Szczegóły publikacji
Opis bibliograficzny
Reinforcement learning as a tool for coordinating and ensuring traffic safety in swarms of mobile robots / Agata NAWROCKA, Marcin NAWROCKI, Ignacy Chabowski, Andrzej KOT // W: 27th International Carpathian Control Conference (ICCC) [Dokument elektroniczny] : 1-3 June 2026, Szilvásvárad, Hungary : proceedings. — Wersja do Windows. — Dane tekstowe. — Piscataway : IEEE, cop. 2026. — Print on Demand(PoD) ISBN: 979-8-3195-3321-0. — e-ISBN: 979-8-3195-3320-3. — S. 306–310. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 309–310, Abstr. — Publikacja dostępna online od: 2026-07-07
Autorzy (4)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 169280 |
|---|---|
| Data dodania do BaDAP | 2026-09-11 |
| Tekst źródłowy | URL |
| DOI | 10.1109/ICCC71363.2026.11593333 |
| Rok publikacji | 2026 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
Abstract
The objective of this research was to develop a collision-free navigation algorithm for a homogeneous swarm of mobile robots using reinforcement learning. The main task was to design a control strategy allowing for the safe movement of robots within a swarm with an unknown initial configuration of agents and targets. The effectiveness of the algorithm was validated in simulation tests for swarms ranging in size from 2 to 32 robots. The results demonstrated high efficiency and versatility of the control system. Test scenarios involved reaching a random target, position exchange, and target collection. Satisfactory results were achieved in each scenario, with a collision-free navigation success rate of 90% across all swarm sizes.
