{"id":"W4401415879","doi":"10.1109/icra57147.2024.10610069","title":"Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots","year":2024,"lang":"en","type":"article","venue":"","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Legged robot; Stair climbing; Computer science; Hill climbing; Climbing; Robot; Reinforcement; Artificial intelligence; Engineering; Physical medicine and rehabilitation; Structural 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":[0.0001387353,0.0001375013,0.0001452664,0.00008248285,0.0000867893,0.0001582289,0.00004478766,0.00004588099,0.0001026486],"category_scores_gemma":[0.00001030603,0.0001077492,0.00003764287,0.00009983208,0.00001465086,0.0001522917,0.00001403981,0.0001564275,0.00002015431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004208378,"about_ca_system_score_gemma":0.00001740177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006931824,"about_ca_topic_score_gemma":0.00001836247,"domain_scores_codex":[0.9993079,0.000009686936,0.0001695598,0.0001647483,0.0001088428,0.0002392255],"domain_scores_gemma":[0.9997374,0.00006399721,0.00001090892,0.00008794398,0.00002613376,0.0000735892],"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":[0.00003642951,0.000005013413,0.00007361685,0.0001763336,0.0001151771,0.000005449888,0.0003382491,0.9786391,0.0008755745,0.005208881,0.000664075,0.01386208],"study_design_scores_gemma":[0.001677134,0.0001692361,0.0001503289,0.00009425368,0.00004254746,0.000007920326,0.0003145225,0.9864246,0.0004796072,0.00005485372,0.01038159,0.0002033667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01820986,0.0005090802,0.9600672,0.0004977203,0.0002814042,0.0006157329,5.266861e-7,0.0009957138,0.01882281],"genre_scores_gemma":[0.9909436,0.00004138641,0.002191811,0.00006156364,0.0000825083,0.00006835463,0.000008188527,0.0000381977,0.006564423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9727337,"threshold_uncertainty_score":0.4393885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009271217130658056,"score_gpt":0.2163382736499159,"score_spread":0.2070670565192578,"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."}}