{"id":"W2910054127","doi":"10.1109/lra.2019.2891991","title":"Deep Reinforcement Learning Robot for Search and Rescue Applications: Exploration in Unknown Cluttered Environments","year":2019,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":378,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canada Research Chairs","keywords":"Reinforcement learning; Task (project management); Computer science; Artificial intelligence; Urban search and rescue; Robot; Deep learning; Rescue robot; Search and rescue; Mobile robot; Identification (biology); Frontier; Human–computer interaction; Engineering; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001433401,0.0001202517,0.000128684,0.0001339911,0.00007160639,0.00007257419,0.00004166044,0.00006233763,0.00000357528],"category_scores_gemma":[0.000005245748,0.0001329402,0.00001874644,0.00009563858,0.00001975221,0.0002222882,0.00001085479,0.0000945374,0.00001032437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000710212,"about_ca_system_score_gemma":0.000004030889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007259315,"about_ca_topic_score_gemma":0.000008689943,"domain_scores_codex":[0.9992262,0.00002501775,0.0002622959,0.0001798699,0.0001299719,0.0001766999],"domain_scores_gemma":[0.9997634,0.00004225873,0.00002572291,0.0001117252,0.00001281795,0.00004408274],"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":[0.00000419235,0.000007231563,0.0003716696,0.000104573,0.000009954548,2.561723e-7,0.0002418169,0.9727636,0.02322116,0.0005765147,0.00001464164,0.002684394],"study_design_scores_gemma":[0.000573962,0.00003222442,0.001077843,0.00003413088,0.000008903164,8.203211e-7,0.00006223147,0.9962656,0.001442329,0.00003758189,0.0003159677,0.0001483993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09092907,0.0000562585,0.9076746,0.0005091001,0.00008673487,0.0006675239,5.151452e-7,0.00005814627,0.00001805364],"genre_scores_gemma":[0.9909369,0.0002169531,0.008366577,0.0001829136,0.00004309153,0.00008114498,0.00009371545,0.000027833,0.00005091177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9000078,"threshold_uncertainty_score":0.5421144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01267934446708015,"score_gpt":0.2174006178996612,"score_spread":0.2047212734325811,"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."}}