Papers
arxiv:2506.13922

DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance

Published on Jun 16
· Submitted by MaxDu on Jun 18
Authors:

Abstract

DynaGuide, a steering method using an external dynamics model, enhances diffusion policies by allowing them to adapt to multiple objectives and maintain robustness, outperforming goal-conditioning especially with low-quality objectives.

AI-generated summary

Deploying large, complex policies in the real world requires the ability to steer them to fit the needs of a situation. Most common steering approaches, like goal-conditioning, require training the robot policy with a distribution of test-time objectives in mind. To overcome this limitation, we present DynaGuide, a steering method for diffusion policies using guidance from an external dynamics model during the diffusion denoising process. DynaGuide separates the dynamics model from the base policy, which gives it multiple advantages, including the ability to steer towards multiple objectives, enhance underrepresented base policy behaviors, and maintain robustness on low-quality objectives. The separate guidance signal also allows DynaGuide to work with off-the-shelf pretrained diffusion policies. We demonstrate the performance and features of DynaGuide against other steering approaches in a series of simulated and real experiments, showing an average steering success of 70% on a set of articulated CALVIN tasks and outperforming goal-conditioning by 5.4x when steered with low-quality objectives. We also successfully steer an off-the-shelf real robot policy to express preference for particular objects and even create novel behavior. Videos and more can be found on the project website: https://dynaguide.github.io

Community

Paper author Paper submitter

Normally, changing robot policy behavior means changing its weights or relying on a goal-conditioned policy. What if there was another way?

Check out DynaGuide, a novel policy steering approach that works on any pretrained diffusion policy. https://dynaguide.github.io/

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.13922 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.13922 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.13922 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.