覆盖度、吻合自然概率及兴趣区间的校园测试场景库,能够提高校园复杂环境无人驾驶仿真测试的效率。In order to accelerate the speed and efficiency of autonomous systems testing,the method of generating a scene database for unmanned driving in campus environments was proposed.Firstly,the simulation test scenarios in complex campus environment were analyzed,and the campus scenes were simplified as a combination of road network structure,ground properties,interacting members and environmental factors.Secondly,the method of generating the scene database based on importance indicators was proposed to solve the boundedness of the campus scenario database.Then,the complexity indicators and interest probability indicators were used to describe the importance indicators of scenarios.The fuzzy analytic hierarchy process(FAHP)was used to evaluate the complexity of the scenario.The interest probability of the scenario was calculated by combining the kernel density estimation method and the interested weight calculation method.Next,the parameter space was segmented to obtain the set of similar scenarios,and the scenario sets were sorted according to test priority and importance indicators.The filtered scenarios were gradually added to the test scenario database,and the scenario database with test sequences was generated.Finally,the test evaluations based on the real-world campus scenario database were conducted to verify the effectiveness of the scenario database generation method proposed in this paper.The results show that the campus test scenes can be effectively described using four scene elements and the tree structure.The method proposed in this paper can generate a campus test scene library with high test efficiency,high coverage,conformity to natural probability,and interest interval,which is helpful to improve the efficiency of unmanned simulation test in complex campus environment.

关 键 词：校园复杂环境 无人驾驶 场景库生成 场景模型 重要性指标 

分 类 号：X951[环境科学与工程—安全科学] U463[机械工程—车辆工程]