基于D3QN的目标驱动移动机器人自主导航方法
DOI:
CSTR:
作者:
作者单位:

新疆大学机械工程学院 乌鲁木齐 830017

作者简介:

通讯作者:

中图分类号:

TP242.6;TN711

基金项目:

新疆维吾尔自治区自然科学基金(2022D01C392)、国家自然科学基金(62063033)、新疆维吾尔自治区重点研发计划项目(2022B01050-2)资助


D3QN-based target-driven autonomous navigation for mobile robots
Author:
Affiliation:

School of Mechanical Engineering, Xinjiang University,Urumqi 830017, China

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:

    在未知或危险环境中(如应急救灾、抢险救援),传统导航方法因无法预先获得先验地图和位置信息,难以实现特定目标的导航。本文提出了一种基于竞争双深度Q网络(D3QN)的目标驱动移动机器人自主导航方法。该方法的跨模态融合模块对不同模态特征动态加权融合,在整合观测数据的同时充分捕捉环境信息,增强了对环境的感知能力。在此基础上,设计了一种通用的目标驱动导航方法,使用YOLOv5识别特定目标(如火焰、烟雾)并获取其位置,用识别出的目标位置替代深度强化学习导航中的预设位置点,实现自主导航至特定目标。仿真实验结果表明,本文方法在导航成功率等指标上具有显著优势,在简单、复杂和动态场景中,成功率分别提高了9%、27%和38%。此外,在简单仿真环境中训练的模型,能够直接部署在复杂的仿真环境和真实场景中,表现出良好的泛化能力。

    Abstract:

    In unknown or hazardous environments (such as emergency rescue and disaster relief), traditional navigation methods struggle to achieve specific target navigation due to the inability to obtain prior maps and location information. This paper proposes a target-driven autonomous navigation method for mobile robots based on dueling double deep Q network (D3QN). The cross-modal fusion module of this method dynamically weights and integrates features from different modalities, effectively consolidating observational data while fully capturing environmental information. This significantly enhances the capability to perceive the environment.Building on this, a general target-driven navigation approach is designed, where YOLOv5 is used to recognize specific targets (such as flames or smoke) and obtain their locations. The identified target locations are used to replace predefined waypoints in deep reinforcement learning-based navigation, enabling autonomous navigation to specific targets. Simulation results show that the proposed method has significant advantages in the navigation success rate and other indicators. In simple, complex, and dynamic scenarios, the success rates increased by 9%, 27%, and 38%, respectively. Moreover, the model trained in a simple simulation environment can be directly deployed in more complex simulation environments and real-world scenarios, exhibiting strong generalization capability.

    参考文献
    相似文献
    引证文献
引用本文

卢赵清,王宏伟,何丽,司盼召,陈耀华.基于D3QN的目标驱动移动机器人自主导航方法[J].电子测量技术,2025,48(9):9-18

复制
相关视频

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:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2025-05-23
  • 出版日期:
文章二维码