{"id":"W2968288611","doi":"10.1109/icra.2019.8794425","title":"CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction","year":2019,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Visual odometry; Artificial intelligence; Computer science; Robustness (evolution); Simultaneous localization and mapping; Initialization; Computer vision; Feature (linguistics); Odometry; Pixel; Probabilistic logic; Pattern recognition (psychology); Mobile robot; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002010169,0.0001182293,0.0001255748,0.0001669538,0.00004854825,0.00008213866,0.00005302504,0.00007651572,0.00002739039],"category_scores_gemma":[0.00003521601,0.00009722485,0.00002700379,0.0003392507,0.00001619285,0.0001808367,0.00002770556,0.0001063101,0.00001218612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001118436,"about_ca_system_score_gemma":0.000008988806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009614414,"about_ca_topic_score_gemma":0.00002326185,"domain_scores_codex":[0.9992697,0.00002881127,0.0002120306,0.0001603151,0.000123883,0.0002052446],"domain_scores_gemma":[0.9997141,0.00007650557,0.00002575664,0.0001283854,0.00002288699,0.00003231125],"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":[0.000002619057,0.00001614433,0.01988016,0.0001031836,0.00001408666,0.000002147768,0.0002291918,0.5988104,0.3767627,0.0000638905,0.0000216716,0.004093851],"study_design_scores_gemma":[0.0002011529,0.00001947076,0.005960242,0.00005182072,0.000006999253,0.000004412291,0.0003312661,0.983295,0.009935482,0.000008847697,0.00006917365,0.0001161349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8019338,0.00009161337,0.1913583,0.00001347573,0.0002886593,0.0001811906,0.000001103058,0.0001861223,0.005945722],"genre_scores_gemma":[0.9970495,0.00001352726,0.002710947,0.00003513437,0.00006968986,0.000001842309,0.000006582199,0.00003259776,0.00008015289],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3844846,"threshold_uncertainty_score":0.3964714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0147550676250778,"score_gpt":0.2119159606580827,"score_spread":0.1971608930330049,"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."}}