Papers
arxiv:2611.26103

UniVEP: Unifying Velocity and Endpoint Prediction for Robot Manipulation

Published on Nov 19
Authors:
,
,
,
,
,
,
,
,
,
,

Abstract

UniVEP combines endpoint and velocity prediction with consistency supervision and switches from endpoint recovery to velocity refinement as noise decreases, improving success and efficiency in few-step robot action generation.

Flow-matching robot policies usually use one prediction target throughout action generation, even though recovering actions from noise and polishing nearly clean actions bring different challenges. We systematically compare velocity prediction (V), endpoint prediction (X), and velocity-weighted endpoint prediction (X--V) across multiple robot policies, benchmarks, and inference budgets. On StarVLA and LiLa-WAM, X--V works best for few-step generation, while V gains more from iterative refinement. We further uncover their complementary strengths across noise levels: clean actions have concentrated covariance spectra, endpoint predictions stay more stable under high noise, and velocity predictions offer more accurate corrections near clean actions. Inspired by these findings, we introduce UniVEP, which learns both prediction targets together with consistency supervision and switches from endpoint recovery to velocity refinement as noise drops. Each step only needs one network run, and joint training also boosts single-step endpoint generation. Tests on simulated and real-world manipulation show better success rates and efficiency. On RoboTwin, UniVEP hits 61.36% success with one StarVLA run, beating the best single-target baseline at sixteen runs (59.96%). With LiLa-WAM, two runs outperform the best sixteen-step single-target baseline and cut inference latency by 77.1%.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.26103 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.26103 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.26103 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.