{"id":"W2548459939","doi":"10.1109/icra.2017.7989235","title":"Reducing drift in visual odometry by inferring sun direction using a Bayesian Convolutional Neural Network","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Visual odometry; Artificial intelligence; Odometry; Convolutional neural network; Computer science; Computer vision; Leverage (statistics); Bayesian probability; Robustness (evolution); Pipeline (software); Pattern recognition (psychology); Robot; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002834112,0.0003489982,0.0004105671,0.0002824775,0.0001909476,0.0002447868,0.0001829966,0.0004444024,0.00005232111],"category_scores_gemma":[0.00006846681,0.0004100686,0.0001098188,0.0001842388,0.00004175862,0.0001656737,0.000168171,0.0007266108,0.000003488148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004039276,"about_ca_system_score_gemma":0.00006354336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001361535,"about_ca_topic_score_gemma":0.0001787833,"domain_scores_codex":[0.9982969,0.00006460566,0.0005079549,0.0004233487,0.0002518973,0.0004553277],"domain_scores_gemma":[0.9993052,0.00006023647,0.0001338723,0.0003354552,0.00006053923,0.0001046273],"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":[0.000006656785,0.00001910619,0.007509544,0.0001186425,0.00003840028,0.000006263308,0.00004136981,0.9892929,0.001229821,0.0001147302,0.0006345637,0.0009880543],"study_design_scores_gemma":[0.0002345948,0.00001036842,0.004005076,0.0003356996,0.00002416206,0.000006535106,0.00001246778,0.9943013,0.000324032,0.0001793811,0.0001415319,0.0004248762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4467618,0.0007975897,0.5458558,0.00003726952,0.00334027,0.0003350199,0.00001184169,0.0004014256,0.002458971],"genre_scores_gemma":[0.9949121,0.00007752827,0.003904433,0.00002289974,0.0006717415,0.00001072859,0.000216073,0.00008450102,0.0001000273],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5481503,"threshold_uncertainty_score":0.9998351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01954149982568431,"score_gpt":0.2691418932235792,"score_spread":0.2496003933978949,"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."}}