TY  - EJOU
AU  - Hou, Gang 
AU  - Liu, Aifeng 
AU  - Zhao, Tao 
AU  - Wei, Wenyuan 
AU  - Li, Bo 
AU  - Liu, Jiancheng 
AU  - Wei, Siwen 

TI  - Segment-Conditioned Latent-Intent Framework for Cooperative Multi-UAV Search
T2  - Computers, Materials \& Continua

PY  - 2026
VL  - 87
IS  - 1
SN  - 1546-2226

AB  - Cooperative multi-UAV search requires jointly optimizing wide-area coverage, rapid target discovery, and endurance under sensing and motion constraints. Resolving this coupling enables scalable coordination with high data efficiency and mission reliability. We formulate this problem as a discounted Markov decision process on an occupancy grid with a cellwise Bayesian belief update, yielding a Markov state that couples agent poses with a probabilistic target field. On this belief–MDP we introduce a segment-conditioned latent-intent framework, in which a discrete intent head selects a latent skill every <i>K</i> steps and an intra-segment GRU policy generates per-step control conditioned on the fixed intent; both components are trained end-to-end with proximal updates under a centralized critic. On the <mml:math id="mml-ieqn-1"><mml:mn>50</mml:mn><mml:mo>×</mml:mo><mml:mn>50</mml:mn></mml:math> grid, coverage and discovery convergence times are reduced by up to 48% and 40% relative to a flat actor-critic benchmark, and the aggregated convergence metric improves by about 12% compared with a state-of-the-art hierarchical method. Qualitative analyses further reveal stable spatial sectorization, low path overlap, and fuel-aware patrolling, indicating that segment-conditioned latent intents provide an effective and scalable mechanism for coordinated multi-UAV search.
KW  - Multi-agent reinforcement learning; Markov decision process; multi-UAV cooperative search

DO  - 10.32604/cmc.2026.073202