{"id":"W2892557643","doi":"10.1109/icra.2019.8793649","title":"Robot eye-hand coordination learning by watching human demonstrations: a task function approximation approach","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Interpretability; Task (project management); Robot; Artificial intelligence; Visual servoing; Function (biology); Controller (irrigation); Reinforcement learning; Process (computing); Task analysis; Human–computer interaction; Eye–hand coordination; Retraining; Computer vision; Machine learning; Engineering","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":[0.0004305298,0.0005345696,0.0005636979,0.0002023558,0.000150744,0.0002838563,0.0008629983,0.0006451737,0.001304363],"category_scores_gemma":[0.001580189,0.0002946634,0.0002718647,0.0001810742,0.0003030852,0.0004751817,0.0005247634,0.000727237,0.0002544214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000392608,"about_ca_system_score_gemma":0.0004593444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003199944,"about_ca_topic_score_gemma":0.002413533,"domain_scores_codex":[0.9998013,0.00004858396,0.000008160275,0.0000600163,0.00005290262,0.00002910897],"domain_scores_gemma":[0.9995911,0.0001718681,0.00006266971,0.00007589272,0.00006737908,0.0000311931],"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":[0.0002566921,0.0001743173,0.001286432,0.0001279156,0.00005792262,0.000137574,0.0001549324,0.7139364,0.04565707,0.003237609,0.001449838,0.2335233],"study_design_scores_gemma":[0.0000103241,0.00005048169,0.0003235399,0.000002717195,0.000003085482,0.00002893567,0.000004808466,0.99467,0.003948322,0.0006366257,0.0003162963,0.000004864052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02343189,0.0001241341,0.9745257,0.00006028784,0.00000963913,0.00003067621,0.00002897493,0.0008824464,0.0009062105],"genre_scores_gemma":[0.7755601,0.0001102717,0.2213924,0.00007473538,0.00002043997,0.000139276,0.00009315297,0.0001222979,0.00248746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003199944,"threshold_uncertainty_score":0.006362617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01718536006674713,"score_gpt":0.2779053878366022,"score_spread":0.260720027769855,"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."}}