融合COLREGs的水上交通场景认知建模  

Cognitive modeling of waterborne traffic scenario incorporating COLREGs

作　　者：文元桥[1,2,3] 程小东 黄亮[1,2,3] 黄亚敏[1,2] 徐顺强 钟书彬 WEN Yuanqiao;CHENG Xiaodong;HUANG Liang;HUANG Yamin;XU Shunqiang;ZHONG Shubin(State Key Laboratory of Maritime Technology and Safety(Wuhan University of Technology),Wuhan 430063,China;National Engineering Research Center for Water Transport Safety(Wuhan University of Technology),Wuhan 430063,China;Sanya Science and Education Innovation Park,Wuhan University of Technology,Sanya 572000,Hainan,China)

机构地区：[1]水路交通控制全国重点实验室(武汉理工大学),武汉430063 [2]国家水运安全工程技术研究中心(武汉理工大学),武汉430063 [3]武汉理工大学三亚科教创新园,海南三亚572000

出　　处：《哈尔滨工业大学学报》2024年第11期151-161,共11页Journal of Harbin Institute of Technology

基　　金：三亚市科技创新专项(2022KJCX36);国家自然科学基金面上项目(52072287)。

摘　　要：为实现国际海上避碰规则(COLREGs)场景的语义表达与推理,让船舶具备类人的水上交通场景理解与推理能力,提出一种融合COLREGs的场景认知计算建模方法。基于COLREGs水上交通场景的语义描述,将水上交通场景解析为时间、对象、属性、关系、行为、事件等要素相互作用的综合体,构建水上交通场景的概念模型;采用本体建模实现COLREGs场景概念模型的结构化表达;通过定义语义计算操作函数和触发集搭建COLREGs场景认知计算框架,进而提出一种基于逻辑推理的场景认知计算方法。选取厦门港环境和船舶AIS数据,在场景语义抽取的基础上对COLREGs场景认知模型进行案例验证,结果表明:相对于数据驱动的方法,所提模型能够对场景中的对象属性、船舶行为、事件等进行描述和语义计算,并能更好地支持场景中各类要素相关知识的获取与查询。研究提出的场景认知建模方法对于船舶实现规则约束下的场景自主认知具有可行性和有效性。To achieve semantic expression and reasoning of scenarios under the International Regulations for Preventing Collisions at Sea(COLREGs),enabling ships to understand and reason about waterborne traffic scenarios similarly to humans,a scenario cognition computing modeling method incorporating COLREGs is proposed.Based on the semantic description of waterborne traffic scenarios under COLREGs,this approach parses the scenarios into a comprehensive system of interactions among elements such as time,objects,attributes,relations,behaviors,and events,thereby constructing a conceptual model of waterborne traffic scenarios.It employs ontological modeling to structure the expression of the COLREGs scenario conceptual model.Through defining semantic computational operation functions and trigger sets,a COLREGs scenario cognition computing framework is established,leading to the proposal of a logic reasoning-based scenario cognition computing method.The model is validated with case studies using the environment of Xiamen Port and ship AIS data based on semantic extraction from scenarios.The results shows that,compared to data-driven model,the proposed model can describe and computationally process object attributes,ship behaviors,and traffic events in scenarios,and support the acquisition and querying of related knowledge of various elements within the scenario.The proposed scenario cognition modeling method is feasible and effective for enabling autonomous scenario cognition of ships under rule constraints.

关 键 词：水路运输 COLREGS 水上交通场景 知识建模 知识表达 本体 

分 类 号：U675[交通运输工程—船舶及航道工程]