{"id":"W2897861898","doi":"10.1109/lra.2019.2901638","title":"Learn Fast, Forget Slow: Safe Predictive Learning Control for Systems With Unknown and Changing Dynamics Performing Repetitive Tasks","year":2019,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Model predictive control; Computer science; Gaussian process; Process (computing); Bayesian optimization; Regression; Artificial intelligence; Bayesian probability; Control theory (sociology); Term (time); Robot; Machine learning; Gaussian; Control (management); Mathematics; Statistics","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":[0.0001948499,0.0001905966,0.0002759892,0.0001525203,0.0001543331,0.00009651983,0.00004022027,0.00007378346,4.449601e-7],"category_scores_gemma":[0.00002003783,0.0001825879,0.00002623234,0.0001046668,0.00002576112,0.0003724654,0.000008154701,0.0001440282,0.000001321757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001253449,"about_ca_system_score_gemma":0.000007784417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003705324,"about_ca_topic_score_gemma":0.000003437256,"domain_scores_codex":[0.9990859,0.00003219821,0.0002423024,0.0002244771,0.0001329648,0.0002821623],"domain_scores_gemma":[0.9994867,0.000149792,0.0001316937,0.00009896383,0.00007864081,0.00005419278],"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":[0.00002256078,0.000002474274,0.0009865483,0.000251573,0.00007732661,0.000001063794,0.0004879261,0.9940459,0.001817566,0.0007093587,0.000007601583,0.001590084],"study_design_scores_gemma":[0.001398478,0.0001118703,0.0003329322,0.0002609195,0.00005166441,0.0000177659,0.0005927659,0.9968607,0.0000406787,0.000007068793,0.0001064677,0.0002187329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09599627,0.0001036882,0.9020975,0.0001668211,0.0003370326,0.0009127349,0.00001704516,0.0002350841,0.0001338559],"genre_scores_gemma":[0.9946231,0.00001986423,0.004792094,0.00005590711,0.0001156846,0.00008135063,0.00004123431,0.00005534248,0.0002153744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8986269,"threshold_uncertainty_score":0.7445719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002388532783694127,"score_gpt":0.1717302431133358,"score_spread":0.1693417103296417,"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."}}