{"id":"W4200066496","doi":"10.1109/iros51168.2021.9636422","title":"Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Trajectory; Generalization; Terrain; Constraint (computer-aided design); Feature (linguistics); Task (project management); Computer vision; Collision avoidance; Visual space; Machine learning; Collision; Mathematics; Engineering; Psychology","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":[0.0004688568,0.0002393042,0.0003551415,0.0002245113,0.00009100007,0.0002462293,0.0005380666,0.000122491,0.00005147813],"category_scores_gemma":[0.0001118292,0.000232636,0.0001215165,0.00019179,0.0000978116,0.0001701438,0.0001250612,0.0002420134,0.00000946281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001145595,"about_ca_system_score_gemma":0.000129219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005145292,"about_ca_topic_score_gemma":0.0001383764,"domain_scores_codex":[0.997754,0.0001888546,0.0007242157,0.0006893431,0.0003524031,0.0002912346],"domain_scores_gemma":[0.9986024,0.0002363049,0.0003068354,0.0003208925,0.0004157637,0.0001178022],"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":[0.0001939592,0.00114885,0.01398783,0.0003642316,0.0003795837,0.0000945752,0.003846138,0.4905272,0.1822855,0.1504602,0.00006844116,0.1566436],"study_design_scores_gemma":[0.0004840218,0.000173954,0.00463093,0.0003418033,0.000008252447,0.00004883102,0.0003441373,0.9893458,0.003903109,0.0004119351,0.00008414553,0.0002231197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1689173,0.0001328807,0.8286489,0.0005417153,0.000873311,0.000508265,0.00002750412,0.00003387472,0.0003163523],"genre_scores_gemma":[0.9962857,0.00004419766,0.002945389,0.0000543508,0.0001003413,0.000199535,0.00006283887,0.00001544385,0.0002921521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8273685,"threshold_uncertainty_score":0.948662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04299268943244507,"score_gpt":0.328001037531914,"score_spread":0.285008348099469,"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."}}