{"id":"W4205991048","doi":"10.1109/lra.2021.3135940","title":"Learning an Explainable Trajectory Generator Using the Automaton Generative Network (AGN)","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Toyota Research Institute","keywords":"Computer science; Artificial intelligence; Component (thermodynamics); Leverage (statistics); Automaton; Theoretical computer science; Generator (circuit theory); Pipeline (software); Machine learning; Key (lock); Representation (politics); Finite-state machine; Generative model; Artificial neural network; Generative grammar; Programming language","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":[0.0003806764,0.0001651468,0.0001628039,0.00004678015,0.0008364969,0.0005856444,0.0002365084,0.00005257879,0.00000736128],"category_scores_gemma":[0.00002328937,0.0001345218,0.0000487996,0.0003350245,0.00004562727,0.0004531342,0.00007059104,0.0002734807,0.000004134327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003909944,"about_ca_system_score_gemma":0.00007509105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001994899,"about_ca_topic_score_gemma":0.000004573226,"domain_scores_codex":[0.9984494,0.0004269446,0.000216143,0.0003619017,0.000233771,0.0003117658],"domain_scores_gemma":[0.9993231,0.00008719736,0.0001307285,0.0002997394,0.00007227669,0.00008693531],"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":[4.81249e-7,0.00001385778,0.0003075738,0.000009105,0.00001714647,0.00002845392,0.001016049,0.9762396,0.01398504,0.002255964,0.0004577287,0.005669005],"study_design_scores_gemma":[0.0001584027,0.00003210384,0.0007567615,0.00002119427,0.00001174246,0.00006143491,0.00007824722,0.9956763,0.002148095,0.0001209793,0.0007465048,0.0001882433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2771533,0.0001413327,0.7186513,0.003153738,0.0005945746,0.0000638158,3.873709e-7,0.0002162091,0.000025309],"genre_scores_gemma":[0.5262285,0.00002938206,0.4675798,0.004745355,0.001137841,0.00001166439,0.00001461279,0.00003189404,0.000220873],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2510715,"threshold_uncertainty_score":0.6433743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01624430306944624,"score_gpt":0.2481310575836374,"score_spread":0.2318867545141912,"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."}}