{"paper":{"title":"Automated Curriculum Design for High-dimensional Human Motor Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A framework using motor learning models and stochastic nonlinear MPC designs curricula that speed skill acquisition by about 23 percent over random schedules.","cross_cats":["cs.HC","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Ankur Kamboj, Rajiv Ranganathan, Vaibhav Srivastava, Xiaobo Tan","submitted_at":"2026-05-14T04:47:24Z","abstract_excerpt":"Designing effective practice schedules for high-dimensional motor learning tasks remains a challenge, especially when skill states are unobservable and task performance may not reflect the true learning. We propose an automated curriculum design framework that combines a human motor learning model and personalized real-time skill estimation with Stochastic Nonlinear Model Predictive Control in \\emph{de-novo} (novel) motor learning paradigms. We validated our framework both through simulations and human-subject studies (N = 36) using a hand exoskeleton. Our proposed approach accelerates skill a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our proposed approach accelerates skill acquisition by ∼23%, and ∼17% when compared to a random curriculum and a performance heuristics-based curriculum, respectively.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The human motor learning model combined with real-time skill estimation accurately captures unobservable skill states in de-novo tasks, allowing the stochastic nonlinear MPC to select effective curricula.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A model-based curriculum using stochastic nonlinear MPC and real-time skill estimation accelerates high-dimensional motor learning by ~23% versus random schedules and ~17% versus performance-based heuristics in simulations and N=36 human experiments with a hand exoskeleton.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A framework using motor learning models and stochastic nonlinear MPC designs curricula that speed skill acquisition by about 23 percent over random schedules.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"85c6219b315045cef1681a55cdb8652ca4b411783c91e6b3b8d25b492ee4caab"},"source":{"id":"2605.14367","kind":"arxiv","version":1},"verdict":{"id":"fa714de5-4581-49d1-8eca-ef12610944c4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:31:58.003011Z","strongest_claim":"Our proposed approach accelerates skill acquisition by ∼23%, and ∼17% when compared to a random curriculum and a performance heuristics-based curriculum, respectively.","one_line_summary":"A model-based curriculum using stochastic nonlinear MPC and real-time skill estimation accelerates high-dimensional motor learning by ~23% versus random schedules and ~17% versus performance-based heuristics in simulations and N=36 human experiments with a hand exoskeleton.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The human motor learning model combined with real-time skill estimation accurately captures unobservable skill states in de-novo tasks, allowing the stochastic nonlinear MPC to select effective curricula.","pith_extraction_headline":"A framework using motor learning models and stochastic nonlinear MPC designs curricula that speed skill acquisition by about 23 percent over random schedules."},"references":{"count":36,"sample":[{"doi":"","year":2018,"title":"R. A. Schmidt, T. D. Lee, C. Winstein, G. Wulf, and H. N. Zelaznik, Motor Control and Learning: A Behavioral Emphasis . Human Kinetics, 2018","work_id":"eb863647-c8ee-411e-a1e2-20ab6b500bb7","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Individualized challenge point practice as a method to aid motor sequence learning,","work_id":"84894eeb-c1e7-4b91-a7c1-ed0c8827afff","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Dynamic difficulty adjustment (DDA) in computer games: A review,","work_id":"f312cde9-6d25-46a6-98e4-939b1f8b1af8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Learning control in robot-assisted rehabilitation of motor skills: A review,","work_id":"04d8bb19-d5b1-4dbb-9cda-df770c6eef7f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Interactive curriculum learning increases and homogenizes motor smoothness,","work_id":"415e2b6f-edff-455b-9c87-8b223cfca615","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":36,"snapshot_sha256":"e5508f6f964b8dfe75d77350969d685ceb50cb35ec470f9020f7c695fa39e45d","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c48d92d99eb58ab8536e153efffbb55879e66513f30398e85cf6d70da74057d8"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}