{"paper":{"title":"Domain-Aware Machine Learning for Accelerating MILP-Based Motion Planning with Temporal Logic and Chance Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Neuro-symbolic guidance accelerates MILP motion planning for temporal logic and chance constraints by about 20 percent.","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Bistra Dilkina, Brendan Long, Junyang Cai, Jyotirmoy V. Deshmukh, Lars Lindemann, Matthew Cleaveland, Weimin Huang","submitted_at":"2025-08-11T00:13:36Z","abstract_excerpt":"Motion-planning problems with temporal-logic or chance constraints are often encoded as mixed-integer linear programs (MILPs). Although these encodings provide rigorous specifications, their combinatorial structure can make planning prohibitively slow. Machine learning for combinatorial optimization (ML4CO) has accelerated general-purpose MILP solving, but its standard graph representations discard semantic information available in control problems, such as variable roles, time indices, sample identities, and formula structure. We introduce a domain-aware ML4CO framework for MILP-based motion "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through extensive experiments, we show that neuro-symbolic search techniques yield scalability gains. Our approach yields substantial improvements across all three classes of planning problems, achieving an average performance gain of about 20% over state-of-the-art solver across key metrics, including runtime and solution quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Graph neural network-based learning methods can reliably guide traditional symbolic MILP solvers on branching variable selection and solver parameter configuration for the three classes of planning problems (STL, CPP, CaTL).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neuro-symbolic GNN guidance accelerates MILP solvers for STL, CPP chance constraints, and CaTL planning problems with average 20% gains in runtime and solution quality over state-of-the-art solvers.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neuro-symbolic guidance accelerates MILP motion planning for temporal logic and chance constraints by about 20 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"85be8ed3b8abe71571132dd34823a76fb99caa15e27fa0f9996f05cad6dde1c1"},"source":{"id":"2508.07515","kind":"arxiv","version":3},"verdict":{"id":"5c63d08a-7b4b-4350-8c21-dcc1eec18280","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T00:33:39.993692Z","strongest_claim":"Through extensive experiments, we show that neuro-symbolic search techniques yield scalability gains. Our approach yields substantial improvements across all three classes of planning problems, achieving an average performance gain of about 20% over state-of-the-art solver across key metrics, including runtime and solution quality.","one_line_summary":"Neuro-symbolic GNN guidance accelerates MILP solvers for STL, CPP chance constraints, and CaTL planning problems with average 20% gains in runtime and solution quality over state-of-the-art solvers.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Graph neural network-based learning methods can reliably guide traditional symbolic MILP solvers on branching variable selection and solver parameter configuration for the three classes of planning problems (STL, CPP, CaTL).","pith_extraction_headline":"Neuro-symbolic guidance accelerates MILP motion planning for temporal logic and chance constraints by about 20 percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.07515/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}