{"id":"W4413391615","doi":"10.1115/omae2025-157355","title":"Reinforcement Learning-Based Controller With NMPC-Assisted Training for Autonomous Surface Vessels","year":2025,"lang":"en","type":"article","venue":"","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Memorial University of Newfoundland","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Training (meteorology); Engineering; Structural engineering; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006307202,0.0004717449,0.0003799381,0.0001996187,0.0002154963,0.0003726824,0.0005839727,0.0004285607,0.00111289],"category_scores_gemma":[0.001973562,0.0002047104,0.0002331163,0.0001155058,0.0004795975,0.0003159362,0.0005147725,0.0007801169,0.0002209181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003819031,"about_ca_system_score_gemma":0.0007556479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006022246,"about_ca_topic_score_gemma":0.004103275,"domain_scores_codex":[0.9997295,0.00006015191,0.00001446369,0.00006373128,0.00009111028,0.00004115927],"domain_scores_gemma":[0.9991805,0.0004106504,0.0001027259,0.00007912009,0.0001935648,0.00003350897],"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":[0.0001280953,0.0001143129,0.0007516948,0.00007175237,0.00002512069,0.00007376765,0.00008153592,0.9182259,0.01040275,0.001864851,0.000665657,0.06759451],"study_design_scores_gemma":[0.000005335346,0.00004951715,0.0001142534,0.000002938727,0.000002717261,0.000005350959,0.000002442133,0.9979436,0.001429204,0.0002133035,0.000228774,0.00000269875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.078326,0.0002196893,0.9156374,0.0001797377,0.00006933074,0.00007799466,0.00001836907,0.001294721,0.004176839],"genre_scores_gemma":[0.9701863,0.00003963859,0.02868497,0.00004884524,0.000009888783,0.00004725857,0.00001893553,0.00002124598,0.0009429867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006022246,"threshold_uncertainty_score":0.01197439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04035054245181818,"score_gpt":0.3587430588473915,"score_spread":0.3183925163955734,"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."}}