{"id":"W7115607610","doi":"","title":"Bench-Push: Benchmarking Pushing-based Navigation and Manipulation Tasks for Mobile Robots","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Benchmarking; Mobile robot; Robotics; Robot; Modular design; Python (programming language); Implementation; Obstacle","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00161739,0.003187557,0.0010669,0.001200971,0.0008274923,0.001257847,0.004187028,0.002022541,0.007684869],"category_scores_gemma":[0.006141188,0.0007132051,0.001260205,0.001203002,0.001180944,0.001881844,0.002864067,0.002062488,0.005158625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061788,"about_ca_system_score_gemma":0.002285472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01161974,"about_ca_topic_score_gemma":0.01631117,"domain_scores_codex":[0.9984697,0.0003342759,0.000137887,0.0003853316,0.0004491542,0.0002237072],"domain_scores_gemma":[0.9976548,0.001085515,0.0001304785,0.000446233,0.000427463,0.0002555467],"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":[0.002468312,0.002164479,0.01151681,0.006474687,0.0007928765,0.0004181967,0.0004590034,0.5143231,0.01491959,0.008445477,0.1210716,0.3169459],"study_design_scores_gemma":[0.0004377049,0.00166325,0.006020107,0.0002326596,0.0001069793,0.0002168411,0.0003053689,0.9372209,0.01533286,0.006699698,0.03164176,0.0001218931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3826668,0.006601303,0.3232248,0.001452215,0.002679065,0.00224694,0.03123379,0.1960859,0.05380926],"genre_scores_gemma":[0.629862,0.00164573,0.2892663,0.0007030193,0.0001435955,0.002163233,0.06128007,0.006598954,0.008337283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01161974,"threshold_uncertainty_score":0.02570838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03979216649602045,"score_gpt":0.3016447239538219,"score_spread":0.2618525574578014,"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."}}