SMILE: Smooth Motion for Improved Long-Horizon VLA Execution
Robotics
Summary
The authors propose SMILE, a method that improves Vision-Language-Action (VLA) models by representing actions as smooth B-spline curves instead of raw, jittery data. This approach keeps existing model structures but allows for longer action sequences with better accuracy and efficiency. They tested SMILE on several models and benchmarks, showing it reduces erratic movements and increases success rates both in simulations and real robot tasks. Overall, the authors demonstrate that using smooth coefficient-based actions helps VLA models perform longer tasks more reliably.
Authors
Jongwoo Park, E-Ro Nguyen, Kanchana Ranasinghe, Cristina Mata, Xiang Li, Michael S Ryoo
Abstract
Vision-Language-Action (VLA) models reduce inference cost by executing multiple actions per call, but longer horizons often degrade accuracy because raw chunks contain jitter and outliers. We introduce SMILE, an architecture-preserving interface that predicts B-spline coefficients and decodes them into smooth action sequences. SMILE changes only the action representation, enabling longer fixed horizons while retaining each baseline's backbone and model scale. We apply SMILE to SmolVLA, Evo1, VPP, and DAWN, improving accuracy and amortized inference efficiency across LIBERO, CALVIN, and real-world experiments. SMILE-Evo1 reaches 98.0% with a 1.1x speedup on LIBERO, while SMILE-VPP reaches an average length of 4.42 with a 1.5x speedup on CALVIN. At a matched execution horizon of 10, SMILE-SmolVLA reduces non-boundary acceleration by 78.6% and velocity sign-change rate by 42.3%. Real-world xArm tests show higher success, fewer drops, and fewer contacts. These results establish smooth coefficient-space generation as a route to accurate, efficient long-horizon VLA execution. Project page: jongwoopark7978.github.io/smilevla