{"id":"W3176880374","doi":"10.1109/lra.2021.3093551","title":"A Sim-to-Real Pipeline for Deep Reinforcement Learning for Autonomous Robot Navigation in Cluttered Rough Terrain","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Traverse; Terrain; Reinforcement learning; Robot; Pipeline (software); Artificial intelligence; Computer science; Computer vision; Point (geometry); Mobile robot; Trajectory; Geography; Mathematics; Cartography","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004834082,0.0002387163,0.0002923771,0.000201134,0.0002359925,0.0003730634,0.0002910147,0.00009665285,0.000002616602],"category_scores_gemma":[0.0001671087,0.0002680089,0.00009426251,0.0003632987,0.00002664452,0.0004624213,0.0001035313,0.0001712418,0.000007440198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002015373,"about_ca_system_score_gemma":0.00007190674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000273578,"about_ca_topic_score_gemma":0.00001611571,"domain_scores_codex":[0.997997,0.00007629301,0.000659862,0.0005080188,0.0002827877,0.0004760695],"domain_scores_gemma":[0.9988467,0.0002759322,0.0002608724,0.0003244483,0.0001777475,0.000114288],"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":[0.00001055615,0.00001819746,0.0001411555,0.00009421139,0.00001679317,0.000006045904,0.001396162,0.9822825,0.007529847,0.002275044,0.0003806225,0.00584884],"study_design_scores_gemma":[0.001226635,0.0001249758,0.000615902,0.0001079478,0.00001687303,0.000009100382,0.00005175491,0.9950338,0.001375953,0.0001725958,0.0009547368,0.000309726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007852049,0.00001147469,0.9766116,0.01391407,0.0005337723,0.0008387378,0.000001064964,0.0001876901,0.00004952416],"genre_scores_gemma":[0.7057514,0.00001047491,0.2905358,0.002777776,0.0001558136,0.0001525775,0.0001711901,0.00003171467,0.0004132254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6978994,"threshold_uncertainty_score":0.9999772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01694845159004387,"score_gpt":0.2673356383234801,"score_spread":0.2503871867334362,"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."}}