{"id":"W3204193097","doi":"10.1177/02783649211045736","title":"Self-supervised learning for using overhead imagery as maps in outdoor range sensor localization","year":2021,"lang":"en","type":"article","venue":"The International Journal of Robotics Research","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Engineering and Physical Sciences Research Council; University of Oxford","keywords":"Computer science; Artificial intelligence; Ground truth; Computer vision; Overhead (engineering); Robustness (evolution); USable; Radar; Workspace; Image sensor; Real-time computing; Robot; Telecommunications","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001368671,0.001320779,0.0009935924,0.001092478,0.0004601247,0.0009391865,0.002733953,0.001342763,0.001897028],"category_scores_gemma":[0.006716614,0.0004439227,0.000696669,0.001137068,0.001107935,0.002013334,0.001770607,0.001827169,0.001607022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000678787,"about_ca_system_score_gemma":0.0007988415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002915972,"about_ca_topic_score_gemma":0.004036925,"domain_scores_codex":[0.9986546,0.0004092699,0.00006394144,0.0004928384,0.0002755473,0.00010376],"domain_scores_gemma":[0.9975315,0.0008495892,0.0002922088,0.0005748675,0.0006266432,0.0001251612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003023216,0.0003402492,0.004334641,0.0003467824,0.0001576502,0.0001722029,0.000267269,0.4136194,0.00805429,0.007730201,0.01932946,0.5453455],"study_design_scores_gemma":[0.00001579437,0.00007000349,0.0004382552,0.00002121355,0.00001081885,0.00005197374,0.00004062422,0.9858765,0.002983454,0.00837798,0.002099826,0.00001361998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02404521,0.0004956826,0.968808,0.0002446795,0.0001162035,0.00009285931,0.0003657282,0.003824505,0.002007055],"genre_scores_gemma":[0.6464376,0.0003648047,0.3429331,0.0006023839,0.0002977165,0.0004646422,0.003774738,0.0006325465,0.004492554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002915972,"threshold_uncertainty_score":0.007238328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06517878868075411,"score_gpt":0.3502725975523526,"score_spread":0.2850938088715985,"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."}}