GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion

2026-02-26

AI Summary

This work addresses the limitations of imitation learning–based grasping policies, which often suffer from low precision and poor generalization across object geometries and environments. To overcome these challenges, the authors propose a latent diffusion policy that integrates grasp priors into the generative process. Specifically, grasp pose priors are incorporated during the reverse diffusion process, while a self-supervised reconstruction objective based on wrist-mounted camera images guides action decoding and implicitly embeds graspability priors. By innovatively combining geometric priors with diffusion models, the method significantly enhances dynamic grasping accuracy and cross-scenario, cross-object generalization. Extensive experiments in both simulation and real-world robotic settings demonstrate that the proposed approach outperforms existing baselines across multiple performance metrics.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Manipulation
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This paper focuses on enhancing the grasping precision and generalization of manipulation policies learned via imitation learning. Diffusion-based policy learning methods have recently become the mainstream approach for robotic manipulation tasks. As grasping is a critical subtask in manipulation, the ability of imitation-learned policies to execute precise and generalizable grasps merits particular attention. Existing imitation learning techniques for grasping often suffer from imprecise grasp executions, limited spatial generalization, and poor object generalization. To address these challenges, we incorporate grasp prior knowledge into the diffusion policy framework. In particular, we employ a latent diffusion policy to guide action chunk decoding with grasp pose prior, ensuring that generated motion trajectories adhere closely to feasible grasp configurations. Furthermore, we introduce a self-supervised reconstruction objective during diffusion to embed the graspness prior: at each reverse diffusion step, we reconstruct wrist-camera images back-projected the graspness from the intermediate representations. Both simulation and real robot experiments demonstrate that our approach significantly outperforms baseline methods and exhibits strong dynamic grasping capabilities.

Problem

• grasping
• imitation learning
• generalization
• precision
• robotic manipulation

Innovation

• latent diffusion
• grasp prior
• imitation learning
• self-supervised reconstruction
• grasp generalization