{"id":"W4210754841","doi":"10.1016/j.comcom.2022.01.013","title":"Weighted triplet loss based on deep neural networks for loop closure detection in VSLAM","year":2022,"lang":"en","type":"article","venue":"Computer Communications","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Odometer; Artificial intelligence; Metric (unit); Simultaneous localization and mapping; Artificial neural network; Extrapolation; Deep learning; Global Positioning System; Closure (psychology); Boundary (topology); Computer vision; Robot; Mobile robot; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001489398,0.0001170201,0.0001316229,0.0001723816,0.000312159,0.00003745575,0.0004632104,0.00005140453,0.00001256252],"category_scores_gemma":[0.00000628911,0.0001398797,0.00006941827,0.0004399485,0.00002507538,0.00004425555,0.00009871245,0.0003193034,0.000001669174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00013703,"about_ca_system_score_gemma":0.000008540504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008661963,"about_ca_topic_score_gemma":0.00008471084,"domain_scores_codex":[0.9991874,0.0001521237,0.0002501887,0.0001349894,0.00009852924,0.0001767403],"domain_scores_gemma":[0.9987734,0.0002630752,0.00003861078,0.0008444068,0.00004394109,0.00003659528],"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":[0.00001556806,0.00007850327,0.0002812433,0.000009247246,0.000008338478,8.178651e-7,0.00004951406,0.9804166,0.00001733187,0.0005692737,0.0002265353,0.01832702],"study_design_scores_gemma":[0.0007156434,0.0001032676,0.0009103646,0.000007078107,0.000009435695,0.000002017656,0.00001007607,0.9940151,0.0000315303,0.0001226808,0.003929101,0.0001437359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01212741,0.0001840412,0.9860672,0.0004817541,0.0003989214,0.0004061057,0.00001331483,0.0001976016,0.000123625],"genre_scores_gemma":[0.9885747,0.00002067168,0.01040421,0.0003210797,0.00007004062,0.0001930053,0.0003741195,0.00003496782,0.000007194804],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9764473,"threshold_uncertainty_score":0.5704129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647343383994798,"score_gpt":0.2248184250037022,"score_spread":0.2083449911637542,"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."}}