Disentangled Point Diffusion for Precise Object Placement

2026-04-13

AI Summary

This work addresses the limited generalization of end-to-end robotic manipulation policies to novel object geometries and their insufficient placement accuracy by proposing a target-centric, hierarchically decoupled point diffusion framework. The approach replaces conventional SE(3) diffusion paradigms with a dense Gaussian mixture model to construct spatially dense priors and explicitly decouples object geometry from the placement coordinate frame. This architecture substantially improves pose prediction accuracy and cross-object generalization, achieving state-of-the-art performance on both simulated and real-world high-precision insertion tasks in industrial settings. Furthermore, the method successfully extends to non-rigid cloth hanging tasks, demonstrating its broad applicability and robustness across diverse manipulation scenarios.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Diffusion Models for Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent advances in robotic manipulation have highlighted the effectiveness of learning from demonstration. However, while end-to-end policies excel in expressivity and flexibility, they struggle both in generalizing to novel object geometries and in attaining a high degree of precision. An alternative, object-centric approach frames the task as predicting the placement pose of the target object, providing a modular decomposition of the problem. Building on this goal-prediction paradigm, we propose TAX-DPD, a hierarchical, disentangled point diffusion framework that achieves state-of-the-art performance in placement precision, multi-modal coverage, and generalization to variations in object geometries and scene configurations. We model global scene-level placements through a novel feed-forward Dense Gaussian Mixture Model (GMM) that yields a spatially dense prior over global placements; we then model the local object-level configuration through a novel disentangled point cloud diffusion module that separately diffuses the object geometry and the placement frame, enabling precise local geometric reasoning. Interestingly, we demonstrate that our point cloud diffusion achieves substantially higher accuracy than a prior approach based on SE(3)-diffusion, even in the context of rigid object placement. We validate our approach across a suite of challenging tasks in simulation and in the real-world on high-precision industrial insertion tasks. Furthermore, we present results on a cloth-hanging task in simulation, indicating that our framework can further relax assumptions on object rigidity.

Problem

• object placement
• generalization
• precision
• object geometry
• robotic manipulation

Innovation

• disentangled diffusion
• point cloud diffusion
• object placement
• Dense GMM
• geometric generalization