{"id":"W2064779083","doi":"10.1109/coase.2010.5584599","title":"A hierarchical reinforcement learning based control architecture for semi-autonomous rescue robots in cluttered environments","year":2010,"lang":"en","type":"article","venue":"","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Teleoperation; Rescue robot; Robot; Search and rescue; Urban search and rescue; Reinforcement learning; Computer science; Task (project management); Mobile robot; Robot control; Collision avoidance; Artificial intelligence; Human–computer interaction; Telerobotics; Engineering; Computer security; Collision; Systems 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":[0.0005465981,0.0003334453,0.000304292,0.0001458071,0.0002725543,0.000410005,0.00080248,0.0004433175,0.001330351],"category_scores_gemma":[0.0007502979,0.000179715,0.0002223122,0.00009516802,0.0005720553,0.0003136846,0.0004410427,0.0004595708,0.0003360554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005481144,"about_ca_system_score_gemma":0.0008755395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004940673,"about_ca_topic_score_gemma":0.003758805,"domain_scores_codex":[0.9997969,0.00005438683,0.00001197243,0.00005165512,0.00005455306,0.00003056772],"domain_scores_gemma":[0.999696,0.00008558227,0.00005685403,0.00003536081,0.00009337395,0.00003276087],"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":[0.000159706,0.0001440162,0.0008189569,0.0001062928,0.00004613648,0.000169239,0.0002036928,0.8553813,0.02922384,0.008563464,0.001316147,0.1038672],"study_design_scores_gemma":[0.00002216193,0.00009585679,0.0002032976,0.000004652287,0.000005460138,0.00002056114,0.000004755301,0.9971144,0.001229355,0.0008042154,0.0004882276,0.000007041572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03867512,0.0001554272,0.9562159,0.000177082,0.0000362448,0.00007990166,0.00002325568,0.001393387,0.00324375],"genre_scores_gemma":[0.9248214,0.00007104929,0.07281049,0.00008213599,0.00001846498,0.0001506508,0.00003819948,0.00001975088,0.00198803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004940673,"threshold_uncertainty_score":0.009823799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00494750687231205,"score_gpt":0.1952001196053014,"score_spread":0.1902526127329894,"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."}}