GAF: Gaussian Action Field as a Dynamic World Model for Robotic Manipulation

• URL: http://arxiv.org/abs/2506.14135v2
• Date: Mon, 23 Jun 2025 06:02:31 GMT
• Title: GAF: Gaussian Action Field as a Dynamic World Model for Robotic Manipulation
• Authors: Ying Chai, Litao Deng, Ruizhi Shao, Jiajun Zhang, Liangjun Xing, Hongwen Zhang, Yebin Liu,
• Abstract summary: Existing approaches typically follow either a Vision-to-Action (V-A) paradigm, predicting actions directly from visual inputs, or a Vision-to-3D-to-Action (V-3D-A) paradigm, leveraging intermediate 3D representations.<n>We propose a Vision-to-4D-to-Action framework that enables direct action reasoning from motion-aware 4D representations via a Gaussian Action Field (GAF)<n>Experiments demonstrate significant improvements, with achieving +11.5385 dB PSNR and -0.5574 LPIPS improvements in reconstruction quality, while boosting the average success rate in robotic manipulation tasks by 10.33%
• Score: 35.25620666966874
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate action inference is critical for vision-based robotic manipulation. Existing approaches typically follow either a Vision-to-Action (V-A) paradigm, predicting actions directly from visual inputs, or a Vision-to-3D-to-Action (V-3D-A) paradigm, leveraging intermediate 3D representations. However, these methods often struggle with action inaccuracies due to the complexity and dynamic nature of manipulation scenes. In this paper, we propose a Vision-to-4D-to-Action (V-4D-A) framework that enables direct action reasoning from motion-aware 4D representations via a Gaussian Action Field (GAF). GAF extends 3D Gaussian Splatting (3DGS) by incorporating learnable motion attributes, allowing simultaneous modeling of dynamic scenes and manipulation actions. To learn time-varying scene geometry and action-aware robot motion, GAF supports three key query types: reconstruction of the current scene, prediction of future frames, and estimation of initial action via robot motion. Furthermore, the high-quality current and future frames generated by GAF facilitate manipulation action refinement through a GAF-guided diffusion model. Extensive experiments demonstrate significant improvements, with GAF achieving +11.5385 dB PSNR and -0.5574 LPIPS improvements in reconstruction quality, while boosting the average success rate in robotic manipulation tasks by 10.33% over state-of-the-art methods. Project page: http://chaiying1.github.io/GAF.github.io/project_page/

Related papers

• DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos [52.46386528202226]
  We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM)<n>It is the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene.<n>It achieves performance on par with state-of-the-art monocular video 3D tracking methods.
  arXiv  Detail & Related papers  (2025-06-11T17:59:58Z)
• Object-centric 3D Motion Field for Robot Learning from Human Videos [56.9436352861611]
  We propose to use object-centric 3D motion field to represent actions for robot learning from human videos.<n>We present a novel framework for extracting this representation from videos for zero-shot control.<n> Experiments show that our method reduces 3D motion estimation error by over 50% compared to the latest method.
  arXiv  Detail & Related papers  (2025-06-04T17:59:06Z)
• OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation [68.11862866566817]
  3D-aware policies achieve state-of-the-art performance on precise robot manipulation tasks, but struggle with generalization to unseen instructions, scenes, and objects.<n>We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies.
  arXiv  Detail & Related papers  (2025-06-01T22:15:45Z)
• 3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks [19.026406684039006]
  Recent work has demonstrated the capabilities of fine-tuning large Vision-Language Models to learn the mapping between RGB images, language instructions, and joint space control.<n>In this work, we explore methods to improve the scene context awareness of a popular recent Vision-Language-Action model.<n>Our proposed model, 3D-CAVLA, improves the success rate across various LIBERO task suites, achieving an average success rate of 98.1$%$.
  arXiv  Detail & Related papers  (2025-05-09T05:32:40Z)
• VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation [53.63540587160549]
  VidBot is a framework enabling zero-shot robotic manipulation using learned 3D affordance from in-the-wild monocular RGB-only human videos.<n> VidBot paves the way for leveraging everyday human videos to make robot learning more scalable.
  arXiv  Detail & Related papers  (2025-03-10T10:04:58Z)
• ManiTrend: Bridging Future Generation and Action Prediction with 3D Flow for Robotic Manipulation [11.233768932957771]
  3D flow represents the motion trend of 3D particles within a scene.<n>ManiTrend is a unified framework that models the dynamics of 3D particles, vision observations and manipulation actions.<n>Our method achieves state-of-the-art performance with high efficiency.
  arXiv  Detail & Related papers  (2025-02-14T09:13:57Z)
• Prediction with Action: Visual Policy Learning via Joint Denoising Process [14.588908033404474]
  PAD is a visual policy learning framework that unifies image Prediction and robot Action.<n>DiT seamlessly integrates images and robot states, enabling the simultaneous prediction of future images and robot actions.<n>Pad outperforms previous methods, achieving a significant 26.3% relative improvement on the full Metaworld benchmark.
  arXiv  Detail & Related papers  (2024-11-27T09:54:58Z)
• SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer [57.506654943449796]
  We propose an efficient, sparse-controlled video-to-4D framework named SC4D that decouples motion and appearance. Our method surpasses existing methods in both quality and efficiency. We devise a novel application that seamlessly transfers motion onto a diverse array of 4D entities.
  arXiv  Detail & Related papers  (2024-04-04T18:05:18Z)
• Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations [7.733935820533302]
  We name the proposed model Continuous Grasping Function (CGF) CGF is learned via generative modeling with a Variational Autoencoder using 3D human demonstrations. Compared to previous planning algorithms, CGF is more efficient and achieves significant improvement on success rate when transferred to grasping with the real Allegro Hand.
  arXiv  Detail & Related papers  (2022-07-11T17:59:50Z)
• MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks [77.56526918859345]
  We present a novel framework that brings the 3D motion task from controlled environments to in-the-wild scenarios. It is capable of body motion from a character in a 2D monocular video to a 3D character without using any motion capture system or 3D reconstruction procedure.
  arXiv  Detail & Related papers  (2021-12-19T07:52:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.