{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VCV2SF2GISK7YXLMIVOETZRKON","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fdf385febbc19aa6d07f267b28b2d84d41a2ca70082dc0ba079631c34352dd1c","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2026-05-13T09:13:10Z","title_canon_sha256":"a3a7a623069631ec7f1a4f6409a5980d40aeeccc6ec412768f174ab20f072177"},"schema_version":"1.0","source":{"id":"2605.13220","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13220","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13220v1","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13220","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"VCV2SF2GISK7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VCV2SF2GISK7YXLM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VCV2SF2G","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4f59b4d6d876fccc7e9d8baa509565b2f000e7e3bbd7bf33707e00297f1b355a","target":"graph","created_at":"2026-05-18T03:08:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Compared to a model predictive control implementation using real-time iterations, the Gaussian process based approximation computes control inputs about five times faster while achieving similar closed-loop tracking performance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The curvilinear coordinate transformation combined with the nominal feedforward component reduces the problem sufficiently that a Gaussian process can generalize across distinct reference trajectories using a manageable amount of training data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Gaussian process approximation of MPC in curvilinear coordinates with residual feedforward learning enables 5x faster real-time trajectory tracking on embedded hardware with comparable closed-loop performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Gaussian process approximations of model predictive control enable five times faster computation for vehicle trajectory tracking on embedded systems."}],"snapshot_sha256":"ae9d5165d3f39b74262938b5d02fbb7afecc3a5cc4a000f9d4a83ddeea166e67"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Applying model predictive control on embedded systems remains challenging due to the high computational cost of solving optimal control problems. To address this limitation, computationally efficient Gaussian process approximations of the implicit model predictive control law can be employed. However, for trajectory-tracking applications, the large amount of training data required for successful generalization across distinct reference trajectories poses a significant challenge. To improve data efficiency, we propose to transform the model into curvilinear coordinates around the reference traj","authors_text":"Alexander Rose, Lukas Theiner, Rolf Findeisen","cross_cats":["cs.SY"],"headline":"Gaussian process approximations of model predictive control enable five times faster computation for vehicle trajectory tracking on embedded systems.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2026-05-13T09:13:10Z","title":"Real-time Gaussian Process based Approximate Model Predictive Trajectory Tracking Control for Autonomous Vehicles"},"references":{"count":42,"internal_anchors":0,"resolved_work":42,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Model predictive control with Gaussian-process-supported dynamical constraints for autonomous vehicles,","work_id":"375bcb4c-96eb-4d31-bfc7-eda67f28638c","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Model predictive control for autonomous ground vehicles: a review,","work_id":"160cc538-8764-4e4b-b6f1-4123bd26002e","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Model predictive control for quadcopters with almost global trajectory tracking guarantees,","work_id":"471d9729-063c-4a70-9df6-0219809828c2","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Model predictive interaction control for industrial robots,","work_id":"94bf62a5-8ab8-4522-a0e0-90a02f9decac","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Embedded optimization in control: An introduction, opportunities, and challenges,","work_id":"cef04bd4-2c71-4d67-97e2-e5092ebd2543","year":2026}],"snapshot_sha256":"b68baa77d22e7a2829f0d93ff66c6d7110e56a75b8174c116c504aac13f75371"},"source":{"id":"2605.13220","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:47:38.430091Z","id":"59e78d54-f47e-41bd-b8ca-ef0219544460","model_set":{"reader":"grok-4.3"},"one_line_summary":"Gaussian process approximation of MPC in curvilinear coordinates with residual feedforward learning enables 5x faster real-time trajectory tracking on embedded hardware with comparable closed-loop performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Gaussian process approximations of model predictive control enable five times faster computation for vehicle trajectory tracking on embedded systems.","strongest_claim":"Compared to a model predictive control implementation using real-time iterations, the Gaussian process based approximation computes control inputs about five times faster while achieving similar closed-loop tracking performance.","weakest_assumption":"The curvilinear coordinate transformation combined with the nominal feedforward component reduces the problem sufficiently that a Gaussian process can generalize across distinct reference trajectories using a manageable amount of training data."}},"verdict_id":"59e78d54-f47e-41bd-b8ca-ef0219544460"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:189bc47130b544e565dffce6ed24cc1a8ea2e511acfa60302a9cb43128c7834e","target":"record","created_at":"2026-05-18T03:08:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fdf385febbc19aa6d07f267b28b2d84d41a2ca70082dc0ba079631c34352dd1c","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2026-05-13T09:13:10Z","title_canon_sha256":"a3a7a623069631ec7f1a4f6409a5980d40aeeccc6ec412768f174ab20f072177"},"schema_version":"1.0","source":{"id":"2605.13220","kind":"arxiv","version":1}},"canonical_sha256":"a8aba917464495fc5d6c455c49e62a735396b648c85f8579cc9b684cd16e22f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8aba917464495fc5d6c455c49e62a735396b648c85f8579cc9b684cd16e22f6","first_computed_at":"2026-05-18T03:08:48.403009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:48.403009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1QGtTrhJYXua/1bQclNgLclNo7CxsZ0c5gTGUQsKMm2muMbRb2odU/zY3qHcYQeQzMwyEkFLK39k5NoBOy+mBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:48.403663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13220","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:189bc47130b544e565dffce6ed24cc1a8ea2e511acfa60302a9cb43128c7834e","sha256:4f59b4d6d876fccc7e9d8baa509565b2f000e7e3bbd7bf33707e00297f1b355a"],"state_sha256":"4f93c1327ef008f596ffeee7a9b1864ec4b357b3e5802a27dc26f8258f4b7466"}