{"id":"W3009482281","doi":"10.1109/icra40945.2020.9197362","title":"DeepMEL: Compiling Visual Multi-Experience Localization into a Deep Neural Network","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leverage (statistics); Visual odometry; Computer science; Path (computing); Artificial intelligence; Odometry; Artificial neural network; Deep neural networks; Computer vision; Robot; Range (aeronautics); Mobile robot; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007491054,0.0004163474,0.0004164165,0.00007966519,0.0001353288,0.0001846715,0.0002786475,0.0003429848,0.0000674972],"category_scores_gemma":[0.0000459986,0.0004486969,0.0001215029,0.0003128548,0.0000511082,0.0000889099,0.0002690977,0.0004962538,0.00003926817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001320715,"about_ca_system_score_gemma":0.00002351144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001006594,"about_ca_topic_score_gemma":0.0001763569,"domain_scores_codex":[0.9982395,0.00005745657,0.0005505183,0.0004997553,0.0002748428,0.0003779825],"domain_scores_gemma":[0.9992768,0.00003683343,0.00008015781,0.0003025157,0.0001103321,0.0001933792],"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":[0.000007504349,0.00002183509,0.001244961,0.0002290242,0.00003427318,0.00001187032,0.00118825,0.9946024,0.0002915357,0.0003125006,0.0001753323,0.001880508],"study_design_scores_gemma":[0.0002233929,0.00002354104,0.0003215779,0.00007031621,0.00002789543,0.000001749075,0.000158616,0.9976868,0.0004386712,0.0002460551,0.0003126333,0.0004887313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02024329,0.0004034392,0.9761052,0.00006178561,0.001472322,0.0003777302,0.000001969967,0.001054785,0.0002794433],"genre_scores_gemma":[0.9621033,0.00009668701,0.03637466,0.0003957647,0.0004916642,0.00003406961,0.0003742058,0.0001158301,0.00001381418],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.94186,"threshold_uncertainty_score":0.9997965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02549346913501806,"score_gpt":0.2729217937731298,"score_spread":0.2474283246381117,"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."}}