paper-with-me

Papers

DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes

2024-10-30 · Jialiang Zhang, Haoran Liu, Danshi Li, Xinqiang Yu, Haoran Geng, Yufei Ding, Jiayi Chen, He Wang

Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic benchmark, encompassing 1319 objects, 8270 scenes, and 427 million grasps. Beyond benchmarking, we also propose a novel two-stage grasping method that learns efficiently from data by using a diffusion model that conditions on local geometry. Our proposed generative method outperforms all baselines in simulation experiments. Furthermore, with the aid of test-time-depth restoration, our method demonstrates zero-shot sim-to-real transfer, attaining 90.7% real-world dexterous grasping success rate in cluttered scenes.

📄 PDF Abstract BibTeX arXiv:2410.23004

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarking

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation

2022-10-06 · Ruicheng Wang, Jialiang Zhang, Jiayi Chen, Yinzhen Xu 외

Robotic dexterous grasping is the first step to enable human-like dexterous object manipulation and thus a crucial robotic technology. However, dexterous grasping is much more under-explored than object grasping with par…

Object

UGG: Unified Generative Grasping

2023-11-28 · Jiaxin Lu, Hao Kang, Haoxiang Li, Bo Liu 외

Dexterous grasping aims to produce diverse grasping postures with a high grasping success rate. Regression-based methods that directly predict grasping parameters given the object may achieve a high success rate but ofte…

Grasp GenerationObject

DexVLG: Dexterous Vision-Language-Grasp Model at Scale

2025-07-03 · Jiawei He, Danshi Li, Xinqiang Yu, Zekun Qi 외 arxiv

As large models gain traction, vision-language-action (VLA) systems are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controll…

Zero-shot GeneralizationPose Prediction

Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping

2024-10-03 · Ziye Huang, Haoqi Yuan, Yuhui Fu, Zongqing Lu

Universal dexterous grasping across diverse objects presents a fundamental yet formidable challenge in robot learning. Existing approaches using reinforcement learning (RL) to develop policies on extensive object dataset…

GPUMixture-of-ExpertsMulti-Task LearningReinforcement Learning (RL)

SECOND-Grasp: Semantic Contact-guided Dexterous Grasping

2026-05-13 · Han Yi Shin, Heeju Ko, Jaewon Mun, Qixing Huang 외 arxiv

Achieving reliable robotic manipulation, such as dexterous grasping, requires a synergy between physically stable interactions and semantic task guidance, yet these objectives are often treated as separate, disjoint goal…