{"paper":{"title":"Reactive Motion Generation via Phase-varying Neural Potential Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PNPF learns phase-conditioned neural potential functions from demonstrations to produce stable, reactive vector fields that handle state revisits in point-to-point, periodic, and 6D robotic tasks.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ahmet Tekden, Aude Billard, Dimitrios Kanoulas, Yasemin Bekiroglu","submitted_at":"2026-04-29T09:05:27Z","abstract_excerpt":"Dynamical systems (DS) methods for Learning-from-Demonstration (LfD) provide stable, continuous policies from few demonstrations. First-order dynamical systems (DS) are effective for many point-to-point and periodic tasks, as long as a unique velocity is defined for each state. For tasks with intersections (e.g., drawing an \"8\"), extensions such as second-order dynamics or phase variables are often used. However, by incorporating velocity, second-order models become sensitive to disturbances near intersections, as velocity is used to disambiguate motion direction. Moreover, this disambiguation"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"PNPF generalizes effectively across point-to-point, periodic, and full 6D motion tasks, outperforms existing baselines on trajectories with intersections, and demonstrates robust performance in real-time robotic manipulation under external disturbances.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a phase variable can be reliably estimated directly from state progression in a way that disambiguates motion direction at intersections without introducing sensitivity to disturbances or failing on near-identical state pairs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PNPF learns phase-conditioned neural potential functions from demonstrations to produce stable, reactive vector fields that handle state revisits in point-to-point, periodic, and 6D robotic tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"9c098d1f62944c3a12a22b38ea23eb82c1cc831f4d7997de6ab64e7d3e6aebaf"},"source":{"id":"2604.26450","kind":"arxiv","version":1},"verdict":{"id":"6093ecae-a60f-47fb-a22a-c7d31fd87980","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T11:53:20.893965Z","strongest_claim":"PNPF generalizes effectively across point-to-point, periodic, and full 6D motion tasks, outperforms existing baselines on trajectories with intersections, and demonstrates robust performance in real-time robotic manipulation under external disturbances.","one_line_summary":"PNPF learns phase-conditioned neural potential functions from demonstrations to produce stable, reactive vector fields that handle state revisits in point-to-point, periodic, and 6D robotic tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a phase variable can be reliably estimated directly from state progression in a way that disambiguates motion direction at intersections without introducing sensitivity to disturbances or failing on near-identical state pairs.","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.26450/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"}