{"id":"W3003991701","doi":"10.1109/iros40897.2019.8967704","title":"SuMa++: Efficient LiDAR-based Semantic SLAM","year":2019,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":482,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Segmentation; Semantic mapping; Semantics (computer science); Convolutional neural network; Task (project management); Matching (statistics); Projection (relational algebra); Semantic matching","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00005392096,0.0000969173,0.0001027259,0.00006615395,0.0000199138,0.00003064537,0.00006384851,0.00005006498,0.0004468373],"category_scores_gemma":[0.000005944525,0.000087397,0.00004185641,0.0001335561,0.000007777257,0.0000172478,0.00000631762,0.00005728475,0.0008414694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003162902,"about_ca_system_score_gemma":0.00001045406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001032953,"about_ca_topic_score_gemma":0.000005265456,"domain_scores_codex":[0.9994458,0.000008242567,0.0001286851,0.0001127698,0.0001311013,0.0001733893],"domain_scores_gemma":[0.9996813,0.00002860797,0.000009663088,0.0002059653,0.00002858932,0.00004589848],"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":[0.000001720163,0.00001494705,0.0009068055,0.00005015095,0.000005934984,0.000001634167,0.00001783945,0.99365,0.003135311,0.00164069,0.0003252324,0.000249695],"study_design_scores_gemma":[0.0002680258,0.00002184117,0.00086358,0.00001715749,0.00000555425,5.48242e-7,0.00001388163,0.9869229,0.01035727,0.00001422654,0.00138415,0.0001308825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7209309,0.00003878255,0.2535002,0.00007350316,0.0004887091,0.0001772031,0.000001396542,0.0003963652,0.02439292],"genre_scores_gemma":[0.9982784,0.000002347975,0.0008802484,0.000102051,0.00002695343,0.000001991415,0.00001399533,0.00002722777,0.0006668058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2773474,"threshold_uncertainty_score":0.9999365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004790865206244858,"score_gpt":0.1788997548915594,"score_spread":0.1741088896853146,"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."}}