{"id":"W3112133818","doi":"10.1109/icra48506.2021.9561701","title":"Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Segmentation; Point cloud; Artificial intelligence; Lidar; Annotation; Process (computing); Deep learning; Key (lock); Tracing; Computer vision; Point (geometry); Machine learning; Session (web analytics); Remote sensing; 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":[0.0001234739,0.0001809562,0.0002623023,0.00009088119,0.00004061506,0.00007269605,0.00008060246,0.0002461288,0.00003995602],"category_scores_gemma":[0.00002217364,0.0002067705,0.0001155253,0.00009610897,0.00000774093,0.00006698937,0.00004392087,0.0002252623,0.000002416707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001292621,"about_ca_system_score_gemma":0.00006882341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002461676,"about_ca_topic_score_gemma":0.000003895917,"domain_scores_codex":[0.9990771,0.00003335354,0.0003928369,0.0002148015,0.0001446721,0.0001372738],"domain_scores_gemma":[0.9994478,0.00005359984,0.00009233091,0.0001722694,0.0001950023,0.00003901661],"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":[0.000004042992,0.00002415501,0.0002771389,0.001554114,0.00009180944,9.188631e-7,0.0009613544,0.9814824,0.009792083,0.0002475154,0.00002507747,0.005539317],"study_design_scores_gemma":[0.0003394812,0.00003137171,0.0001085722,0.0001262824,0.0000634285,7.796618e-7,0.0002789846,0.9499571,0.04867596,0.00006535175,0.0001539344,0.000198723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2594,0.0001232793,0.73857,0.00001845481,0.0004071891,0.0005182686,0.00001333411,0.0003382077,0.0006113274],"genre_scores_gemma":[0.8616863,0.00008709806,0.1354275,0.00001281614,0.00008500153,0.00006662359,0.002495618,0.00005917429,0.00007979917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6031424,"threshold_uncertainty_score":0.8431857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01235420610678109,"score_gpt":0.2325233616709778,"score_spread":0.2201691555641967,"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."}}