Grasp-Taxonomy Conditioning as a Mode Switch for Dexterous Grasping of Climbing Holds
Organizations: The authors are with the Department of Mechanical Engineering, Carnegie Mellon University.
Abstract
Dexterous grasping in robotics relies on distinct hand configurations depending on object geometry. We introduce BetaGrasp, a 3D diffusion policy that conditions a DP3-style point-cloud policy on a four-class grasp label (crimp, sloper, pinch, and jug), running on a Franka arm with a 16-DoF LEAP hand. We also introduce a climbing-hold benchmark: a spring testbed whose ratchet gives a slip-force reading in newtons. In our analysis the policy's point-cloud encoder did not separate the four holds, so the scan alone gave it little to choose a grasp from. Without the label (a DP3-style baseline), simulated rollouts from the robot's reset pose all end in a jug grasp, whatever the hold (25% correct grasp type, versus 94% for BetaGrasp). The label works as a switch for which grasp the policy performs. On 80 paired hardware trials, BetaGrasp raises average slip force from 9.6 N to 14.3 N, and grasps slipping fully off the hold drop from 44% of trials to 10%.
Figures & tables
| Method | Point-cloud input | Grasp-type conditioning | Trajectory policy |
| DP3 [ 5 ] | ✓ | ✓ | |
| Dexonomy [ 6 ] | ✓ | ✓ | |
| Grasp as You Say [ 7 ] | ✓ | ✓ | |
| OmniDexVLG [ 26 ] | ✓ | ✓ | |
| DexGraspVLA [ 27 ] | ✓ | ||
| BetaGrasp | ✓ | ✓ | ✓ |
| Avg. slip force (N) | Slipped off (%) | |||
|---|---|---|---|---|
| Hold | DP3 | BetaGrasp | DP3 | BetaGrasp |
| Crimp | 11.8 | 17.4 | 25 | 5 |
| Sloper | 5.2 | 8.2 | 100 | 35 |
| Pinch | 9.0 | 15.8 | 20 | 0 |
| Jug | 12.5 | 15.8 | 30 | 0 |
| All | 9.6 | 14.3 | 44 | 10 |
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