{"id":"W2782673766","doi":"10.1177/0278364917749732","title":"Inferring sun direction to improve visual odometry: A deep learning approach","year":2018,"lang":"en","type":"article","venue":"The International Journal of Robotics Research","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Visual odometry; Artificial intelligence; Odometry; Pipeline (software); Computer vision; Computer science; Orientation (vector space); Robot; Mathematics; Mobile robot","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":[0.0004319604,0.001288954,0.0006998419,0.001007642,0.0004077097,0.0007787774,0.001506416,0.0006733657,0.001506187],"category_scores_gemma":[0.001877153,0.0005978317,0.0008166116,0.00120298,0.000430371,0.001228081,0.001522234,0.001543514,0.0008245489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006830612,"about_ca_system_score_gemma":0.001250271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02654266,"about_ca_topic_score_gemma":0.03979733,"domain_scores_codex":[0.999661,0.00003050721,0.00001490513,0.0001348489,0.00009504088,0.00006370158],"domain_scores_gemma":[0.99954,0.00008402163,0.00005836812,0.0001077107,0.0001784411,0.00003144232],"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":[0.0001302086,0.0001970204,0.0076613,0.0001001455,0.0001951076,0.00006072763,0.0001211505,0.4413146,0.01477381,0.002381281,0.005030395,0.5280342],"study_design_scores_gemma":[0.000009997098,0.00002279428,0.001552824,0.00001577866,0.0000164831,0.00001905824,0.00002016455,0.9913368,0.003495865,0.002238289,0.001260231,0.00001175045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05692833,0.0005099595,0.9346603,0.0002819583,0.00016567,0.00004493834,0.0006953834,0.004062397,0.002651031],"genre_scores_gemma":[0.6962218,0.0003276703,0.2959894,0.0002893156,0.0001416397,0.00006697977,0.002368986,0.0002846625,0.00430946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02654266,"threshold_uncertainty_score":0.05277634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03991735156067796,"score_gpt":0.35111873518514,"score_spread":0.3112013836244621,"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."}}