{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001321405,0.00007393189,0.00008615925,0.00005475117,0.0001800792,0.00004463337,0.00002300144,0.00004201524,0.00002081806],"category_scores_gemma":[0.000006704428,0.00007034049,0.00001789968,0.0001067061,0.00001684325,0.00002936503,0.00002767074,0.0000418046,0.00000538598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001976736,"about_ca_system_score_gemma":0.000005082569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000283979,"about_ca_topic_score_gemma":0.000002001503,"domain_scores_codex":[0.9995344,0.000004941174,0.0001382989,0.0001158377,0.00007161711,0.0001348953],"domain_scores_gemma":[0.9998075,0.00004901742,0.00001110045,0.00006095482,0.00001916195,0.00005230117],"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":[0.000001446697,0.000002960696,0.0001638028,0.00002357664,0.000005856429,5.010308e-7,0.00006994323,0.9746035,0.02019835,0.003055985,0.00005385613,0.001820184],"study_design_scores_gemma":[0.0002829642,0.00002497155,0.002152256,0.00001432864,0.00001046252,0.000002855708,0.00004865154,0.9959615,0.001079774,0.00008210882,0.0002509478,0.00008920604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9378639,0.00002128274,0.05912058,0.00005771608,0.0000215303,0.0002326409,7.971396e-7,0.0002437994,0.00243779],"genre_scores_gemma":[0.9958058,0.00007764078,0.003785529,0.00000226992,0.00003279781,0.00001616448,0.00004186176,0.00001480521,0.0002231266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05794194,"threshold_uncertainty_score":0.2868402,"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."}}