{"id":"W2012502327","doi":"10.1109/iros.2013.6696833","title":"Underwater stereo SLAM with refraction correction","year":2013,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Epipolar geometry; Computer vision; Artificial intelligence; Computer science; Underwater; Stereoscopy; Simultaneous localization and mapping; Refraction; Tracing; Pixel; Ray tracing (physics); Calibration; Geology; Optics; Image (mathematics); Mathematics; Mobile robot; Robot; Physics","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":[0.0002505647,0.0006163127,0.0006054256,0.0008780637,0.0004941871,0.00045463,0.0008678702,0.0005067629,0.00285283],"category_scores_gemma":[0.0008209641,0.0005068158,0.0005952871,0.0008625026,0.0003348294,0.0009314548,0.001406979,0.0006457853,0.001320583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005355664,"about_ca_system_score_gemma":0.0009614661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004253795,"about_ca_topic_score_gemma":0.008188843,"domain_scores_codex":[0.9993513,0.00005560901,0.00001597975,0.00007073538,0.0004650853,0.00004121762],"domain_scores_gemma":[0.9997417,0.0000348277,0.00003530343,0.00007442384,0.0001027358,0.00001103302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001498792,0.00005488073,0.001189826,0.0002106608,0.00008389959,0.0002095568,0.0002494072,0.1077683,0.1107925,0.01502033,0.007688197,0.7565825],"study_design_scores_gemma":[0.00005910776,0.0001220028,0.001939371,0.00004289719,0.00004101931,0.0005236552,0.00008491887,0.8801834,0.06770908,0.008947479,0.04028077,0.00006626936],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005448557,0.00009009624,0.9892657,0.00003627599,0.00005847932,0.00002429245,0.00007087811,0.001525111,0.003480594],"genre_scores_gemma":[0.2130161,0.0002410445,0.777251,0.00008305113,0.00005815242,0.00009020292,0.000349906,0.0003720837,0.008538531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004253795,"threshold_uncertainty_score":0.009543657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004871061573362403,"score_gpt":0.16292573976642,"score_spread":0.1580546781930576,"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."}}