{"id":"W2995454304","doi":"10.1109/tvt.2019.2958622","title":"Deep Learning-Based Driving Maneuver Prediction System","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Advanced driver assistance systems; Driving simulator; Vehicle dynamics; Set (abstract data type); Fuse (electrical); Computer science; Engineering; Artificial neural network; Work (physics); Safe driving; Simulation; Artificial intelligence; Control engineering; Automotive engineering","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":[0.0002096885,0.000726111,0.0006023622,0.0005839126,0.0003118386,0.000386169,0.00100773,0.0005659237,0.003272212],"category_scores_gemma":[0.0004270151,0.0003413706,0.0004593913,0.0003303523,0.0001184855,0.0005331488,0.0006536564,0.0008387259,0.001861627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005894495,"about_ca_system_score_gemma":0.0009549423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01416132,"about_ca_topic_score_gemma":0.01588861,"domain_scores_codex":[0.999811,0.00000946224,0.00001251594,0.00007622266,0.00004705634,0.00004378401],"domain_scores_gemma":[0.9998099,0.00001641193,0.00001995025,0.0000184358,0.0001161966,0.00001920043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000549842,0.0006697428,0.01135921,0.0001894417,0.0001425483,0.0003982284,0.00009192358,0.1830514,0.03594769,0.001390484,0.02225573,0.7439537],"study_design_scores_gemma":[0.00001305946,0.0000670474,0.001733135,0.000007475468,0.00001790298,0.0000373206,0.000008671628,0.9913182,0.004656001,0.0005460455,0.00158022,0.00001488746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2066024,0.001276884,0.7430269,0.0007819369,0.0007047234,0.0002910346,0.004874013,0.02742084,0.01502134],"genre_scores_gemma":[0.9217275,0.0002614946,0.06221737,0.0003550654,0.00006857768,0.00018362,0.00420307,0.0000949355,0.0108884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01416132,"threshold_uncertainty_score":0.02815777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002815007703812615,"score_gpt":0.1685892621526575,"score_spread":0.1657742544488449,"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."}}