Robotics · Grasping · Dex-Net 3.0Benchmark detail
Grasp benchmark · Suction

Dex-Net 3.0

suctionseal modelGQ-CNNsynthetic training

Dex-Net 3.0 extended the GQ-CNN approach to suction grasping by introducing a quasi-static analytic model of the suction-cup seal: it predicts whether a seal will form on the local surface and whether that seal can resist the wrench imposed by gravity and dynamics.

Its three-tier object split — basic, typical, adversarial — exposed how sharply suction reliability falls as surfaces become porous, curved, or non-flat.

Primary source
At a glance
Source
Mahler et al., ICRA 2018
Year
2018
Scale
2.8M point clouds · 1,500 models · analytic suction-seal labels
Gripper
Suction
Modality
Depth · point cloud
Best-known
HW: 98% basic · 82% typical · 58% adversarial
Key results
  • HW: 98% success on basic objects
  • HW: 82% on typical objects · 58% on adversarial objects
  • Introduced an analytic suction-seal + wrench-resistance model

SIM = simulation result · HW = physical hardware. Image-wise accuracy is detection quality, not real-robot pick success. Figures cited from Mahler et al., ICRA 2018.

Related benchmarks

← Back to the grasping register
Suction

SuctionNet-1Billion

HW: 80.65% grasp success · 100% object clearance (their method)