GROOVE reduces jerky robotic arm motions for smoother task execution
GROOVE: Geometry-Guided Reduction of Operational-Space Jerk in VLA Execution
Robotics
Summary
When robots follow a set of commands, their movements can be jerky and cause wear or errors. The authors present GROOVE, a software tool that adjusts the robot’s hand path in real time to make movements smoother without changing the original commands. GROOVE uses math to find better directions that reduce sudden changes in speed or rotation. Tests show that GROOVE lowers jolts in robot arm motions while maintaining or improving the success of tasks.
What this means in practice
- •For industrial robot programmers: Reduce robotic arm jerks during complex multi-step tasks for smoother and more reliable manufacturing operations.
- •For robotic automation engineers: Improve robotic tool motion smoothness without retraining models, enabling real-time correction of actuator stress in assembled systems.
Authors
Sangho Yun, Minsoo Kim, Minwoo Cho, Hwanjo Yu
Abstract
Chunked vision language action (VLA) policies execute several commands per query, but jerk within chunks and across replanning boundaries can induce oscillatory motion and sharp actuator transients. We present GROOVE, an online regulator that searches directional correction regions around the raw three dimensional end effector (EEF) path, without retraining or additional VLA inference. It optimizes the new chunk using delivered commands as boundary conditions, reducing boundary and within chunk jerk while bounding cumulative translation and local axis angle deviation from the raw plan after every command. Using quadratic programs (QPs), GROOVE generates a cube reference and thirteen directional candidates, then selects the one with the lowest command space jerk under a reference relative deviation cap. On a held out LIBERO benchmark, GROOVE achieves the largest reductions among the evaluated methods, reducing translational and rotational EEF jerk by 33.02% and 43.42%, respectively, with task success of 95.75% versus 93.75% for raw execution. Across 50 matched UR5e pairs with measured execution timing, it reduces translational and rotational tool center point (TCP) jerk by 16.39% and 19.49% and joint current slew by 29.09%.