《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (8): 2533-2540.DOI: 10.11772/j.issn.1001-9081.2025070804

• 先进计算 • 上一篇    下一篇

分层自适应隐式分位数的多智能体路径规划

薛婧颖1,2, 况立群1,2,3(), 王智巽1,2,3, 郭正涛1,2,3, 韩慧妍1,2,3   

  1. 1.中北大学 计算机科学与技术学院,太原 030051
    2.机器视觉与虚拟现实山西省重点实验室(中北大学),太原 030051
    3.山西省视觉信息处理及智能机器人工程研究中心,太原 030051
  • 收稿日期:2025-07-21 修回日期:2025-09-30 接受日期:2025-10-14 发布日期:2025-11-05 出版日期:2026-08-10
  • 通讯作者: 况立群
  • 作者简介:薛婧颖(2001—),女,山西运城人,硕士研究生,主要研究方向:强化学习、路径规划
    况立群(1976—),男,江西高安人,教授,博士,CCF会员,主要研究方向:人工智能、计算机视觉
    王智巽(2002—),男,山西太原人,硕士研究生,主要研究方向:人工智能、计算机视觉
    郭正涛(2000—),男,山西长治人,硕士研究生,主要研究方向:人工智能、计算机视觉
    韩慧妍(1980—),女,山西临汾人,副教授,博士,CCF会员,主要研究方向:人工智能、计算机视觉。
  • 基金资助:
    山西省科技重大专项(202201150401021);山西省自然科学基金资助项目(202303021211153);山西省科技成果转化引导专项(202104021301055)

Multi-agent path planning with hierarchical adaptive implicit quantiles

Jingying XUE1,2, Liqun KUANG1,2,3(), Zhixun WANG1,2,3, Zhengtao GUO1,2,3, Huiyan HAN1,2,3   

  1. 1.College of Computer Science and Technology,North University of China,Taiyuan Shanxi 030051,China
    2.Shanxi Key Laboratory of Machine Vision and Virtual Reality (North University of China),Taiyuan Shanxi 030051,China
    3.Shanxi Vision Information Processing and Intelligent Robot Engineering Research Center,Taiyuan Shanxi 030051,China
  • Received:2025-07-21 Revised:2025-09-30 Accepted:2025-10-14 Online:2025-11-05 Published:2026-08-10
  • Contact: Liqun KUANG
  • About author:XUE Jingying, born in 2001, M. S. candidate. Her research interests include reinforcement learning, path planning.
    WANG Zhixun, born in 2002, M. S. candidate. His research interests include artificial intelligence, computer vision.
    GUO Zhengtao, born in 2000, M. S. candidate. His research interests include artificial intelligence, computer vision.
    HAN Huiyan, born in 1980, Ph. D., associate professor. Her research interests include artificial intelligence, computer vision.
  • Supported by:
    Shanxi Provincial Major Science and Technology Program(202201150401021);Shanxi Natural Science Foundation(202303021211153);Shanxi Science and Technology Achievement Transformation Guiding Program(202104021301055)

摘要:

针对虚拟现实(VR)场景中的多目标路径规划实时性不足与局部冲突协调不足的问题,提出一种分层自适应隐式分位数的多智能体路径规划算法。首先,引入高低层策略协同优化实现全局规划与局部执行的统一,并基于隐式分位数网络进行价值分布的建模;其中,高层策略生成兼顾环境全局分布与目标位置的子目标,而低层策略根据子目标实时感知局部环境动态;其次,通过自适应条件风险价值(CVaR)机制动态调整决策;最后,为了引导智能体快速且稳定地到达目标点,设计一种目标流畅奖励函数,以优化策略反馈结构。实验结果表明,所提算法在智能体数为3,目标数为5、10、15、20的情况下,较次优算法adaptive_IQN (Adaptive Implicit Quantile Network)分别提升了2、3、3和4个百分点,从而优化了路径规划效率,能够增强VR场景中多用户交互的流畅度与沉浸感。

关键词: 路径规划, 虚拟现实场景, 多智能体, 分层策略, 奖励机制

Abstract:

To address limitations of real-time and local conflict coordination for multi-objective path planning in Virtual Reality (VR) scenes, a multi?agent path planning algorithm based on hierarchical adaptive implicit quantile was proposed. First, collaborative optimization of high- and low-level strategies was introduced to unify global planning and local execution, and an implicit quantile network was employed for value distribution modeling. The high-level strategy was used to generate sub-goals considering both global environmental distribution and target positions, while the low-level strategy was used to perceive local environmental dynamics according to sub-goals in real time. Then, an adaptive Conditional Value at Risk (CVaR) mechanism was used to dynamically adjust decisions. Finally, a goal-smooth reward function was designed to guide agents toward rapid and stable target achievement by optimizing feedback structure of the strategy. Experimental results show that the proposed algorithm outperforms the suboptimal algorithm, adaptive_IQN (Adaptive Implicit Quantile Network), by 2, 3, 3, and 4 percentage points under scenarios with 3 agents and 5, 10, 15, and 20 targets, respectively, optimizing path planning efficiency and enhancing fluency and immersion of multi-user interactions in VR scenes.

Key words: path planning, Virtual Reality (VR) scene, multi-agent, hierarchical strategy, reward mechanism

中图分类号: