{"id":"W3156199997","doi":"10.1109/itsc48978.2021.9565113","title":"Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Air Force Research Laboratory; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Western Canada Research Grid; Compute Canada; Defense Advanced Research Projects Agency; Mitacs","keywords":"Trajectory; Computer science; Kinematics; Differentiable function; State (computer science); Acceleration; Artificial neural network; Artificial intelligence; Obstacle avoidance; Control theory (sociology); Simulation; Algorithm; Control (management); Robot; Mathematics; Mobile robot","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000436716,0.0005751764,0.0004715136,0.0002297662,0.0002613134,0.0006627025,0.001151558,0.001148962,0.002277755],"category_scores_gemma":[0.00191397,0.0004671497,0.0006142916,0.0002027906,0.000868547,0.001014938,0.0009566429,0.001434277,0.0004710221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008576907,"about_ca_system_score_gemma":0.0007766292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01323807,"about_ca_topic_score_gemma":0.01315213,"domain_scores_codex":[0.9998367,0.00005658134,0.00000540541,0.00004796289,0.00003034745,0.00002297776],"domain_scores_gemma":[0.999408,0.0003543663,0.00005675706,0.00007608853,0.00004789804,0.00005695301],"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":[0.00002195591,0.000008077197,0.0004168839,0.000006616205,0.000008647373,0.0000264908,0.00002151722,0.9920615,0.0003654788,0.003181121,0.0003108124,0.003570976],"study_design_scores_gemma":[0.000001295131,0.000002205474,0.00001861125,7.979893e-7,5.123928e-7,0.000002414025,0.000001393636,0.9986997,0.0000792046,0.00111879,0.00007425258,8.608637e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1246543,0.0002994868,0.8677447,0.0007652789,0.00007141774,0.00003885563,0.0004212748,0.001576922,0.004427771],"genre_scores_gemma":[0.9521458,0.00009595163,0.04404741,0.0001071545,0.00002112241,0.00004536486,0.0004332392,0.000143943,0.002960095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01323807,"threshold_uncertainty_score":0.02632201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01747730950923697,"score_gpt":0.2338954679509317,"score_spread":0.2164181584416947,"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."}}