物联网学报 ›› 2020, Vol. 4 ›› Issue (3): 69-77.doi: 10.11959/j.issn.2096-3750.2020.00179

• 专题:智慧交通物联网 • 上一篇    下一篇

面向自动驾驶应用的车联多智能体信息融合协同决策机制研究

曹佳钰,冷甦鹏(),张科   

  1. 电子科技大学信息与通信工程学院,四川 成都 611731
  • 修回日期:2020-07-28 出版日期:2020-09-30 发布日期:2020-09-07
  • 作者简介:曹佳钰(1995- ),女,山西大同人,电子科技大学硕士生,主要研究方向为车联网和移动边缘计算|冷甦鹏(1973- ),男,四川资中人,电子科技大学教授、博士生导师,主要研究方向为物联网、车联网、新一代宽带无线网络、无线自组织网、智能交通信息系统的资源管理、介质访问控制、路由、组网与互联、智能算法理论及技术应用等|张科(1978- )男,重庆人,博士,电子科技大学讲师,主要研究方向为物联网、车联边缘计算与存储
  • 基金资助:
    四川省科技计划重点研发项目(2019YFG0520)

Multi-agent driven collaborative decision mechanism of information fusion for autonomous driving vehicles

Jiayu CAO,Supeng LENG(),Ke ZHANG   

  1. School of Information and Communication Engineering,University of Electronic Science and Technology of China,Chengdu 611731,China
  • Revised:2020-07-28 Online:2020-09-30 Published:2020-09-07
  • Supported by:
    The Key R&D Project of Sichuan Science and Technology Plan(2019YFG0520)

摘要:

自动驾驶车辆是智能交通系统的重要组成部分,自动驾驶应用需要在采集大量交通数据的基础上,实施信息处理与控制决策。由于交通信息的时空属性,即信息只在某一时间段内或某一区域内有效,独立车辆有限的信息感知范围严重制约了自动驾驶应用数据采集的有效性。车联多智能体协同决策为上述问题提供了可行的解决思路,提出了一种多维度感知信息融合机制,提升车载信息融合对自动驾驶任务的增益。在此基础上,设计了面向自动驾驶应用的智能分布式的决策算法,在最大化信息融合对自动驾驶任务增益的同时,最大化路网交通车流量,并满足自动驾驶车辆的成本和资源约束。仿真结果验证了所提算法的收敛性和实用性。

关键词: 自动驾驶, 多智能体, 信息融合, 移动边缘服务

Abstract:

Autonomous vehicles play an important part in intelligent transportation systems.In these vehicles,driving control decision is obtained based on the collection of massive traffic states and intensive information processing.However,the spatial-temporal characteristics of the traffic states and the constrained environmental perception range of an individual vehicle seriously undermine the effectiveness of the state collection.Multi-agent driven collaborative decision provides a potential approach to address the problem.A multi-dimensional information fusion mechanism was proposed,which improved the gain of vehicular information fusion for autonomous driving tasks.Moreover,an intelligent distributed decision algorithm was designed for autonomous driving applications,which maximized the road traffic flow while maximizing the gain of information fusion on the autonomous driving mission under vehicular cost and resource constraints.Numerical results demonstrate the convergence and practicability of the proposed algorithm.

Key words: autonomous driving, multi-agent, information fusion, mobile edge service

中图分类号: