{"id":"W4399182933","doi":"10.3390/drones8060226","title":"UAV Multi-Dynamic Target Interception: A Hybrid Intelligent Method Using Deep Reinforcement Learning and Fuzzy Logic","year":2024,"lang":"en","type":"article","venue":"Drones","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Concordia University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Process (computing); Controller (irrigation); Fuzzy logic; Control engineering; Machine learning; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005630582,0.00019787,0.0002030794,0.0002048001,0.0001557961,0.0003234592,0.0003210886,0.00004898507,0.00002945569],"category_scores_gemma":[0.00005441452,0.0001792015,0.00006258427,0.0002441719,0.00004700746,0.0003436555,0.000382747,0.0002818535,0.0001036539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001323699,"about_ca_system_score_gemma":0.00003880973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003269309,"about_ca_topic_score_gemma":9.024236e-7,"domain_scores_codex":[0.998512,0.0001317846,0.0002866044,0.0005199619,0.0002224914,0.0003271702],"domain_scores_gemma":[0.9994488,0.0001180713,0.0000636687,0.0002313967,0.00004064836,0.00009735003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007960104,0.00004806312,0.0004141981,0.0002639802,0.0001215827,0.000474318,0.008059671,0.7985349,0.003649874,0.004084845,0.00006895199,0.1842716],"study_design_scores_gemma":[0.00009758244,0.00008506016,0.0001252438,0.0001554881,0.00001452896,0.0002551758,0.0001955452,0.9964059,0.0003418683,0.001342656,0.0007653389,0.0002156427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002357643,0.001840636,0.9940181,0.0002650706,0.0008371344,0.000150536,5.042998e-7,0.0003557436,0.0001746437],"genre_scores_gemma":[0.2260632,0.00006770862,0.7730922,0.0000846401,0.00005622361,0.00001040925,0.000007669181,0.0000154692,0.0006024761],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2237055,"threshold_uncertainty_score":0.7307624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03822006424078118,"score_gpt":0.337876574272333,"score_spread":0.2996565100315519,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}