{"id":"W4416749103","doi":"10.1109/iros60139.2025.11247412","title":"Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning","year":2025,"lang":"","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Health Industry Development Institute; National Research Foundation; Ministry of Health","keywords":"Reinforcement learning; Motion planning; Motion (physics); Measure (data warehouse); Differentiable function; Thresholding","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001166889,0.001042657,0.001234779,0.0005539511,0.0003982229,0.0006467113,0.001177099,0.001340649,0.0021734],"category_scores_gemma":[0.004522941,0.000622273,0.0005361023,0.0004112145,0.001259712,0.001061145,0.001122925,0.00226401,0.0003731206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001496779,"about_ca_system_score_gemma":0.001582731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01057057,"about_ca_topic_score_gemma":0.007757262,"domain_scores_codex":[0.9995965,0.0001209422,0.00002371893,0.0001014846,0.0000906764,0.00006669055],"domain_scores_gemma":[0.9980513,0.001391588,0.0001688773,0.000077836,0.0001957418,0.0001147307],"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":[0.0000327646,0.00002322087,0.0002529773,0.00002899632,0.000008970082,0.00002460482,0.00002431492,0.9805,0.000642904,0.003856638,0.0005136075,0.01409103],"study_design_scores_gemma":[0.000003685137,0.000007294819,0.00001981314,0.000002457918,9.881893e-7,0.000002881699,0.000001364428,0.9983602,0.0001223559,0.001389998,0.00008757319,0.000001381226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02663621,0.0004796606,0.9691066,0.0004776172,0.00005300348,0.00004393246,0.00006677986,0.0008082652,0.002327975],"genre_scores_gemma":[0.8776945,0.0002738714,0.1177072,0.0002618572,0.00003993015,0.0001439886,0.0001935447,0.0001937944,0.003491267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01057057,"threshold_uncertainty_score":0.02101803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007735008664649107,"score_gpt":0.231361508955214,"score_spread":0.2236265002905649,"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."}}