{"id":"W3045101785","doi":"10.1109/lra.2020.3011394","title":"Cluster-based Penalty Scaling for Robust Pose Graph Optimization","year":2020,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Spurious relationship; Computer science; Consistency (knowledge bases); Estimator; Graph; Scaling; Global optimization; Cluster (spacecraft); Penalty method; Data mining; Artificial intelligence; Mathematical optimization; Algorithm; Machine learning; Mathematics; Theoretical computer science; Statistics","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":[0.00008694792,0.0001667269,0.0001670515,0.00009556655,0.0001226633,0.0001265622,0.00006777632,0.00007676205,0.000006677909],"category_scores_gemma":[0.00002883164,0.0001789508,0.00006311495,0.0002010624,0.00002594793,0.0001426146,0.000005681246,0.0000773817,0.000003193485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003019654,"about_ca_system_score_gemma":0.00001044486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001832707,"about_ca_topic_score_gemma":7.830835e-7,"domain_scores_codex":[0.999154,0.00002256202,0.0002913986,0.0001936084,0.0001423376,0.0001961007],"domain_scores_gemma":[0.9995916,0.00007296263,0.0000616977,0.00009901951,0.0000602982,0.0001143599],"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":[0.000008595046,0.000008875872,0.00004249739,0.0001755643,0.00001700498,9.742236e-7,0.0000992139,0.9941329,0.002946565,0.0001243138,0.001996224,0.0004472273],"study_design_scores_gemma":[0.0006875103,0.00003051492,0.00006396836,0.00003546114,0.00003702094,0.000001004032,0.00001457176,0.9975732,0.001245418,0.00001691338,0.00007925529,0.0002151935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01264906,0.00003008236,0.9803091,0.005923106,0.0003674143,0.0003293501,0.00001423444,0.0003591613,0.00001855087],"genre_scores_gemma":[0.688493,0.00002450537,0.3058949,0.005017187,0.0002794225,0.00001806584,0.0002001253,0.00007022888,0.000002580952],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6758439,"threshold_uncertainty_score":0.7297402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01917851241904025,"score_gpt":0.204819712937441,"score_spread":0.1856412005184008,"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."}}