{"id":"W4404959089","doi":"10.2139/ssrn.5042919","title":"Large Vision-Language Models Enabled Novel Objects 6d Pose Estimation for Human-Robot Collaboration","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Pose; Artificial intelligence; Computer science; Computer vision; Robot; Estimation; Human–computer interaction; Engineering","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":[0.0009935024,0.001366801,0.001500959,0.0007300875,0.0006341424,0.001872516,0.002133981,0.002153765,0.007300155],"category_scores_gemma":[0.003182258,0.0009228609,0.001141087,0.001201629,0.0008004294,0.002845837,0.004592495,0.002380684,0.005213113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006038955,"about_ca_system_score_gemma":0.001308893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005577954,"about_ca_topic_score_gemma":0.008847175,"domain_scores_codex":[0.9985064,0.0002836134,0.00005378037,0.0005318245,0.000436368,0.0001880075],"domain_scores_gemma":[0.9988245,0.000372966,0.00007989855,0.0003475447,0.000257067,0.0001179682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001675016,0.0007050822,0.002152007,0.0003775708,0.0002804004,0.0009821015,0.0007096183,0.1765788,0.1251128,0.01140356,0.01675113,0.6632718],"study_design_scores_gemma":[0.00003446232,0.000127585,0.0006193597,0.00001902823,0.00002889324,0.0001690141,0.0001109952,0.9639203,0.02181282,0.00901325,0.004108237,0.00003597869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02253418,0.0003911272,0.967414,0.0002699039,0.0001775153,0.00007427548,0.0005767345,0.006272923,0.00228932],"genre_scores_gemma":[0.5834638,0.0003528757,0.4052969,0.0003383723,0.0001201807,0.0001978407,0.002121582,0.0008009135,0.007307347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007300155,"threshold_uncertainty_score":0.02442151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01735565198766188,"score_gpt":0.2867454545712884,"score_spread":0.2693898025836265,"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."}}