{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002953169,0.0004843441,0.0005607914,0.0005594231,0.0005920071,0.00009069785,0.0003787735,0.0009402932,0.0006745437],"category_scores_gemma":[0.00007017048,0.0005387812,0.0002351539,0.0005494918,0.00009981392,0.0001880904,0.0001043271,0.000461713,0.00002786006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004227403,"about_ca_system_score_gemma":0.0002037677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002931301,"about_ca_topic_score_gemma":0.000005607078,"domain_scores_codex":[0.9977152,0.00002657465,0.0007786893,0.0006288953,0.0001258322,0.0007248163],"domain_scores_gemma":[0.9988298,0.0002080207,0.0001331276,0.0006063055,0.0001312268,0.00009156554],"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":[0.0001036701,0.0001663635,0.002658518,0.0005143113,0.0001527521,0.000002425337,0.000100379,0.9737316,0.0006878639,0.003926816,0.00151864,0.01643661],"study_design_scores_gemma":[0.002119431,0.000112154,0.002248685,0.0003131071,0.000189675,8.913181e-7,0.0001072552,0.9811249,0.01039136,0.0009464728,0.001973442,0.0004726267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03346791,0.0003876479,0.951649,0.0009442347,0.001069941,0.00122856,0.00002706636,0.00127935,0.009946262],"genre_scores_gemma":[0.9498525,0.00004017222,0.04484248,0.0002317199,0.00007150633,0.0002088017,0.0001605663,0.00006908885,0.004523186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9163846,"threshold_uncertainty_score":0.9997064,"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."}}