GraspGen-X: Cross-Embodiment 6-DOF Diffusion-based Grasping
About
We study cross-embodiment 6-DOF robot grasping. Unlike prior works, we require the model not only to generalize to novel objects / scenes but also to novel gripper morphologies and physical grasping processes. Our method extends diffusion model based generative 6-DOF grasping models to condition on the additional gripper's representation. We propose a swept-volume heuristic for encoding the gripper. We train our cross-embodiment model with procedural grippers and a large-scale dataset of 2 Billion grasps. In simulation experiments, our model has the best zero-shot generalization to novel real-world grippers and objects over baseline methods. Our model also serves as a good initialization for fine-tuning to adapt to novel grippers. In ablations, we demonstrate the efficiency of our sweep-volume gripper representation and our procedural gripper training dataset. Last, we show zero-shot generalization to real-world novel grippers for 6-DOF grasping, surpassing baselines in cross-embodiment generalization.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 6-DOF Grasp Generation | Novel Grippers and Objects (test) | Success Rate (Parallel 2F)50.2 | 3 | |
| 6-DoF Grasping | Robotiq-2F140 Industrial Manipulator (Isolated Objects) | Grasp Success Rate85.7 | 3 | |
| 6-DoF Grasping | Robotiq-2F140 Industrial Manipulator (Clutter) | Grasp Success Rate71.4 | 3 | |
| 6-DoF Grasping | Robotiq-2F140 Industrial Manipulator (overall) | Grasp Success Rate79 | 3 |