{"id":"W6907073358","doi":"10.20944/preprints202503.0300.v1","title":"Deep Reinforcement Learning Based Coverage Path Planning in Unknown Environments","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sherbrooke O.E.M (Canada); Université de Sherbrooke","funders":"","keywords":"Motion planning; Adaptability; Redundancy (engineering); Path (computing); Robot; Smoothing; Reinforcement learning","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001487383,0.00063983,0.000707009,0.0005415533,0.0001888554,0.0001115664,0.00267849,0.0004797635,0.0001002416],"category_scores_gemma":[0.0004085114,0.0007429001,0.0002085405,0.0003759504,0.00006411703,0.0002568306,0.006010653,0.002299587,0.0004880119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007104084,"about_ca_system_score_gemma":0.000389719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001754885,"about_ca_topic_score_gemma":0.000001250743,"domain_scores_codex":[0.9949676,0.0004571378,0.0009659927,0.00190684,0.0008653504,0.0008370868],"domain_scores_gemma":[0.9966384,0.0002981558,0.0005697209,0.002250396,0.00003973095,0.0002036349],"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":[0.00001203939,0.00007756817,0.2331366,0.0001141201,0.00004303682,0.0001702989,0.001199341,0.7639927,0.0001209961,0.0001656491,0.00001090544,0.000956799],"study_design_scores_gemma":[0.0007365884,0.00002903501,0.1191621,0.001099837,0.00001978344,0.000003609656,0.0000199252,0.873863,0.001544199,0.0004203638,0.00248268,0.0006187595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03018402,0.0001766456,0.9555336,0.000193786,0.001189857,0.0007920299,0.000002299765,0.0003568419,0.01157096],"genre_scores_gemma":[0.9712135,0.00006294571,0.02392475,0.0003869378,0.00008298656,0.0002622067,0.00009886204,0.00003472358,0.003933075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9410295,"threshold_uncertainty_score":0.9995022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06671034790712617,"score_gpt":0.3140584236215285,"score_spread":0.2473480757144023,"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."}}