AdapGrasp: A Stiffness and Grasp Affordance Dataset with a Transformer-Based Adaptive Grasp Model
Menghao Pu, Chaoqun Han, Zhiping Chai, Tiyong Zhao, Dunxuan Wu, Pu Wen, Xingxing Ke, Han Ding, Zhigang Wu
AI summary
Problem
Existing grasp datasets and models only predict initial gripper configurations, ignoring object stiffness and grasp affordance, which causes fragile object damage or unstable grasps.
Approach
The authors introduce a new dataset annotating final grasp width and grasp affordance, and train a transformer-based model with a denoising principle to predict both initial and final grasp states accurately.
Key results
- 98.04% grasp precision on the new dataset
- 2.71 pixels mean absolute error for final grasp width prediction
- 95% real-world grasping accuracy with a flexible gripper
- 19.5% accuracy improvement over baselines lacking FGW/GAW
Why it matters
Enables safer, more stable robotic manipulation of diverse objects without extra sensors, benefiting industrial, household, and medical automation.
Abstract
Robotic grasp has been employed in various industrial, household, and medical applications. However, neglecting the final grasping state and objects' stiffness and affordance, prevailing strategies predominantly emphasize the grippers’ initial state upon reaching grasp positions and often fail due to damage or grasp slippage. Here, we propose an AdapGrasp strategy with a dataset named AdapGraspDataset and a corresponding model named AdapGraspNet. The dataset focuses on the object stiffness and grasp affordance. Specifically, for objects with different stiffness properties, the corresponding final grasp width (FGW) is annotated to ensure the object's intactness. For objects’ grasp affordance properties, higher grasp affordance weight (GAW) is typically annotated closer to the centroid, increasing grasp stability. Meanwhile, to output the set of grasping configurations (initial and final grasp states) more accurately, a denoising principle is introduced to build a corresponding transformer-based model. It enables more accurate convergence of FGW and GAW, achieving a precision of 98.04% and a mean absolute final width error of 2.71 pixels. Finally, extensive real-world experiments are conducted, where the AdapGrasp strategy ensures the intactness of fragile objects and thus enhances grasping stability without any additional sensors. It achieves a grasping accuracy of 95% and yields a 19.5% improvement compared with those without FGW and GAW. The AdapGrasp strategy is publicly available at https://embodied-soft-intelligence.github.io/AdapGrasp/.