GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation
Summary
GOAG is a deep generative grasp planner that learns a gripper-specific contact surface distribution to sample valid grasps for unseen objects without object-specific training, achieving state-of-the-art results on the MultiDex dataset for dexterous robotic manipulation.
View Cached Full Text
Cached at: 08/21/26, 04:11 PM
Paper page - GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation
Source: https://huggingface.co/papers/2608.19759
Abstract
GOAG is an object-agnostic deep generative grasp planner that learns a gripper-specific contact surface distribution to sample valid grasps for unseen objects without object-specific training.
Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to generalize to new objects because they are trained on limited, object-specific datasets. We introduce a fundamentally different approach, grounded in the observation that the gripper and the object share identical surface geometry at their mutual contact points. We propose GOAG: Generative andObject-Agnostic Grasp PlannerforDexterous Robotic Manipulation, a noveldeep generative modelthat learns a compactlatent representationof a specific gripper’scontact surface distribution, enabling the efficient sampling of valid grasp configurations without relying on object-specific training data. We show that by introducing object features only at inference time, our model can effectively retrieveadmissible contact areasthat are compatible with the gripper’s capabilities. We validate our approach through extensive experiments on established grasp protocols in both simulated and real-world scenarios, demonstrating its effectiveness with different grippers from the literature. Our method delivers state-of-the-art results on the objects from the MultiDex dataset, achieving an average success rate of 86.93%. It offers significantly faster processing when generating numerous grasps, while matching the performance of leading approaches specifically trained on this dataset. Unlike these methods, our approach does not rely on object-specific training data, highlighting the advantages of object-agnostic learning. It effectively addresses the generalization challenges faced by traditional data-driven grasp planners. Code and videos are available on our project website https://cea-list.github.io/goagweb/ .
View arXiv pageView PDFProject pageGitHub3Add to collection
Get this paper in your agent:
hf papers read 2608\.19759
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.19759 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.19759 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.19759 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
CoToGrasp is a generative framework that synthesizes diverse, stable grasps conditioned on specific contact topologies using a canonical workspace for zero-shot generalization, outperforming existing planners on the DexGraspNet dataset.
Agentic RAG-VLM: Affordance-Aware Retrieval-Augmented Generation with Self-Reflective Planning for Robotic Grasping
This paper introduces Agentic RAG-VLM, a unified framework that integrates retrieval-augmented generation with vision-language models and self-reflective planning for generalizable robotic grasping in cluttered environments, achieving 78.3% success rate.
Grabette: an open system to record robot-manipulation data
Grabette is an open, low-cost system for recording robot manipulation data using a handheld gripper and camera, aiming to build a shared dataset for robot learning.
Domain randomization and generative models for robotic grasping
Researchers explore a data generation pipeline using domain randomization and procedurally generated objects to train a deep neural network for robotic grasp planning. The proposed autoregressive model achieves >90% success on unseen objects in simulation and 80% in the real world, despite being trained only on random simulated objects.
Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
Open-AoE is an open, community-oriented egocentric manipulation dataset and toolchain that spans from smartphone capture to model training, providing approximately 2,000 hours of manipulation video with annotations and downstream tools for embodied learning.