{"paper":{"title":"Stochastic Differential Dynamic Programming for Trajectory Optimization under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A stochastic differential dynamic programming algorithm optimizes spacecraft trajectories under partial observability by jointly handling control and belief-state evolution.","cross_cats":["cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Masahiro Fujiwara, Naoya Ozaki","submitted_at":"2026-05-08T09:57:48Z","abstract_excerpt":"Designing spacecraft trajectories remains challenging in the presence of stochastic effects such as maneuver execution errors and observation uncertainties. Although covariance control and belief-space planning provide useful tools for designing robust control policies and information-aware trajectories under uncertainty, practical methods remain limited for partially observable trajectory optimization problems in which trajectory design, orbit determination, and correction maneuver planning are tightly coupled. This paper presents a stochastic differential dynamic programming algorithm for su"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the proposed method can exploit the coupling between trajectory design and orbit determination to obtain navigation-aware solutions with substantially lower fuel consumption than those from deterministic local optimization starting from the same initial guess","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The belief dynamics accurately capture the dependence of covariance propagation on the nominal trajectory and that the stochastic differential dynamic programming iterations converge to a solution that respects all general mission constraints without separation of estimation and control","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A new stochastic differential dynamic programming method optimizes coupled trajectory design and orbit determination under partial observability, producing navigation-aware solutions with lower fuel consumption than deterministic local optimization in examples like the circular restricted three-body","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A stochastic differential dynamic programming algorithm optimizes spacecraft trajectories under partial observability by jointly handling control and belief-state evolution.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4f38fb6162e4a5683227cfeae1a07852630d32d9aa9c6e5f799caa4a77385dc0"},"source":{"id":"2605.07529","kind":"arxiv","version":2},"verdict":{"id":"9d82ed97-e775-4a0f-988f-886b12dd6848","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T01:55:59.543450Z","strongest_claim":"the proposed method can exploit the coupling between trajectory design and orbit determination to obtain navigation-aware solutions with substantially lower fuel consumption than those from deterministic local optimization starting from the same initial guess","one_line_summary":"A new stochastic differential dynamic programming method optimizes coupled trajectory design and orbit determination under partial observability, producing navigation-aware solutions with lower fuel consumption than deterministic local optimization in examples like the circular restricted three-body","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The belief dynamics accurately capture the dependence of covariance propagation on the nominal trajectory and that the stochastic differential dynamic programming iterations converge to a solution that respects all general mission constraints without separation of estimation and control","pith_extraction_headline":"A stochastic differential dynamic programming algorithm optimizes spacecraft trajectories under partial observability by jointly handling control and belief-state evolution."},"integrity":{"clean":false,"summary":{"advisory":0,"critical":1,"by_detector":{"doi_compliance":{"total":1,"advisory":0,"critical":1,"informational":0}},"informational":0},"endpoint":"/pith/2605.07529/integrity.json","findings":[{"note":"DOI '10.1061/(asce' as printed in the bibliography is syntactically invalid and cannot resolve.","detector":"doi_compliance","severity":"critical","ref_index":2,"audited_at":"2026-05-19T11:42:48.773265Z","detected_doi":"10.1061/(asce","finding_type":"broken_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T10:42:02.877116Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T05:41:04.340476Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.677503Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:42:48.773265Z","status":"completed","version":"1.0.0","findings_count":1}],"snapshot_sha256":"8cb6e478a315fb154aecd19ccabcf1c2e0cdec4328e16a028e37e769e16ccb7e"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3265807c0282af0d6b5739d64fa1995385567804f9e96d4c8c4b81fa3dac3b41"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}