Proactive Coordination in Multi-Agent Systems: The Adaptive Negotiation Consensus Algorithm (ANCA)
Kata Kunci:
Multi-Agent Systems,, Task Allocation, Conflict Resolution, Consensus AlgorithmAbstrak
Multi-Agent Systems (MAS) are a cornerstone of modern logistics automation, yet their effectiveness is often hindered by decoupled approaches to two critical problems: task allocation and conflict resolution. This separation can lead to inefficiency, congestion, and deadlocks in dynamic environments. This research addresses this challenge by developing a decentralized framework that integrates both processes simultaneously. We propose the Adaptive Negotiation Consensus Algorithm (ANCA), a hybrid algorithm that models coordination as a process of achieving consensus on an integrated "Action-Plan," which encompasses the task, path, and schedule. ANCA utilizes a multi-factor auction mechanism that proactively accounts for estimated conflict costs within its bid calculation, enabling agents to make collectively intelligent decisions. Simulation-based evaluations in a virtual warehouse environment with 20 AGVs demonstrate that ANCA significantly outperforms standard approaches. It successfully reduced the average task completion time by 25%, increased system throughput by 28%, and suppressed deadlock incidents by 95% compared to conventional Contract Net-based protocols. This research demonstrates that modeling coordination as a consensus on an integrated action is an effective and robust paradigm, offering a promising solution for developing more efficient, scalable, and reliable autonomous systems in logistics and manufacturing.
Referensi
Axak, N., Korablyov, M., & Ushakov, M. (2021). The Development of a Multi-Agent System for Controlling an Autonomous Robot. CEUR Workshop Proceedings, 3013, 96–105.
Braquet, M., & Bakolas, E. (2021). Greedy Decentralized Auction-based Task Allocation for Multi-Agent Systems. IFAC-PapersOnLine, 54(20), 675–680. https://doi.org/10.1016/j.ifacol.2021.11.249
Gerrits, B., Mes, M., & Schuur, P. (2019). A simulation model for the planning and control of AGVs at automated container terminals. Proceedings - Winter Simulation Conference, 2018-Decem(i), 2941–2952. https://doi.org/10.1109/WSC.2018.8632529
Kapitan, R., Veretilnyk, T., & Demyanenko, V. (2017). Development of a Multi-Agent Collision Resolution System At the Supply of Spare Parts and Components To the Production Equipment of Industrial Enterprises. EUREKA: Physics and Engineering, 6(6), 27–34. https://doi.org/10.21303/2461-4262.2017.00505
Karagoz, C. S., Bozma, H. I., & Koditschek, D. E. (2014). Coordinated navigation of multiple independent disk-shaped robots. IEEE Trans. Robot., 30(6), 1289–1304. https://doi.org/10.1109/TRO.2014.2337571
Kato, T., & Kamoshida, R. (2020). Multi-agent simulation environment for logistics warehouse design based on self-contained agents. Applied Sciences (Switzerland), 10(21), 1–20. https://doi.org/10.3390/app10217552
Liu, W., Chen, D., & Guo, J. (2018). Goal-Capability-Commitment based Mediation for Multi-Agent Collaboration. Proceedings of the 2018 IEEE 22nd International Conference on Computer Supported Cooperative Work in Design, CSCWD 2018, 353–358. https://doi.org/10.1109/CSCWD.2018.8465204
Liu, Y., Ji, S., Su, Z., & Guo, D. (2019). Multi-objective AGV scheduling in an automatic sorting system of an unmanned (intelligent) warehouse by using two adaptive genetic algorithms and a multi-adaptive genetic algorithm. PLoS ONE, 14(12), 1–21. https://doi.org/10.1371/journal.pone.0226161
Liyun, X., Ning, W., & Xufeng, L. (2021). Study on Conflict-free AGVs Path Planning Strategy for Workshop Material Distribution Systems. Procedia CIRP, 104, 1071–1076. https://doi.org/10.1016/j.procir.2021.11.180
Michael Wooldridge. (2009). An Introduction to Multiagent Systems Second Edition (2nd ed.). John Wiley & Sons Ltd.
Osmond, A. B., & Supangkat, S. H. (2019). Platform dan Pemodelan Kerjasama Multi Agen untuk Layanan Pengiriman Barang. Jurnal Sistem Cerdas, 2(1), 22–34. https://doi.org/10.37396/jsc.v2i1.15
Pamosoaji, A. K. (2019). Perencanaan Rute dan Kecepatan AGV pada Sistem Pergudangan Menggunakan Algoritma Ant Colony Optimization. SAINTEK: Jurnal Ilmiah Sains Dan Teknologi Industri, 3(2), 52. https://doi.org/10.32524/saintek.v3i2.595
Pandian, Dr. A. P. (2019). Artificial Intelligence Application in Smart Warehousing Environment for Automated Logistics. Journal of Artificial Intelligence and Capsule Networks, 2019(2), 63–72. https://doi.org/10.36548/jaicn.2019.2.002
Rashidah Mohamad, N., Hafidz Fazli Md Fauadi, M., Azni Jafa, F., Zaki Mohamed Noor, A., & Hisham Nordin, M. (2018). Simulation-Based Multi-Objective Optimization for Distributed Material Transportation System. International Journal of Engineering & Technology, 7(3.20), 92. https://doi.org/10.14419/ijet.v7i3.34.18987
Ribas-Xirgo, L., & Chaile, I. F. (2013). Multi-agent-based controller architecture for AGV systems. IEEE International Conference on Emerging Technologies and Factory Automation, ETFA, 0–3. https://doi.org/10.1109/ETFA.2013.6648084
Wilson, K. (2016). AGENT-BASED SOFTWARE ARCHITECTURE FOR DECISION MAKING IN THE DATA WAREHOUSE. http://www.journal
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Proceedings International Conference on Aligning Sustainability with Vocational Innovations (ICASVI)
Artikel ini berlisensi Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
