GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation

1Université Paris-Saclay, CEA-List,     2École Centrale de Lyon, CNRS, LIRIS, UMR5205, Institut Universitaire de France (IUF)

2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Descriptive alt text for your teaser

GOAG Paradigm. A successful grasp on an object induces dual contact zones on both object and gripper, at the intersection of the two geometries. Our method is built on this key observation: these contact zones $(\mathcal{C}(\cdot))$ are closely the same from either perspective. GOAG capitalizes on this by training exclusively on gripper geometry, allowing it to learn a robust and generalizable grasping strategy without ever being exposed to a grasp database with specific objects geometries.

Abstract

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 and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation, a novel deep generative model that learns a compact latent representation of a specific gripper's contact 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 retrieve admissible contact areas that 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.

Video Presentation

Qualitative Results: Synthesized Grasps and Real-World Experiments

BibTeX

@inproceedings{merand2026goag,
  title={GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation},
  author={Mérand, Julien and Meden, Boris and Grossard, Mathieu and Chen, Liming},
  booktitle={2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2026},
  url={https://cea-list.github.io/goagweb/}
}