{"paper":{"title":"From Kinematics to Dynamics: Learning to Refine Hybrid Plans for Physically Feasible Execution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reinforcement learning refines first-order hybrid plans into dynamically feasible robot trajectories using second-order constraints.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ayal Taitler, Lidor Erez, Shahaf S. Shperberg","submitted_at":"2026-04-14T09:00:08Z","abstract_excerpt":"In many robotic tasks, agents must traverse a sequence of spatial regions to complete a mission. Such problems are inherently mixed discrete-continuous: a high-level action sequence and a physically feasible continuous trajectory. The resulting trajectory and action sequence must also satisfy problem constraints such as deadlines, time windows, and velocity or acceleration limits. While hybrid temporal planners attempt to address this challenge, they typically model motion using linear (first-order) dynamics, which cannot guarantee that the resulting plan respects the robot's true physical con"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results show that this approach can reliably recover physical feasibility and effectively bridge the gap between a planner's initial first-order trajectory and the dynamics required for real execution.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an MDP incorporating analytical second-order constraints allows reinforcement learning to consistently find feasible refinements without excessive computation or failure to converge on valid trajectories.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Reinforcement learning refines first-order hybrid plans into second-order dynamically feasible trajectories for robotic missions with deadlines and physical limits.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reinforcement learning refines first-order hybrid plans into dynamically feasible robot trajectories using second-order constraints.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4b9d9cc24daaed8fb95eca7d2cd011b868dc5f8e0a0e66033b59fc97116191d3"},"source":{"id":"2604.12474","kind":"arxiv","version":3},"verdict":{"id":"a2f8e308-62ca-40a7-9a52-fb8738bd10cb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:12:15.348514Z","strongest_claim":"Our results show that this approach can reliably recover physical feasibility and effectively bridge the gap between a planner's initial first-order trajectory and the dynamics required for real execution.","one_line_summary":"Reinforcement learning refines first-order hybrid plans into second-order dynamically feasible trajectories for robotic missions with deadlines and physical limits.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an MDP incorporating analytical second-order constraints allows reinforcement learning to consistently find feasible refinements without excessive computation or failure to converge on valid trajectories.","pith_extraction_headline":"Reinforcement learning refines first-order hybrid plans into dynamically feasible robot trajectories using second-order constraints."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.12474/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"}