基于贝叶斯网络构建RoboSim模型的自动驾驶行为决策方法
作者:
作者单位:

作者简介:

通讯作者:

杜德慧,E-mail:dhdu@sei.ecnu.edu.cn

中图分类号:

TP311

基金项目:

国家自然科学基金(61972153);科技部重点项目(2020AAA0107800)


Autonomous Driving Behavior Decision-Making Approach with RoboSim Model Based on Bayesian Network
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为汽车自动驾驶提供安全高效的自动驾驶行为决策, 是汽车自动驾驶领域面临的挑战性问题之一.目前, 随着自动驾驶行业的蓬勃发展, 工业界与学术界提出了诸多自动驾驶行为决策方法, 但由于汽车自动驾驶行为决策受环境不确定因素的影响, 决策本身也要求实效性及高安全性, 现有的行为决策方法难以完全支撑这些要素.针对以上问题, 本文提出了一种基于贝叶斯网络构建RoboSim模型的自动驾驶行为决策方法.首先, 基于领域本体分析自动驾驶场景元素之间的语义关系, 并结合LSTM模型预测场景中动态实体的意图, 进而为构建贝叶斯网络提供驾驶场景理解信息; 然后, 通过贝叶斯网络推理特定场景的自动驾驶行为决策, 并使用RoboSim模型的状态迁移承载行为决策的动态执行过程, 以减少贝叶斯网络推理的冗余操作, 提高了决策生成的效率.RoboSim模型具有平台无关、能模拟仿真执行周期的特点, 并支持多种形式化的验证技术.为确保行为决策的安全性, 本文使用模型检测工具UPPAAL对RoboSim模型进行验证分析.最后, 结合变道超车场景案例, 进一步证实本文所提方法的可行性, 为设计安全、高效的自动驾驶行为决策提供了一种可行的途径.

    Abstract:

    Providing safe, reliable, and efficient decisions is a challenging issue in the field of autonomous driving. At present, with the vigorous development of the autonomous driving industry, various behavioral decision-making methods are proposed. However, the decision of autonomous driving behavior is influenced by uncertainties in the environment, and the decision itself also requires effectiveness and high security, current methods are difficult to completely cover these issues. Therefore, we propose an autonomous driving decision-making approach with RoboSim model based on the Bayesian network. Semantic relationship information in driving scenarios is modeled by domain ontology, and an LSTM model for intention prediction of dynamic entities in scenarios is combined to provide driving scenario information for Bayesian networks. Using the decisions inferred by the Bayesian network, we abstract a specific RoboSim model for autonomous driving behavior decision-making, which is platform-independent, and it can simulate decision-making simulation execution cycle. In addition, the RoboSim model also can be transformed into other formal verification models, and in this paper, we use the model checking tool UPPAAL for verification and analysis to ensure the safety of the decision-making model. Combined with the case of lane change overtaking scenario, the feasibility of Bayesian network and RoboSim model construction method for autonomous driving behavior decision making is illustrated, which lays a foundation for providing a safe and efficient autonomous driving decision-making approach.

    参考文献
    相似文献
    引证文献
引用本文

陈洁娜,张铭茁,杜德慧,李博,聂基辉,任婧瑶.基于贝叶斯网络构建RoboSim模型的自动驾驶行为决策方法.软件学报,,():0

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-09-05
  • 最后修改日期:2021-10-14
  • 录用日期:
  • 在线发布日期: 2022-01-28
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号