{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005841528,0.0005921097,0.0005123399,0.0002021258,0.0002996872,0.0004158669,0.000658844,0.0005251169,0.001600617],"category_scores_gemma":[0.001584035,0.0002662432,0.0002653517,0.0001030709,0.0007657763,0.000287027,0.0006368676,0.0006844489,0.000197488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005330776,"about_ca_system_score_gemma":0.0006272162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004857759,"about_ca_topic_score_gemma":0.004190802,"domain_scores_codex":[0.9998243,0.00005363025,0.000008699833,0.00003804108,0.00004357665,0.00003169482],"domain_scores_gemma":[0.9994777,0.0002688558,0.00008553029,0.00003241318,0.00008333857,0.0000521808],"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":[0.00006092878,0.00003522382,0.0004530985,0.0000370885,0.0000190659,0.00008098415,0.00004708768,0.9786104,0.002839078,0.00308206,0.0002278097,0.01450714],"study_design_scores_gemma":[0.000006942287,0.00002948052,0.0000561609,0.000002299658,0.000001892064,0.000005671335,0.000002705381,0.998859,0.0002234475,0.0006891692,0.0001211764,0.000001992572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08447899,0.0002765531,0.9090815,0.0002036911,0.0000590715,0.00007763691,0.00002648793,0.0006563963,0.005139818],"genre_scores_gemma":[0.9707528,0.0000502594,0.02728586,0.00004664555,0.00001185995,0.00006443718,0.00002012641,0.00001911197,0.001749048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004857759,"threshold_uncertainty_score":0.009658933,"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."}}