DOI QR코드

DOI QR Code

A Time-Based Efficient Global Path Generation Method for Multiple Maneuvering Platforms in Ground MUM-T Operations

지상 MUM-T 운용을 위한 다수 기동 플랫폼의 시간 기반 효율적 광역 경로 생성 기법

  • Received : 2026.02.02
  • Accepted : 2026.06.30
  • Published : 2026.08.05

Abstract

This paper proposes a time-based efficient global path generation method for multiple ground maneuvering platforms operating under a manned-unmanned teaming(MUM-T) framework. Using road-network information, the proposed method simultaneously generates (i) global routes connecting each platform's start and target positions and (ii) corresponding time schedules for each route segment. By explicitly modeling the space-time occupancy of road segments during the search process, the proposed approach prevents simultaneous usage of the same road segments and produces collision-free trajectories. As a result, multiple platforms can reach their destinations while minimizing overall mission time and alleviating bottlenecks in constrained road networks. The effectiveness of the proposed algorithm is validated through simulation experiments conducted on a virtual two-dimensional map of a military training area located in Pocheon, Gangwon-do, Republic of Korea. The simulation results demonstrate that the proposed method successfully resolves conflicts caused by concurrent road usage and dynamically adapts to changes in mission conditions. The proposed technique is expected to serve as a core enabling technology for future ground MUM-T operations and next-generation battlefield combat systems.

Keywords

Acknowledgement

본 논문은 지상 기동 무기체계의 유무인 복합운용(MUM-T) 기술 고도화를 목표로 수행된 연구의 일환이다. 향후 연구에서는 AI 기반 이종 플랫폼 상태 예측 기법과 학습기반 경로계획 기법을 결합하여, 지상 기동체계 MUM-T 환경에서의 임무 성공률을 향상시킬 수 있는 광역 경로생성 기술로 확장할 예정이다.

References

  1. S. J. Yoon and M. W. Won, "A Method for Creating Global Routes for Unmanned Ground Vehicles Using Open Data Road Section Data," Journal of the Korea Institute of Military Science and Technology, Vol. 26, No. 1, pp. 31-43, 2023. https://doi.org/10.9766/KIMST.2023.26.1.031
  2. R. Stern, N. R. Sturtevant, A. Felner, S. Koenig, H. Ma, T. T. Walker, J. Li, D. Atzmon, L. Cohen, T. K. S. Kumar, R. Barták and E. Boyarski, "MultiAgent Pathfinding: Definitions, Variants, and Benchmarks," Proceedings of the Twelfth International Symposium on Combinatorial Search (SoCS), Vol. 10, pp. 151-159, 2019.
  3. K. S. Yakovlev, "Planning and Learning in MultiAgent Path Finding," Doklady Mathematics, 2022.
  4. N. AbuJabal, T. Rabie, M. Almazrouei, et al., "Path  Planning Techniques for Real-Time Multi-Robot Systems: A Systematic Review," Electronics, Vol. 13, No. 12, pp. 2239, 2024. https://doi.org/10.3390/electronics13122239
  5. A. Andreychuk, K. Yakovlev, P. Surynek, D. Atzmon and R. Stern, "Multi-agent pathfinding with continuous time," Artificial Intelligence, Vol. 305, Article 103662, 2022. https://doi.org/10.1016/j.artint.2022.103662
  6. M. Phillips and M. Likhachev, "SIPP: Safe Interval Path Planning for Dynamic Environments," Proc. IEEE International Conference on Robotics and Automation(ICRA), pp. 5628-5635, 2011.
  7. A. Andreychuk, K. Yakovlev, E. Boyarski and R. Stern, "Improving Continuous-time Conflict-Based Search," Proc. AAAI Conference on Artificial Intelligence, 2021.
  8. J. Gao, Q. Liu, S. Chen, K. Yan, X. Li and Y. Li, "Multi-Agent Path Finding with Time Windows: Preliminary Results," Proc. International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023), pp. 2586-2588, 2023.
  9. S. Song, K.-I. Na and W. Yu, "Anytime Lifelong Multi-Agent Pathfinding in Topological Maps," IEEE Access, Vol. 11, pp. 20365-20380, 2023. https://doi.org/10.1109/ACCESS.2023.3249471
  10. H. Jiang, Y. Zhang, R. Veerapaneni and J. Li, "Scaling Lifelong Multi-Agent Path Finding to More Realistic Settings: Research Challenges and Opportunities," Proceedings of the International Symposium on Combinatorial Search(SoCS), Vol. 17, pp. 234-242, 2024.
  11. M. Tang, R. Xin, C. Fang, Y. Li, H. Liu and J. Wu, "GPU-accelerated Conflict-based Search for Multi-agent Embodied Intelligence," Machine Intelligence Research, Vol. 22, No. 4, pp. 641-654, 2025. https://doi.org/10.1007/s11633-025-1568-y
  12. A. Skrynnik, A. Andreychuk, M. Nesterova, K. Yakovlev and A. Panov, "Learn to Follow: Decentralized Lifelong Multi-Agent Pathfinding via Planning and Learning," Proc. AAAI Conference on Artificial Intelligence, Vol. 38, No. 16, pp. 17541-17549, 2024.