{"id":"W4409098630","doi":"10.1109/tai.2025.3556983","title":"iLeAD: An EMG-Based Adaptive Shared Control Framework for Exoskeleton Assistance via Deep Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exoskeleton; Reinforcement learning; Reinforcement; Computer science; Control (management); Artificial intelligence; Engineering; Simulation; Structural engineering","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":[0.0002637758,0.0002296626,0.0003531412,0.0003290748,0.0003613339,0.00005078051,0.0001214763,0.0002093895,0.0004654422],"category_scores_gemma":[0.0001497781,0.0002223043,0.0003228669,0.0004425567,0.0001436954,0.0001289017,6.204075e-7,0.0005057706,0.0000708108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002475565,"about_ca_system_score_gemma":0.0001821676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003126917,"about_ca_topic_score_gemma":0.0001123573,"domain_scores_codex":[0.9982826,0.00009695914,0.0005586929,0.0004571958,0.000271873,0.0003326728],"domain_scores_gemma":[0.9979961,0.001077336,0.0001172843,0.0003373805,0.0003187944,0.00015309],"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":[0.005137489,0.000698527,0.00005418358,0.0001351058,0.0001805494,0.000004012858,0.0005216784,0.7005528,0.007404992,0.005845667,0.00003346911,0.2794316],"study_design_scores_gemma":[0.0004320278,0.002338386,0.000240475,0.0004750645,0.0002126483,0.000001498309,0.001449581,0.8625666,0.1262593,0.004789674,0.0009522902,0.0002824271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004194945,0.00005371556,0.9917221,0.001092717,0.001194581,0.001238766,0.00001682856,0.000167323,0.0003190111],"genre_scores_gemma":[0.9773669,0.00001442717,0.02022455,0.00111223,0.00009430271,0.0003946777,0.00001240692,0.00002604793,0.0007545211],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9731719,"threshold_uncertainty_score":0.9065308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03832127911133228,"score_gpt":0.3313001407627515,"score_spread":0.2929788616514192,"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."}}