{"ID":6497571,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09648","arxiv_id":"2607.09648","title":"B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations","abstract":"In this work, we present B-spline Policy (BSP), an action representation designed for accelerating robot manipulation policies. Rather than predicting discrete-time action chunks, BSP parameterizes actions as continuous B-spline curves defined by a set of knots and control points. This representation yields smooth, time-continuous trajectories that can be temporally scaled and executed by low-level controllers at higher frequencies and speeds. We show that B-spline-parameterized actions can be seamlessly integrated into standard policy learning pipelines by directly predicting B-spline parameters. Experiments on simulated and real-world tasks demonstrate that BSP significantly reduces task completion time, achieving substantial improvements over baseline methods while maintaining strong success rates. More results: https://b-spline-policy.github.io","short_abstract":"In this work, we present B-spline Policy (BSP), an action representation designed for accelerating robot manipulation policies. Rather than predicting discrete-time action chunks, BSP parameterizes actions as continuous B-spline curves defined by a set of knots and control points. This representation yields smooth, tim...","url_abs":"https://arxiv.org/abs/2607.09648","url_pdf":"https://arxiv.org/pdf/2607.09648v1","authors":"[\"Xiaoshen Han\",\"Haoyu Xiong\",\"Haonan Chen\",\"Chaoqi Liu\",\"Antonio Torralba\",\"Yuke Zhu\",\"Yilun Du\"]","published":"2026-07-10T17:46:32Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}