ARMFUL: Learning Whole-Arm Grasp Configurations for Single-Arm Pickup of Large Objects
Organizations: Thomas Lord Department of Computer Science, University of Southern California, USA
Abstract
Many everyday objects, such as storage boxes, baskets, and chairs, are too large or heavy for a gripper to grasp, yet a single arm can still pick them up by wrapping around and supporting them. Such grasps are hard to learn: wrapping motions are difficult to teleoperate, and existing datasets contain little whole-arm pickup data. We introduce WAG (Whole-Arm Grasp Dataset), the first large-scale dataset for single-arm pickup of large objects, with 1.7~million joint configurations across 793 objects. We sample configurations directly in joint space, execute each through squeeze and lift primitives in simulation, and stress-test survivors under active shaking and external forces. To demonstrate the utility of WAG and accomplish the whole-arm pickup task, we develop ARMFUL, a whole-arm pickup pipeline that pairs a diffusion model trained on WAG, generating whole-arm grasps from the object's point cloud, with a motion planner that reaches them collision-free before the same squeeze-and-lift execution. In simulation, ARMFUL reaches 85.4% lift success on training and 69.9% on held-out objects, and it lifts the object in 70 of 100 trials on a physical Franka arm across 10 IKEA objects.
Figures & tables
| Training object | Held-out object | |||
|---|---|---|---|---|
| Method | Lift | Perturb. | Lift | Perturb. |
| Middle-height wrap | 54.63 1.03 | 46.43 1.21 | 54.29 1.07 | 45.46 1.55 |
| NN retrieval | – | – | 58.00 1.17 | 52.89 0.67 |
| ARMFUL (LiftOnly) | 81.49 1.27 | 76.71 2.24 | 67.40 1.39 | 61.60 1.71 |
| ARMFUL | 85.40 0.85 | 81.80 1.47 | 69.86 1.60 | 63.83 1.93 |
| Object | |||||||||||
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | All | |
| Real | 10/10 | 9/10 | 6/10 | 6/10 | 7/10 | 5/10 | 9/10 | 3/10 | 7/10 | 8/10 | 70/100 |
| Sim, replayed real trajectory | 10/10 | 4/10 | 10/10 | 9/10 | 5/10 | 9/10 | 9/10 | 3/10 | 8/10 | 9/10 | 76/100 |
| Sim, ARMFUL (full pipeline) | 6/10 | 8/10 | 7/10 | 10/10 | 9/10 | 7/10 | 9/10 | 4/10 | 10/10 | 9/10 | 79/100 |
Robotic Grasping
Robotic grasping studies how robots perceive, plan, and execute stable, task-appropriate contacts with objects across varied shapes and conditions.
See all 336 papers