Unified Noise Steering for Efficient Human-Guided VLA Adaptation

TL;DR

UniSteer introduces a unified framework combining human guidance with noise-space reinforcement learning, significantly enhancing real-world robotic manipulation adaptation efficiency.

Contribution

It proposes a novel approximate action-to-noise inversion method enabling effective human-in-the-loop noise steering for VLA models.

Findings

Achieved success rate increase from 20% to 90% in real-world tasks.

Reduced adaptation time to an average of 66 minutes.

Outperformed existing noise-space RL and action-space human-in-the-loop baselines.

Abstract

Diffusion-based vision-language-action (VLA) models have emerged as strong priors for robotic manipulation, yet adapting them to real-world distributions remains challenging. In particular, on-robot reinforcement learning (RL) is expensive and time-consuming, so effective adaptation depends on efficient policy improvement within a limited budget of real-world interactions. Noise-space RL lowers the cost by keeping the pretrained VLA fixed as a denoising generator while updating only a lightweight actor that predicts the noise. However, its performance is still limited due to inefficient autonomous exploration. Human corrective interventions can reduce this exploration burden, but they are naturally provided in action space, whereas noise-space finetuning requires supervision over noise variables. To address these challenges, we propose UniSteer, a Unified Noise Steering framework that combines human corrective guidance with noise-space RL through approximate action-to-noise inversion. Given a human corrective action, UniSteer inverts the frozen flow-matching decoder to recover a noise target, which provides supervised guidance for the same noise actor that is simultaneously optimized via reinforcement learning. Real-world experiments on diverse manipulation tasks show that UniSteer adapts more efficiently than strong noise-space RL and action-space human-in-the-loop baselines, improving the success rate from 20% to 90% in 66 minutes on average across four real-world adaptation tasks.