{"id":"W7131116789","doi":"10.1109/robio66223.2025.11378377","title":"A Strategy Adaptive Adjustment Deep Reinforcement Learning Method with Behavior Cloning for Mobile Robot Navigation","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Reinforcement learning; Obstacle avoidance; Randomness; Obstacle; Robot; Mobile robot; Trajectory; Training (meteorology); Path (computing)","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":[0.0005907048,0.0007997855,0.0008631829,0.0003131193,0.0002972928,0.0004140768,0.001353572,0.0006890837,0.001664529],"category_scores_gemma":[0.001353948,0.000398889,0.0005660917,0.0002414281,0.0004749951,0.0005544413,0.0008756567,0.001168649,0.0003017466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006668828,"about_ca_system_score_gemma":0.001387099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008207185,"about_ca_topic_score_gemma":0.005758546,"domain_scores_codex":[0.9997609,0.00005120976,0.00001504751,0.00006089963,0.00006574435,0.00004610574],"domain_scores_gemma":[0.9996438,0.0001268616,0.00004911695,0.00003375833,0.0001034073,0.00004307938],"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":[0.0001245238,0.0001134757,0.001599474,0.00008736223,0.00007221326,0.0001396005,0.00011152,0.7865726,0.007191565,0.006198813,0.002483893,0.195305],"study_design_scores_gemma":[0.000008975206,0.00002329855,0.00005047102,0.000002623317,0.00000455688,0.000008895038,0.00000203121,0.9987682,0.0003816482,0.000509452,0.0002368675,0.000002962631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02085958,0.0003723311,0.9757607,0.0001849785,0.00008001387,0.00004927595,0.00002636266,0.001063499,0.0016032],"genre_scores_gemma":[0.8275054,0.0002293974,0.1665838,0.0003170388,0.00004267748,0.000221363,0.0001302859,0.0001174824,0.004852483],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008207185,"threshold_uncertainty_score":0.0163188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0254119146095384,"score_gpt":0.3187286794351319,"score_spread":0.2933167648255935,"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."}}