{"id":"W3213426571","doi":"10.1109/tmech.2021.3120628","title":"A Behavior-Based Reinforcement Learning Approach to Control Walking Bipedal Robots Under Unknown Disturbances","year":2021,"lang":"en","type":"article","venue":"IEEE/ASME Transactions on Mechatronics","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Inverted pendulum; Reinforcement learning; Control theory (sociology); Computer science; Robot; Robustness (evolution); Bipedalism; Controller (irrigation); Disturbance (geology); Robot locomotion; Control engineering; Robot control; Artificial intelligence; Control (management); Mobile robot; Engineering; Nonlinear system","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":[0.0004437218,0.000649403,0.0005252328,0.0002944477,0.0002361282,0.000404694,0.0009355101,0.0004594857,0.001169607],"category_scores_gemma":[0.0006487877,0.0002309295,0.0003780667,0.0001685271,0.0005480985,0.0002864332,0.0004796039,0.0007646759,0.0002151688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004814544,"about_ca_system_score_gemma":0.0007009001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004186842,"about_ca_topic_score_gemma":0.002754282,"domain_scores_codex":[0.9997777,0.00004893435,0.00001443034,0.00004009755,0.0000904552,0.00002837256],"domain_scores_gemma":[0.9997024,0.00009428656,0.00005719265,0.00002161096,0.000102616,0.00002191397],"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":[0.00003059985,0.00006577104,0.0003950178,0.0000761277,0.00004661637,0.00008388379,0.00006075058,0.9369372,0.009217402,0.007725132,0.0004619398,0.04489968],"study_design_scores_gemma":[0.00000736822,0.00004049006,0.00006376411,0.000003290546,0.00000397629,0.000009465197,0.000002821387,0.997893,0.0005855801,0.001010673,0.0003764565,0.000003097612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007839362,0.0001037069,0.9892321,0.00006720009,0.00003249968,0.00004729478,0.00001073894,0.0003453984,0.002321786],"genre_scores_gemma":[0.8610464,0.0002234375,0.1340048,0.0001341655,0.00005366186,0.0003456495,0.00004725105,0.00005639102,0.004088232],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004186842,"threshold_uncertainty_score":0.008324921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01223155664040403,"score_gpt":0.2186668019377259,"score_spread":0.2064352452973219,"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."}}