ARDuP: Active Region Video Diffusion for Universal Policies

TL;DR

ARDuP introduces a novel video diffusion framework that emphasizes active regions to improve policy learning for decision-making tasks, eliminating manual annotations and enhancing focus on interaction areas.

Contribution

The paper presents a new active region video diffusion approach that integrates active region conditioning with latent diffusion models for improved policy learning.

Findings

Significant success rate improvements in simulated tasks

Effective automatic active region discovery from motion cues

Generation of realistic and task-relevant video plans

Abstract

Sequential decision-making can be formulated as a text-conditioned video generation problem, where a video planner, guided by a text-defined goal, generates future frames visualizing planned actions, from which control actions are subsequently derived. In this work, we introduce Active Region Video Diffusion for Universal Policies (ARDuP), a novel framework for video-based policy learning that emphasizes the generation of active regions, i.e. potential interaction areas, enhancing the conditional policy's focus on interactive areas critical for task execution. This innovative framework integrates active region conditioning with latent diffusion models for video planning and employs latent representations for direct action decoding during inverse dynamic modeling. By utilizing motion cues in videos for automatic active region discovery, our method eliminates the need for manual annotations of active regions. We validate ARDuP's efficacy via extensive experiments on simulator CLIPort and the real-world dataset BridgeData v2, achieving notable improvements in success rates and generating convincingly realistic video plans.