{"id":"W4403747047","doi":"10.48550/arxiv.2409.12273","title":"Improving Soft-Capture Phase Success in Space Debris Removal Missions: Leveraging Deep Reinforcement Learning and Tactile Feedback","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Space Satellite Systems and Control","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency","keywords":"Soft landing; Debris; Reinforcement learning; Space debris; Computer science; Reinforcement; Phase (matter); Space (punctuation); Human–computer interaction; Artificial intelligence; Geology; Engineering; Physics; Structural engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002421962,0.000480067,0.0004997037,0.0004341893,0.0001176861,0.00019621,0.0002765472,0.0003941791,0.00007469975],"category_scores_gemma":[0.00004148665,0.0005475307,0.0001603761,0.0003942251,0.00004125634,0.0001848592,0.0005611289,0.00151944,0.00003589876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004398086,"about_ca_system_score_gemma":0.00008007262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001281834,"about_ca_topic_score_gemma":0.0001772044,"domain_scores_codex":[0.9982091,0.00007128919,0.0003033407,0.0007997305,0.0001082092,0.0005083823],"domain_scores_gemma":[0.9991424,0.00008207435,0.0001274773,0.0003829677,0.00005588384,0.0002091798],"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":[0.00006667212,0.00002058782,0.001173275,0.001080072,0.0001699852,0.001191706,0.001175775,0.9861125,0.001522009,0.0008907844,0.00007226108,0.006524353],"study_design_scores_gemma":[0.001263035,0.00002590609,0.00005440166,0.0007509514,0.0001331348,0.00002487392,0.001817924,0.99141,0.0002036471,0.000527246,0.003187393,0.0006014818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8639767,0.008260286,0.1169507,0.00008348739,0.001153652,0.0008256987,0.000007560406,0.0007195048,0.008022444],"genre_scores_gemma":[0.9950838,0.0007140868,0.0001256033,0.00001391317,0.0001311201,0.000003369247,0.00002010295,0.00008265867,0.00382534],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1311071,"threshold_uncertainty_score":0.9996976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01988746821018765,"score_gpt":0.1867338126630185,"score_spread":0.1668463444528309,"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."}}