SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies
For robotics practitioners using VLA policies, SEAM provides a training-free method to smooth action chunk transitions without sacrificing performance.
SEAM addresses multimodal bifurcation in VLA policies that use action chunking, where adjacent chunks can produce discontinuous trajectories. It reduces boundary jerk by 28% and chunk transition discontinuity by 27% on LIBERO-10 with pi_0.5, while maintaining task success and computational cost.
Vision-Language-Action (VLA) policies that execute fixed-length action chunks can exhibit multimodal bifurcation: a cross-chunk inconsistency in which adjacent chunks generated from independent Gaussian latents can converge to incompatible trajectory modes, producing abrupt discontinuities at chunk boundaries. Existing remedies either require backpropagation through the policy at each denoising step, rely on rejection sampling, or require retraining, each trading computational cost or task reliability for smoother transitions. We propose SEAM (Smooth Execution of Action-Chunked Motion), a training-free inference-time method for flow matching VLAs. SEAM exploits a simple synchronous-execution insight: after the robot consumes the executed prefix, the previous chunk's unexecuted tail is already available as an analytic consistency reference. Its core mechanism, Velocity-guided Loss Steering (VLS), derives a time-dependent target from this tail and applies a closed-form correction after each Euler step without backpropagating through the policy network. On LIBERO-10 with pi_0.5, SEAM reduces boundary jerk by 28%, reduces chunk transition discontinuity by 27%, preserves baseline-level task success, and keeps denoising-loop cost near the unguided baseline.