{"id":"W3201588370","doi":"10.1109/lra.2022.3189165","title":"Robust Visual Teach and Repeat for UGVs Using 3D Semantic Maps","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer vision; Computer science; Artificial intelligence; Robot; Path (computing); Orientation (vector space); Point cloud; Pose; Orb (optics); Simultaneous localization and mapping; Mobile robot; Image (mathematics); 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":[0.0001462375,0.0001300123,0.0001452974,0.0001209556,0.0002912143,0.00008742686,0.00004214801,0.00003615394,0.000005675478],"category_scores_gemma":[0.000008763416,0.0001477334,0.00002982538,0.0001129605,0.00002458488,0.00009544993,0.00002027136,0.00009631591,6.355135e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006797274,"about_ca_system_score_gemma":0.000007391009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008772298,"about_ca_topic_score_gemma":0.000001595092,"domain_scores_codex":[0.9992507,0.00002934491,0.0002180783,0.0001753558,0.0001428387,0.0001837115],"domain_scores_gemma":[0.9997432,0.0000472739,0.00004683253,0.0000930329,0.00002040767,0.00004929043],"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":[0.000002884415,0.00001084961,0.0002208902,0.00009998729,0.00002004746,0.000003162132,0.0001380929,0.981694,0.01587456,0.0001985282,0.0009360272,0.0008009503],"study_design_scores_gemma":[0.000349134,0.00003215522,0.0002715515,0.00001678765,0.0000407292,0.00002184257,0.00005655834,0.9982953,0.0003461634,0.00003784393,0.0003483967,0.0001835197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3302999,0.00006293529,0.6683887,0.0004994496,0.000393478,0.0001959823,0.00001142153,0.0001362042,0.0000118581],"genre_scores_gemma":[0.9697196,0.00001993827,0.02944595,0.0005405597,0.0001149949,0.00001512696,0.00007365995,0.00004832084,0.00002181607],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6394197,"threshold_uncertainty_score":0.6024393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01952947418004371,"score_gpt":0.2235774631809574,"score_spread":0.2040479890009137,"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."}}