{"id":"W3090242756","doi":"10.1109/icra40945.2020.9197275","title":"A Flexible Method for Performance Evaluation of Robot Localization","year":2020,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Simultaneous localization and mapping; Benchmark (surveying); Artificial intelligence; Robot; Computer science; Mobile robot; Computer vision; Robotics; RGB color model; Motion (physics); Geography","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":[0.0002577444,0.00006188313,0.00009566172,0.00003261918,0.00002206671,0.000008433501,0.00004102031,0.00004003275,0.00006767288],"category_scores_gemma":[0.00005472762,0.00006049269,0.00002780554,0.0001862963,0.00000517832,0.00007269959,0.000004282402,0.00002211524,0.000005061489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000245111,"about_ca_system_score_gemma":0.00001825687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000309332,"about_ca_topic_score_gemma":0.000001365962,"domain_scores_codex":[0.9994633,0.00002028571,0.0001740818,0.00008393104,0.0001789449,0.00007946242],"domain_scores_gemma":[0.999646,0.00002486094,0.00002315066,0.0000691536,0.0002028708,0.00003397136],"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":[0.000007065936,0.000004733983,0.00008106457,0.0001015604,0.00001016637,1.022484e-8,0.000109749,0.9714384,0.004471345,0.0009691493,0.0005360004,0.02227075],"study_design_scores_gemma":[0.0003429284,0.00004880656,0.00009455896,0.000008352389,0.00003447281,1.320775e-7,0.00002276105,0.8935968,0.105128,0.00008801155,0.0005707361,0.00006441475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002994226,0.00004930462,0.9945656,0.00009440771,0.00006807601,0.0002905162,0.00000233336,0.0001166323,0.001818886],"genre_scores_gemma":[0.9236147,0.00001689916,0.07608071,0.0001318053,0.0000478173,0.00001953663,0.00004733889,0.00001921138,0.00002196412],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9206205,"threshold_uncertainty_score":0.246682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06297735164697894,"score_gpt":0.2976443273717732,"score_spread":0.2346669757247943,"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."}}