{"id":"W4287203366","doi":"10.48550/arxiv.2104.11212","title":"Imagining The Road Ahead: Multi-Agent Trajectory Prediction via\\n Differentiable Simulation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","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; Control theory (sociology); Simulation; Algorithm; Control (management); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001382523,0.0002935636,0.0002678625,0.0001423148,0.0002137119,0.00003946151,0.0004062067,0.0004700866,0.0001043379],"category_scores_gemma":[0.00001272016,0.000304872,0.0001814774,0.0002366233,0.0001090853,0.0001659065,0.000318527,0.001046984,0.00003268907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003220067,"about_ca_system_score_gemma":0.00004935901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008046077,"about_ca_topic_score_gemma":0.00006597391,"domain_scores_codex":[0.9988344,0.00008114875,0.0002154635,0.0005113779,0.00005892764,0.000298624],"domain_scores_gemma":[0.9990569,0.00005165086,0.00008797553,0.0006764925,0.00006501571,0.00006191718],"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":[0.000009029231,0.00004399235,0.0031987,0.00006293944,0.0001727816,0.00004048668,0.0003246649,0.9939934,0.0002900872,0.0001875919,0.00002608305,0.00165024],"study_design_scores_gemma":[0.0003442441,0.00001043622,0.02163916,0.00005498842,0.0001476707,0.000002439956,0.0002920878,0.9762955,0.0003696601,0.0003413589,0.0002413294,0.0002610748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5407521,0.0002081674,0.4569502,0.00001570169,0.0005780087,0.000203299,0.0000162269,0.0007857635,0.0004905168],"genre_scores_gemma":[0.9987714,0.0001979438,0.0001945069,0.00001651854,0.00006825619,0.000002886916,0.00008578835,0.0000414412,0.0006213071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4580192,"threshold_uncertainty_score":0.9999403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04353308186930707,"score_gpt":0.1767002500976307,"score_spread":0.1331671682283236,"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."}}