无人驾驶汽车决策系统的规则正确性验证  

Correctness Verification of Rules for Unmanned Vehicles' Decision System

作　　者：刘斌斌[1] 刘万伟[2] 毛晓光[2] 董威[2] 

机构地区：[1]国防科学技术大学计算机学院,长沙410073 [2]国防科学技术大学计算机学院计算机科学与技术系,长沙410073

出　　处：《计算机科学》2017年第4期72-74,113,共4页Computer Science

基　　金：国家自然科学基金(60873120);国家重点基础研究发展规划(973)(2009CB723803)资助

摘　　要：无人驾驶车辆技术是当前科学研究的重点领域之一,目前无人车决策系统的开发过程中面临着安全性不足的问题。针对该问题,提出了验证驱动的基于代码自动生成的无人车决策系统开发框架。该框架利用模型检验技术对无人车决策系统进行环境建模,通过验证可以发现无人车决策系统的设计过程中不易发觉的缺陷,解决其安全性不足的问题,同时能够将安全检查与软件开发同步,降低其维护成本。基于该框架,设计并实现了无人车决策系统辅助开发工具UNMANNED_RULE_EDIT(URE),目前该工具已初步应用于国内某单位研制的无人车上,为其开发研制工作提供了帮助。The technology of unmanned vehicle is one of the key areas of current scientific research.However,the development of decision system is facing the problem of insufficient security.Aiming at this problem,this paper presented a solution framework of verification-driven unmanned vehicle＇s decision system based on automatic code generation.We introduced the technology of model checking to model the environment of unmanned vehicles.So this framework can find the defects that hide deeply during the designing process.With this method,the problem of insufficient security can be solved,which can also reduce the maintenance cost by synchronizing the process of software development with security checking.The tool named UNMANNED_RULE_EDIT（URE）was also implemented based on this framework.Now the tool has been tentatively used in an unmanned vehicle to support their work.

关 键 词：无人驾驶汽车 决策系统 模型检验 环境建模 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]