{"id":"W2967595637","doi":"10.1109/icra.2019.8793961","title":"Learning Motion Planning Policies in Uncertain Environments through Repeated Task Executions","year":2019,"lang":"en","type":"article","venue":"","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Task (project management); Robot; Motion planning; Motion (physics); Work (physics); Artificial intelligence; Collision avoidance; Task analysis; Human–computer interaction; Machine learning; Computer security; Collision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002770996,0.0001443016,0.0001649115,0.0001367385,0.0001056371,0.00008343632,0.0004393212,0.00007959564,0.0000206489],"category_scores_gemma":[0.00005266003,0.0001388878,0.00003500116,0.0004220457,0.00002783764,0.0006013763,0.00019117,0.0002580805,0.000337163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001312929,"about_ca_system_score_gemma":0.00002364846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004322961,"about_ca_topic_score_gemma":8.032326e-7,"domain_scores_codex":[0.9985427,0.000123863,0.0002574691,0.0004227376,0.0002734414,0.0003798086],"domain_scores_gemma":[0.9993518,0.00009196402,0.00009154339,0.0004079026,0.000009647355,0.00004715699],"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":[0.000003134443,0.00006594139,0.1137289,0.000007600635,0.00001405537,0.00004547702,0.008703405,0.8657573,0.004824021,0.004464798,0.0002206259,0.002164717],"study_design_scores_gemma":[0.0005973541,0.0001411457,0.1264866,0.0001030827,0.000003622064,0.00003327665,0.0008823054,0.8677866,0.001019999,0.0009060919,0.001703954,0.0003359545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1915333,0.00004881308,0.7952074,0.0004137274,0.0002649027,0.000201044,7.544153e-7,0.0002568994,0.01207312],"genre_scores_gemma":[0.8877703,0.000006810539,0.1076007,0.0002080123,0.00002425045,0.00001105492,0.00001497916,0.0000108307,0.004353119],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.696237,"threshold_uncertainty_score":0.5663681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02332315286623294,"score_gpt":0.2714470973132572,"score_spread":0.2481239444470242,"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."}}