{"id":"W3157951743","doi":"10.1109/iros51168.2021.9636440","title":"Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Viewpoints; Computer science; Task (project management); Artificial intelligence; Perspective (graphical); Human–computer interaction; Robot; Variety (cybernetics); Computer vision","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":[0.001477331,0.0006998122,0.0008556784,0.0003551438,0.0002429918,0.0005625276,0.001086203,0.000779303,0.001118327],"category_scores_gemma":[0.005604007,0.0004706851,0.0003587831,0.0002627657,0.000790656,0.00108436,0.001166641,0.001204438,0.0002502311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000698257,"about_ca_system_score_gemma":0.0009297078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003370498,"about_ca_topic_score_gemma":0.003217643,"domain_scores_codex":[0.9995779,0.0001275942,0.00002443772,0.0001239777,0.00008997971,0.00005607636],"domain_scores_gemma":[0.9975923,0.001552758,0.0003304956,0.000215756,0.0001411067,0.0001675262],"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":[0.0004108385,0.000194019,0.003301848,0.00009175338,0.00006139725,0.00009266997,0.0001493708,0.8884448,0.008166262,0.003328541,0.0006381386,0.09512033],"study_design_scores_gemma":[0.00002060292,0.00008301796,0.0003635237,0.000007792507,0.000004892664,0.00001412993,0.00001175526,0.9954426,0.001499992,0.00239462,0.0001503845,0.000006664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1643704,0.000345513,0.8330868,0.0002300443,0.00002642538,0.00007563468,0.00007912323,0.0006906469,0.001095348],"genre_scores_gemma":[0.942302,0.000105883,0.05644787,0.00009095153,0.0000157559,0.00008766147,0.0001114861,0.00005379345,0.0007845524],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003370498,"threshold_uncertainty_score":0.007812977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1131611266662068,"score_gpt":0.3296329576508928,"score_spread":0.216471830984686,"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."}}