Article

AdaPolicy: Action-Driven Anticipatory Robot Policies via Next-Chunk Prediction

AdaPolicy proposes an action-driven anticipatory policy framework that shapes future-aware representations through cascaded next-chunk prediction, requiring no encoding of future observations during training and adding zero inference-time overhead. The method achieves consistent gains on MetaWorld, RoboTwin 2.0, LIBERO, and real-world deployment, with improvements of up to 14 percentage points on millimeter-precision tasks such as headphone assembly and shoelace threading.

Part of the event: AdaPolicy: Action-Driven Anticipatory Robot Policy

This page provides a summary and source link only.