{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002809643,0.0004240573,0.0003208787,0.0001241875,0.0002230998,0.0003423019,0.0005298629,0.0005615569,0.00116942],"category_scores_gemma":[0.0007766844,0.0001367544,0.0001960278,0.0001238496,0.0004414879,0.0005420587,0.0006069008,0.0008360748,0.000330296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000307342,"about_ca_system_score_gemma":0.0005874845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001818688,"about_ca_topic_score_gemma":0.001919368,"domain_scores_codex":[0.9998974,0.00002410033,0.000004454228,0.00002163424,0.00003384197,0.000018655],"domain_scores_gemma":[0.9997582,0.00008339537,0.00003638003,0.00003484103,0.00005793737,0.00002935353],"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":[0.000203713,0.0001623448,0.001947452,0.0001301531,0.00004514934,0.0003116463,0.0001300382,0.7189212,0.04292549,0.006511067,0.003453411,0.2252583],"study_design_scores_gemma":[0.00001002934,0.00008963842,0.0002581154,0.000006831116,0.000004662314,0.00005335624,0.00001135732,0.9920273,0.004615001,0.00160003,0.001317368,0.000006268937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05739893,0.0003777781,0.9367704,0.0003962952,0.00007056547,0.00004324488,0.00003951549,0.001453719,0.003449389],"genre_scores_gemma":[0.8620953,0.0002510928,0.1341358,0.0002131725,0.00002160094,0.00006806751,0.00006467357,0.00004440031,0.003105799],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001818688,"threshold_uncertainty_score":0.003912091,"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."}}