{"id":"W4415782431","doi":"10.1177/02783649251365282","title":"Learning an interpretable logic monitor for risk-aware and socially-compliant trajectory planning","year":2025,"lang":"en","type":"article","venue":"The International Journal of Robotics Research","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Toyota Research Institute, North America","keywords":"Leverage (statistics); Task (project management); Parameterized complexity; Trajectory; Software deployment; Robot; Control (management); Plan (archaeology)","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":[0.0015188,0.00007452606,0.0001367053,0.0002590837,0.0002342214,0.00007549976,0.0006186502,0.00009060928,0.000008141452],"category_scores_gemma":[0.0002548844,0.00005687497,0.00005305607,0.00009428308,0.0001305607,0.0001160085,0.00009843765,0.001037826,0.000001835047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001539738,"about_ca_system_score_gemma":0.0001159997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009389867,"about_ca_topic_score_gemma":0.00001082687,"domain_scores_codex":[0.9990978,0.0001003349,0.0002515303,0.00007952007,0.0002728594,0.0001979535],"domain_scores_gemma":[0.9988786,0.0005176215,0.0000701315,0.00008178798,0.0004145668,0.00003727724],"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":[0.0001950214,0.00004781954,0.00661418,0.0000351055,0.0004984019,0.00002846221,0.001253213,0.9368679,0.00281665,0.01100391,0.0009489655,0.03969039],"study_design_scores_gemma":[0.00104322,0.0004487278,0.01936103,0.0003016743,0.00005178096,0.00007625017,0.003832256,0.9072348,0.002066908,0.06391741,0.001486005,0.000179908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6205972,0.002046098,0.3694818,0.004507723,0.001445917,0.0002820174,0.00001108419,0.0001253413,0.001502764],"genre_scores_gemma":[0.9960527,0.000347805,0.003121258,0.00002513942,0.0001646077,0.000004550396,0.000001536216,0.00001204308,0.0002703707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3754555,"threshold_uncertainty_score":0.4508896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05053092852164519,"score_gpt":0.3791718383832804,"score_spread":0.3286409098616352,"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."}}