野外高自适应性多机器人协同实时制图系统

唐洁; 杨迪; 蒋凯; 刘少山

doi:10.12382/bgxb.2025.0655

您当前的位置：

首页 >

文章列表页 >

野外高自适应性多机器人协同实时制图系统

更新时间：2026-02-11

- 野外高自适应性多机器人协同实时制图系统
- Field-Adaptive Multi-Robot Collaborative Real-Time Mapping System
- 兵工学报 2026年
- 作者机构：
  
  1. 华南理工大学计算机学院,广东,广州,510006
  2. 深圳市人工智能与机器人研究院,广东,深圳,518172
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目（62372188）;国家重点研发计划项目（2023YFE0202700）
- DOI：10.12382/bgxb.2025.0655
  中图分类号： TJ301
- 收稿：2025-07-16，
  
  网络首发：2026-02-11，
- 稿件说明：
移动端阅览
唐洁，杨迪，蒋凯，等. 野外高自适应性多机器人协同实时制图系统[J/OL]. 兵工学报, 2026(2026-02-11). https://doi.org/10.12382/bgxb.2025.0655.

TANG J, YANG D, JIANG K, et al. Field-adaptive multi-robot collaborative real-time mapping system[J/OL]. Acta Armamentarii, 2026(2026-02-11). https://doi.org/10.12382/bgxb.2025.0655. (in Chinese)
唐洁，杨迪，蒋凯，等. 野外高自适应性多机器人协同实时制图系统[J/OL]. 兵工学报, 2026(2026-02-11). https://doi.org/10.12382/bgxb.2025.0655. DOI：

TANG J, YANG D, JIANG K, et al. Field-adaptive multi-robot collaborative real-time mapping system[J/OL]. Acta Armamentarii, 2026(2026-02-11). https://doi.org/10.12382/bgxb.2025.0655. (in Chinese) DOI：

摘要

在复杂多变、非结构化的野外战场环境中，实现多无人系统协同建图是支撑智能作战单元任务执行、态势感知与安全保障的关键能力。针对现有系统在环境动态性强、通信受限、平台异构、地图融合效率低等挑战，提出一种面向战术任务的高自适应多机器人协同实时制图系统。该系统围绕战场通信资源稀缺与跨平台感知协同需求，设计了轻量化的数据压缩与高效消息传输机制，实现低带宽条件下异构平台间位姿与观测信息的高效同步。针对地图一致性问题，引入冗余感知驱动的回环检测策略以触发协同地图融合，并结合控制参数驱动的截断最小二乘优化模型与渐进非凸性求解方法，有效抑制异常回环干扰。系统还支持按需调用的全局光束法平差优化模块，显著提升地图精度与稳定性。实验结果表明：该系统可在野外数平方公里作战区域内，仅依赖间歇性低带宽链路，即可实现厘米级相对定位精度与全局地图一致性；在地图数据压缩50%以上的条件下，定位误差平均仅增加5.7mm，显著增强了无人集群在复杂环境下的自主作业与协同感知能力，为智能化战场感知体系建设提供了关键技术支撑。

Abstract

In complex and unstructured battlefield environments

collaborative mapping among unmanned systems is vital for mission execution

situational awareness

and operational safety.Afield-adaptive multi-robot collaborative real-time mapping systemis presentedto meet the demands of tactical operations under low-bandwidth

high-dynamics

and heterogeneous platform constraints. The system features lightweight data compression and efficient cross-platform message passing to enable real-time pose and observation synchronization under intermittent communications. A redundancy-aware loop closure strategy drives inter-robot map fusion

while a truncated least squares model with graduated non-convex optimization suppresses loop-induced errors. An on-demand global bundle adjustment further improves map accuracy. Field testsshow the system maintains centimeter-level relative localization and global map consistency over multi-square-kilometer areas

with only a 5.7 mm average error increase under 50% map data compression. These results demonstrate the system’s potential as a core sensing infrastructure for autonomous unmanned swarms in future intelligent combat systems.

关键词

Keywords

references

CSORBA M. Simultaneous localisation and map building[D]. Oxford, UK: University of Oxford, 1997.

HAHNEL D, BURGARD W, FOX D, et al. An eﬀicient FastSLAM algorithm for generating maps of large-scale cyclic environments from raw laser range measurements[C]// Proceedings 2003 IEEE/RSJ international conference on intelligent robots and systems (IROS 2003). Piscataway, NJ, US: IEEE, 2003: 206-211.

KLEIN G, MURRAY D. Parallel tracking and mapping for small AR workspaces[C]//Proceedings of the 2007 6th IEEE and ACM international symposium on mixed and augmented reality. Piscataway, NJ, US: IEEE, 2007: 225-234.

MUR-ARTAL R, MONTIEL J M M, TARDOS J D. ORB-SLAM: a versatile and accurate monocular SLAM system[J]. IEEE transactions on robotics, 2015, 31(5): 1147-1163.

MUR-ARTAL R, TARDS J D. Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEE transactions on robotics, 2017, 33(5): 1255-1262.

CAMPOS C, ELVIRA R, RODRÍGUEZ J J G, et al. Orb-slam3: an accurate open-source library for visual, visual–inertial, and multimap slam[J]. IEEE Transactions on Robotics, 2021, 37(6): 1874-1890.

