{"id":"W4378191992","doi":"10.1109/ismr57123.2023.10130214","title":"Towards Safe and Efficient Reinforcement Learning for Surgical Robots Using Real-Time Human Supervision and Demonstration","year":2023,"lang":"en","type":"article","venue":"","topic":"Soft Robotics and Applications","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Teleoperation; Reinforcement learning; Computer science; Artificial intelligence; Workload; Robot; Human–robot interaction; Robotics; Robot learning; Machine learning; Process (computing); Human–computer interaction; 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":[0.001226201,0.0008055861,0.0006578279,0.0003045509,0.0002479685,0.0004772709,0.001259925,0.0009512591,0.001381727],"category_scores_gemma":[0.003254314,0.0004444151,0.0004239678,0.0001623866,0.001149987,0.0007122434,0.001435932,0.001542493,0.0003940494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004707281,"about_ca_system_score_gemma":0.001201456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002634963,"about_ca_topic_score_gemma":0.002654582,"domain_scores_codex":[0.9994797,0.0001683497,0.00002287815,0.0001056381,0.0001498025,0.00007367619],"domain_scores_gemma":[0.99839,0.0008512389,0.0002276677,0.0002058413,0.0002026044,0.0001227498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001473223,0.00009617698,0.0007924215,0.00008674055,0.00002978566,0.0001357162,0.0001038516,0.8932032,0.008376523,0.003841465,0.001063547,0.09212328],"study_design_scores_gemma":[0.000007513015,0.00003103616,0.00005181499,0.000003298844,0.000002023088,0.00001759181,0.00000386128,0.9976304,0.0009588939,0.001104121,0.0001870673,0.000002466468],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01490243,0.0001493886,0.9829827,0.0001274732,0.00001929017,0.00003619478,0.00001093921,0.0009707724,0.0008008464],"genre_scores_gemma":[0.8354933,0.000112819,0.1623131,0.0001531312,0.00002396419,0.0001136416,0.00005657684,0.0001191007,0.001614303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002634963,"threshold_uncertainty_score":0.006484866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02606083954130737,"score_gpt":0.2791224802055995,"score_spread":0.2530616406642921,"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."}}