{"id":"W4280518809","doi":"10.1016/j.icte.2022.05.004","title":"ADAS-RL: Safety learning approach for stable autonomous driving","year":2022,"lang":"en","type":"article","venue":"ICT Express","topic":"Traffic control and management","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; National Research Foundation of Korea; Information Technology Research Centre; Ministry of Science, ICT and Future Planning","keywords":"Reinforcement learning; Computer science; Stability (learning theory); Component (thermodynamics); Advanced driver assistance systems; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002035018,0.0001176504,0.0001530588,0.00005546422,0.0002579453,0.00003824167,0.0002006138,0.00002087215,0.000118446],"category_scores_gemma":[0.000008747023,0.0001337316,0.00006894679,0.00007550984,0.00000671223,0.00007934186,0.0001379852,0.0001851186,0.000002682404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108777,"about_ca_system_score_gemma":0.000009235999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001335144,"about_ca_topic_score_gemma":0.000002990603,"domain_scores_codex":[0.9991909,0.00002525759,0.000158571,0.0001800223,0.0001362114,0.000309069],"domain_scores_gemma":[0.9996966,0.000047819,0.00002448909,0.0001753826,0.000009745265,0.00004602558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001361382,0.00002683044,0.00003743547,0.00005957102,0.00004521613,0.000001938815,0.0006162047,0.9753956,0.001214665,0.0008165272,0.002559277,0.01921314],"study_design_scores_gemma":[0.0004340473,0.00002654934,0.0001944198,0.000002551834,0.00001400869,0.000001191919,0.0004606876,0.4409026,0.00006288769,0.00001172681,0.5577552,0.0001341753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02908932,0.001012118,0.9002635,0.0001145505,0.001053119,0.001285431,0.00005421,0.002505056,0.0646227],"genre_scores_gemma":[0.9916097,0.00000796961,0.004018789,0.00002312068,0.00009007628,0.000526602,0.00004402661,0.00004453494,0.003635184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9625204,"threshold_uncertainty_score":0.5453418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007450014817507865,"score_gpt":0.1843666551110687,"score_spread":0.1769166402935608,"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."}}