{"id":"W3118456481","doi":"10.1109/lra.2020.3048657","title":"Learning Goal Conditioned Socially Compliant Navigation From Demonstration Using Risk-Based Features","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Evacuation and Crowd Dynamics","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung","keywords":"Reinforcement learning; Computer science; Representation (politics); Feature (linguistics); Artificial intelligence; Feature learning; Machine learning; Mobile robot; Robot; Space (punctuation); Human–computer interaction; Simple (philosophy); Quality (philosophy)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007824646,0.0001167909,0.0001176367,0.00004765885,0.0002342289,0.0001590043,0.00003157234,0.00008227064,0.00001438215],"category_scores_gemma":[0.00001862939,0.0001396295,0.00004095808,0.0001175812,0.00003583202,0.0002028236,0.000004439114,0.0001840392,0.000007075946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007661324,"about_ca_system_score_gemma":0.00003911474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002066302,"about_ca_topic_score_gemma":0.00003750653,"domain_scores_codex":[0.9993047,0.00006685493,0.0002105087,0.000138747,0.0001609631,0.0001182647],"domain_scores_gemma":[0.9996633,0.00006387932,0.00009180218,0.00007351128,0.00006367761,0.00004386348],"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":[0.00000125841,0.000007045935,0.00100036,0.00001852918,0.00002440372,0.000004608818,0.0001648445,0.8738471,0.123536,0.0002944704,0.0000981764,0.001003277],"study_design_scores_gemma":[0.0003484828,0.000006008161,0.02381578,0.00005196958,0.00004653573,0.000004456315,0.00009503274,0.9705208,0.004620805,0.0003099479,0.00002250008,0.0001576683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5456895,0.00002769362,0.4532411,0.0005326844,0.0002481909,0.00004869386,0.00001778314,0.0001699785,0.00002434876],"genre_scores_gemma":[0.9708431,0.00001322095,0.0280124,0.0003151515,0.0001063704,0.000003035929,0.0006789786,0.00002014347,0.000007625481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4252287,"threshold_uncertainty_score":0.5693925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009660835417818158,"score_gpt":0.2286883210613727,"score_spread":0.2190274856435545,"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."}}