{"id":"W4319766298","doi":"10.1016/j.trc.2023.104049","title":"Framework for Connected and Automated Bus Rapid Transit with Sectionalized Speed Guidance based on deep reinforcement learning: Field test in Sejong City","year":2023,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Traffic control and management","field":"Engineering","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Ministry of Land, Infrastructure and Transport","keywords":"Bus rapid transit; Transport engineering; Intelligent transportation system; Reinforcement learning; Computer science; Field (mathematics); Engineering; Efficient energy use; Real-time computing; Automotive engineering; Public transport; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0005027277,0.0001666119,0.0002057499,0.0006109957,0.0001662596,0.00003460394,0.000146202,0.0001462902,0.00003725829],"category_scores_gemma":[0.0003549467,0.0001570841,0.00003563472,0.001221666,0.00007933209,0.00007548404,0.000005763567,0.0004536102,0.000003500223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005052107,"about_ca_system_score_gemma":0.00002049545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004441563,"about_ca_topic_score_gemma":0.0005302088,"domain_scores_codex":[0.9985825,0.00002688577,0.0002856911,0.0002940144,0.0003524928,0.0004583658],"domain_scores_gemma":[0.998681,0.0009558256,0.00003241748,0.0001942346,0.0001014404,0.00003506916],"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":[0.0002237845,0.00002852276,0.003702118,0.0002625818,0.00005140075,0.00002409629,0.0002822276,0.9859879,0.0004959739,0.002151222,0.0007203218,0.006069822],"study_design_scores_gemma":[0.001811259,0.0005042571,0.03288005,0.0003065466,0.00001597823,1.768865e-7,0.001083614,0.9563169,0.002105673,0.0006219922,0.004124601,0.0002289063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7431579,0.0003828603,0.21398,0.01079237,0.000224169,0.003665806,0.0000372105,0.0271132,0.0006464612],"genre_scores_gemma":[0.997156,0.0002510149,0.001901025,0.00002120779,0.00001101954,0.0004746697,0.0001023582,0.00002682243,0.00005588245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2539981,"threshold_uncertainty_score":0.6405705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03571213166602921,"score_gpt":0.3116582383398674,"score_spread":0.2759461066738382,"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."}}