{"id":"W2791780736","doi":"10.1109/itsc.2017.8317731","title":"Trajectory prediction of traffic agents at urban intersections through learned interactions","year":2017,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"U.S. Department of Transportation","keywords":"Intersection (aeronautics); Computer science; Trajectory; Task (project management); Artificial intelligence; Dynamic Bayesian network; Bayesian network; Machine learning; Object (grammar); Artificial neural network; Tracking (education); Transport engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000444651,0.00009222871,0.0001193452,0.00005886806,0.0003002009,0.00001013422,0.000177932,0.0001079809,0.0005197611],"category_scores_gemma":[0.00001808762,0.00009379997,0.00007581168,0.00003606937,0.0001187199,0.0002697143,0.00004298914,0.0002057948,0.00007234157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001088923,"about_ca_system_score_gemma":0.00000702026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002523473,"about_ca_topic_score_gemma":0.0003375623,"domain_scores_codex":[0.9995053,0.000008991989,0.0001861965,0.0001204672,0.00004949585,0.0001295919],"domain_scores_gemma":[0.9994943,0.00001740102,0.00005333599,0.000393589,0.00001762435,0.00002373738],"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":[0.0003785999,0.001388302,0.08292966,0.0005413856,0.003356065,0.00004727938,0.0282297,0.3417999,0.1293446,0.01213366,0.2515872,0.1482636],"study_design_scores_gemma":[0.002308749,0.0003496533,0.3770909,0.0001398579,0.0002126007,0.0001133044,0.002142099,0.421145,0.07020705,0.0004888299,0.1250882,0.0007138019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9458458,0.00003207331,0.004025217,0.0001292341,0.0008533394,0.00009875387,0.00002000505,0.0008080502,0.04818755],"genre_scores_gemma":[0.9968008,0.00004836668,0.0002406433,0.000009425836,0.00004227043,0.00001480369,0.000008121831,0.00001650338,0.002819108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2941612,"threshold_uncertainty_score":0.569102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03447082140383381,"score_gpt":0.2623047870176779,"score_spread":0.2278339656138441,"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."}}