{"id":"W4389666362","doi":"10.1109/iros55552.2023.10342143","title":"Zero-Shot Fault Detection for Manipulators Through Bayesian Inverse Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Fault detection and isolation; Reinforcement learning; Artificial intelligence; Detector; Fault (geology); Control theory (sociology); Bayesian probability; Controller (irrigation); Machine learning; Real-time computing; Control engineering; Computer vision; Engineering; Control (management); Actuator","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":[0.001352799,0.0008661679,0.001049056,0.0005816932,0.0002994188,0.0006221312,0.001312011,0.001022015,0.001039996],"category_scores_gemma":[0.006265522,0.0003866555,0.0005334907,0.0002389899,0.001266124,0.0008731119,0.001007781,0.001254081,0.0001586022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001153779,"about_ca_system_score_gemma":0.001375717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007383515,"about_ca_topic_score_gemma":0.0052553,"domain_scores_codex":[0.9993848,0.0001362403,0.00002718831,0.0001679753,0.0001953245,0.00008845178],"domain_scores_gemma":[0.9976649,0.001389195,0.0004001617,0.0001241511,0.0002964786,0.0001250116],"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":[0.0001201146,0.00005999495,0.001877136,0.00006227134,0.00003285308,0.0001022837,0.00008557176,0.9419541,0.002621202,0.003857872,0.0003109484,0.04891558],"study_design_scores_gemma":[0.00000461185,0.00002278035,0.0001126731,0.000002643939,0.000002594913,0.000009538522,0.000002280488,0.9983422,0.0004509582,0.0009903589,0.000055929,0.000003436836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04690546,0.0002251072,0.9509987,0.0001797934,0.00002492101,0.00003829847,0.00002327699,0.0007275773,0.0008769857],"genre_scores_gemma":[0.9387892,0.00007582835,0.05966063,0.00008237749,0.00001914382,0.00005056081,0.00005139638,0.00004417363,0.001226839],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007383515,"threshold_uncertainty_score":0.0146811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0235949585184414,"score_gpt":0.2471506599122697,"score_spread":0.2235557013938283,"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."}}