{"id":"W4220783120","doi":"10.1109/lra.2022.3160833","title":"Pressing and Rubbing: Physics-Informed Features Facilitate Haptic Terrain Classification for Legged Robots","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Terrain; Artificial intelligence; Robot; Computer science; Slipping; Feature extraction; Computer vision; Rubbing; Pattern recognition (psychology); Feature (linguistics); Haptic technology; Machine learning; Engineering; Geography; Cartography; Mechanical 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001295711,0.0001471747,0.0001586885,0.00007562514,0.0003281292,0.0001352844,0.00006865878,0.00003311633,0.000005040993],"category_scores_gemma":[0.0000144519,0.0001559935,0.00004408166,0.00008200691,0.00003804043,0.0002079132,0.00001690423,0.0001289492,0.000001432293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007998567,"about_ca_system_score_gemma":0.00001306761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004021387,"about_ca_topic_score_gemma":0.00000130552,"domain_scores_codex":[0.9992242,0.0000319635,0.0002244016,0.0001685268,0.0001511029,0.0001998334],"domain_scores_gemma":[0.9996465,0.00008861214,0.00006600034,0.0001218419,0.00001905583,0.00005791556],"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":[0.000006091604,0.00001130103,0.00003777953,0.0001055206,0.00003668234,5.997888e-7,0.001197085,0.9353752,0.0465018,0.001048581,0.002392255,0.01328708],"study_design_scores_gemma":[0.0007979295,0.00002702152,0.004247894,0.00001908809,0.0000312242,0.000008350262,0.0002201149,0.9932513,0.000243606,0.0001962639,0.0007631508,0.0001940531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06453037,0.0001376276,0.9281203,0.005377008,0.0006205868,0.0006360979,0.00002416341,0.0003927673,0.0001610724],"genre_scores_gemma":[0.991511,0.00001317076,0.007443842,0.0006201044,0.00008144589,0.0001268915,0.00004725905,0.00002581388,0.0001304588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9269806,"threshold_uncertainty_score":0.6361231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02333862690166939,"score_gpt":0.2298319599979744,"score_spread":0.206493333096305,"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."}}