Interagent beliefs for learning to communicate in large-scale multirobot visual object search

Puc, Jernej (avtor), Škulj, Gašper (avtor), Pleterski, Jan (avtor), Podržaj, Primož (avtor), Vrabič, Rok (avtor)

We present Century Maze, a simulated environment for cooperative navigation of groups numbering over 100 robots with primarily visual observations. The underlying task of large-scale object search is designed to push the scalability and efficiency of decentralized multirobot systems relying on communication to overcome the limitations of separate units. To enable the training of robotic agents in large-scale visual embodied applications such as Century Maze, we propose two reinforcement learning (RL) components that facilitate the emergence of effective communication: Differentiable Interagent Belief Learning (DIABL), which provides a clear learning signal by optimizing the agents' beliefs about their goals and propagating gradients back over a differentiable communication channel to include the appropriate observers, and informative event replay (infer), which compensates for the scarcity of samples relevant to DIABL by maintaining a dedicated buffer for auxiliary learning. We demonstrate our combined method through an actor-critic neural network architecture encompassing a decentralized multiagent system of variable size with individual goal-based belief modules. Results on Century Maze show that our method is able to significantly improve performance through cooperation over 100 agents against comparable baselines and maintains its effectiveness in realistic conditions.

• Jezik: Angleški jezik
• Ključne besede: cooperating robots, multirobot systems, reinforcement learning, vision-based navigation
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FS - Fakulteta za strojništvo
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2026
• Št. strani: 20 str.
• Številčenje: Vol. 42
• PID: 20.500.12556/RUL-182457
• UDK: 007.52
• ISSN pri članku: 1941-0468
• DOI: 10.1109/TRO.2026.3677944
• COBISS.SI-ID: 277860355
• Datum objave v RUL: 12.05.2026

Gradivo je del revije

• Naslov: IEEE transactions on robotics
• Skrajšan naslov: IEEE trans. robot.
• Založnik: Institute of Electrical and Electronics Engineers
• ISSN: 1941-0468
• COBISS.SI-ID: 68843011

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: sodelujoči roboti, večrobotski sistemi, spodbujevalno učenje, vizualna navigacija