{"id":"W4405753615","doi":"10.1109/tro.2024.3521864","title":"Multimodal and Force-Matched Imitation Learning With a See-Through Visuotactile Sensor","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Robotics","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Computer vision; Robot; Imitation; Human–computer interaction; Human–robot interaction; Psychology","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":[0.00002931672,0.0002190347,0.0001758331,0.0001652397,0.0004315795,0.0002129709,0.00006634929,0.00009492079,0.0001054238],"category_scores_gemma":[0.00002666032,0.0001924075,0.0000830104,0.0003634584,0.00009796195,0.0006199874,0.000001096099,0.0006565963,0.0002234676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007320622,"about_ca_system_score_gemma":0.00004545022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004204381,"about_ca_topic_score_gemma":0.00004124418,"domain_scores_codex":[0.9986653,0.00009406229,0.0002102694,0.000504994,0.0002452498,0.0002801045],"domain_scores_gemma":[0.9988987,0.0007305946,0.00004737158,0.0001898212,0.00004308126,0.00009043486],"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":[0.0001231999,0.0001350044,0.000007894821,0.00005458377,0.0000384189,0.00008418896,0.002364332,0.8129619,0.1799311,0.0003118654,0.00005257545,0.003934922],"study_design_scores_gemma":[0.0006386998,0.0006050935,0.000039087,0.000171221,0.0001725072,0.0005526403,0.001795925,0.4665737,0.5267737,0.0001600228,0.002058149,0.0004592095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.189309,0.000009008644,0.8064114,0.0009467202,0.0009236966,0.0002928072,0.00002899089,0.0005388964,0.00153944],"genre_scores_gemma":[0.9894255,0.0000994266,0.004612652,0.0002410939,0.00005782031,0.00002965054,0.000001992264,0.00005511666,0.005476686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8017988,"threshold_uncertainty_score":0.7846149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03158170986158924,"score_gpt":0.2868286582953339,"score_spread":0.2552469484337446,"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."}}