20.500.12556/RUL-178107 Večagentno načrtovanje poti za skupino avtomatsko vodenih vozičkov v industrijskem okolju s polnilnicami Multi-agent path planning for a fleet of automated guided vehicles in industrial setting with charging stations V članku je predstavljen pristop, ki omogoča učinkovito načrtovanje poti za več agentov. Okolje je opisano z grafom, ki predstavlja omrežje cest in križišč za vozila različnih oblik in hitrosti. Načrtovanje temelji na algoritmu za načrtovanje poti z varnimi intervali, prioritetami in varnimi mesti, kar omogoča vseživljenjsko delovanje. Algoritem je kompleten in daje skoraj optimalne poti, ki so časovno in prostorsko zvezne. Algoritem smo dopolnili z ocenjevanjem energije baterije, kar omogoča iskanje le izvedljivih planov. Z dopolnitvijo algoritma za implicitno iskanje plana do optimalnega cilja iz nabora ciljev pa lahko dosežemo izbiro varnega mesta ali polnilnice že med načrtovanjem poti. Predlagani pristop je praktično uporaben v raznovrstnih realnih industrijskih scenarijih pri nalogah razvažanja materiala znotraj industrijskega okolja, pri čemer upoštevamo, da morajo agenti med izvajanjem nalog po potrebi tudi v polnilnice. Analizirali smo tudi računsko učinkovitost algoritma glede na število vozil in velikost zemljevida. Rezultati kažejo, da je predstavljeni pristop računsko učinkovit tudi pri velikem številu vozil in v primeru velikih zemljevidov. The paper presents an approach that enables efficient multi-agent path planning. The environment is described by a graph that represents a network of roads and crossroads for vehicles of different shapes and velocities. The multi-agent pathfinding approach is based on a safe interval path planning algorithm with priorities and safe locations, which together allow for lifelong operation. The algorithm is complete and it produces near-optimal plans that are continuous in time and space. We have extended the algorithm with battery energy estimation, which allows finding only feasible plans. Since we also added an option that implicitly selects an optimal goal in a set of goals, we can achieve selection of a safe location or charging station already during planning. The proposed approach is practically applicable in a wide variety of realistic industrial scenarios for material handling within industrial setting, where charging of the agents during execution of the tasks is also considered. We also analysed the computational efficiency of the algorithm with respect to the number of vehicles and the size of the map. The results show that the presented approach is computationally efficient even in the case of a large number of vehicles and large maps. načrtovanje poti večagentni sistemi avtomatsko vodeni vozički industrijska logistika grafi varni intervali varna mesta polnilnice prioritete path planning multi-agent systems automated guided vehicles industrial logistics graphs safe intervals safe locations charging stations priorities true false true Slovenski jezik Angleški jezik Članek v reviji 2026-01-19 10:03:11 2026-01-19 10:03:17 2026-01-21 13:42:43 0000-00-00 00:00:00 2025 0 0 Str. 216-225 št. 4 Letn. 31 avg. 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 681.5 1318-7279 265175043 zdesar-09-2025.pdf zdesar-09-2025.pdf 1 368534DC89AC576D4DCE36CF13CDD418 aed61204167b6f41f5caedc1a45ff86c3b83ffe2636a5b7af95d96d08105b74d c389a5d3-f515-11f0-bf92-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=225655 https://revija-ventil.si/wp-content/uploads/zdesar-09-2025.pdf 1 a3d5577e-f515-11f0-bf92-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=225653 Fakulteta za strojništvo Fakulteta za elektrotehniko 0 0 0