Akademik Veri Yönetim Sistemi
9th International Artificial Intelligence and Data Processing Symposium, IDAP 2025, Malatya, Türkiye, 6 - 07 Eylül 2025, (Tam Metin Bildiri)
Decentralized task allocation is a critical challenge in multi-robot systems, particularly in scenarios where autonomy, scalability, and robustness are essential. While centralized approaches simplify coordination, they suffer from limitations such as single points of failure and poor scalability in dynamic environments. This paper presents a comparative evaluation of three decentralized and distributed task allocation algorithms integrated into a blockchain-powered multi-robot system where Hyperledger Fabric is used as blockchain platform. Each algorithm employs a cost-based selection mechanism to assign tasks autonomously while leveraging a distributed ledger for data consistency and conflict resolution. The algorithms -Euclidean distance, TEB motion planner and every robot computing all robots' costs- are evaluated for a system of three TIAGo++ robots in two different simulation environments. Performance metrics include computational overhead and task request conflict rates. Results show that while Euclidean distance offers the lowest overhead, it suffers from high conflict rates; TEB motion planner improves fairness with moderate overhead; and every robot computing all robots' costs ensures the highest consistency at the cost of increased computation. The findings highlight key trade-offs in decentralized coordination and offer guidance for designing scalable and reliable blockchain-powered multi robot systems.