QIN T, LI P L, SHEN S J. Vins-mono: a robust and versatile monocular visual-inertial state estimator[J]. IEEE Transactions on Robotics, 2018, 34(4): 1004-1020.

BESCOS B, FÁCIL J M, CIVERA J, et al. DynaSLAM: Tracking, mapping, and inpainting in dynamic scenes[J]. IEEE Robotics and Automation Letters, 2018, 3(4): 4076-4083.

LIU Y B, MIURA J. RDS-SLAM: real-time dynamic SLAM using semantic segmentation methods[J]. IEEE Access, 2021, 9:23772-23785.

SONG S, LIM H, LEE A J, et al. DynaVINS: a visual-inertial slam for dynamic environments[J]. IEEE Robotics and Automation Letters, 2022, 7(4): 11523-11530.

CHAKRAA H, GUÉRIN F, LECLERCQ E, et al. Optimization techniques for multi-robot task allocation problems: review on the state-of-the-art [J]. Robotics and Autonomous Systems, 2023, 168: 104492.

XU H, LIU P Z, CHEN X Y, et al. D2SLAM: decentralized and distributed collaborative visual-inertial SLAM system for aerial swarm[J]. IEEE Transactions on Robotics, 2022, 40: 3445-3464.

ZHOU Y, QUANG L, NIETO-GRANDA C, et al. CoPeD-advancing multi-robot collaborative perception: a comprehensive dataset in real-world environments[J]. IEEE Robotics and Automation Letters, 2024, 9(7): 6416-6423.

LIU D, WU J Y, DU Y, et al. SBC-SLAM: semantic bioinspired collaborative SLAM for large-scale environment perception of heterogeneous systems[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 1-10.

ZHANG T, PENG F Y, TANG X W, et al. CME-EPC: a coarse-mechanism embedded error prediction and compensation framework for robot multi-condition tasks[J]. Robotics and Computer-Integrated Manufacturing, 2024, 86: 102675.

LAJOIE P Y, RAMTOULA B, CHANG Y, et al. DOOR-SLAM: distributed, online, and outlier resilient SLAM for robotic teams [J]. IEEE Robotics and Automation Letters, 2020, 5(2): 1656-1663.

TIAN Y L, CHANG Y, ARIAS F H, et al. Kimera-multi: Robust, distributed, dense metric-semantic slam for multi-robot systems[J]. IEEE Transactions on Robotics, 2022, 38(4): 2022-2038.

MANGELSON J G, DOMINIC D, EUSTICE R M, et al. Pairwise consistent measurement set maximization for robust multi-robot map merging[C]//Proceedings of 2018 IEEE international conference on robotics and automation . Piscataway, NJ, US: IEEE, 2018: 2916-2923.

PATEL M, KARRER M, BÄNNINGER P, et al. COVINS-G: a generic back-end for collaborative visual-inertial slam[C]//Proceedings of 2023 IEEE International Conference on Robotics and Automation. Piscataway, NJ, US: IEEE, 2023: 2076-2082.

KARRER M, SCHMUCK P, CHLI M. CVI-SLAM—collaborative visual-inertial SLAM[J]. IEEE Robotics and Automation Letters, 2018, 3(4): 2762-2769.

刘鑫, 王忠, 秦明星. 多机器人协同SLAM技术研究进展[J]. 计算机工程, 2022, 48(5): 1-10.

LIU X, WANG Z, QIN M X. Research progress of multi-robot collaborative SLAM technology[J]. Computer Engineering, 2022, 48(5): 1-10. (in Chinese)

王曦杨, 陈炜峰, 尚光涛, 等. 基于多机器人的协同VSLAM综述[J]. 南京信息工程大学学报, 2024, 16(6): 846-869.

WANG X Y, CHEN W F, SHANG G T, et al. A survey on cooperative visual SLAM for multi-robot systems[J]. Journal of Nanjing University of Information Science and Technology, 2024,16(6): 846-869. (In Chinese)

CHANG Y, EBADI K, DENNISTON C E, et al. LAMP 2.0: a robust multi-robot SLAM system for operation in challenging large-scale underground environments[J]. IEEE Robotics and Automation Letters, 2022, 7(4):9175-9182.

GRANT W S, VOORHIES R. cereal - A C++11 library for serialization[EB/OL]. 2013[2024-04-09]. http://uscilab.github.io/cereal/.

BLACK M J, RANGARAJAN A. On the unification of line processes, outlier rejection, and robust statistics with applications in early vision[J]. International journal of computer vision, 1996, 19(1): 57-91.

YANG H, ANTONANTE P, TZOUMAS V, et al. Graduated non-convexity for robust spatial perception: from non-minimal solvers to global outlier rejection[J]. IEEE Robotics and Automation Letters, 2020, 5(2): 1127-1134.

DELLAERT F, CONTRIBUTORS G. borglab/GTSAM[CP/OL]. Atlanta, GA, US: Georgia Tech Borg Lab, 2023(2023-09-04)[2024-04-09]. https://github.com/borglab/gtsam.

BURRI M, NIKOLIC J, GOHL P, et al. The EuRoC micro aerial vehicle datasets[J]. The International Journal of Robotics Re-search, 2016, 35(10):1157-1163.

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据