Learning Foresight without Explicit Trajectories for 3D Diffusion Policies

Papers

arxiv:2609.20669

Published on Sep 17

· Submitted by

zhongbo zhang on Sep 21

· DaLian University of Technology

Upvote

4

Authors:

Zhongbo Zhang ,

,

,

,

Lijun Wang ,

Abstract

3D diffusion policies are strong at generating geometrically grounded actions from current observations, but successful manipulation requires not only knowing what motion is feasible now, but also anticipating where the interaction is heading. Existing policies largely leave such foresight to emerge implicitly from action learning. We introduce Movement Trend Guidance, a simple but effective way to provide this foresight without introducing an explicit plan. From a short observation history, the policy learns a compact latent representation of interaction evolution. During training, sparse future gripper states supervise this representation; at inference, only the latent is retained as future-oriented conditioning alongside the current observation. The latent provides global conditioning for action generation, while an additional gated FiLM branch is used only at the UNet bottleneck. Despite adding only 3.52% more parameters to DP3, our method preserves the original dense-action and receding-horizon formulation and consistently improves upon DP3 across RoboTwin2.0, LIBERO-40, and DexArt. It reaches 62.8% vs. 56.1% in 50-task RoboTwin2.0 mixed training, 71.93% vs. 37.08% on LIBERO-40, and 72.0% vs. 49.0% on five real-robot tasks. These results show that a diffusion policy can benefit substantially from knowing where an interaction is heading, without being told exactly where to move.

View arXiv page View PDF Project pageGitHub 3 Add to collection

Community

zhangzhongbo2213

Paper author Paper submitter 2 days ago

3D diffusion policies are strong at generating geometrically grounded actions from current observations, but successful manipulation requires not only knowing what motion is feasible now, but also anticipating where the interaction is heading. Existing policies largely leave such foresight to emerge implicitly from action learning. We introduce Movement Trend Guidance, a simple but effective way to provide this foresight without introducing an explicit plan. From a short observation history, the policy learns a compact latent representation of interaction evolution. During training, sparse future gripper states supervise this representation; at inference, only the latent is retained as future-oriented conditioning alongside the current observation. The latent provides global conditioning for action generation, while an additional gated FiLM branch is used only at the UNet bottleneck. Despite adding only 3.52% more parameters to DP3, our method preserves the original dense-action and receding-horizon formulation and consistently improves upon DP3 across RoboTwin2.0, LIBERO-40, and DexArt. It reaches 62.8% vs. 56.1% in 50-task RoboTwin2.0 mixed training, 71.93% vs. 37.08% on LIBERO-40, and 72.0% vs. 49.0% on five real-robot tasks. These results show that a diffusion policy can benefit substantially from knowing where an interaction is heading, without being told exactly where to move. Code is available at \url{https://github.com/zhangzhongbo2213/movement-trend-guidance}.

librarian-bot

about 23 hours ago

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

• DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning (2026)

• Spatially Aware World Action Model via Geometric Latent Diffusion (2026)

• GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation (2026)

• JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction (2026)

• Foresight Without Seeing: Latent Futures for World Action Models (2026)

• Vid2WAM: Distilling Video Diffusion Priors into World Action Models (2026)

• MoWAM: Explicit Future Motion Prediction for Efficient World Action Models (2026)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on HF Mirror checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

4

Get this paper in your agent:

hf papers read 2609.20669

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.20669 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/2609.20669 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/2609.20669 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.