Robotics · Grasping · Dex-Net 4.0Benchmark detail
Grasp benchmark · Ambidextrous (jaw + suction)

Dex-Net 4.0

ambidextrousbin-pickingindustrialsim-to-real

Dex-Net 4.0 trains an "ambidextrous" grasping policy that learns when to use a parallel jaw and when to use suction, choosing per object to maximize reliability across a heaped bin. It is the headline industrial result of the Dex-Net program at UC Berkeley.

It learns from over five million synthetic grasps across 1,664 objects in simulated heaps, with domain-randomized depth rendering to bridge the sim-to-real gap.

Primary source
At a glance
Source
Mahler et al., Science Robotics 2019
Year
2019
Scale
5M+ synthetic grasps · 1,664 objects in simulated heaps
Gripper
Ambidextrous (jaw + suction)
Modality
Depth
Best-known
HW: 95% reliability · 300 MPPH (ABB YuMi)
Key results
  • HW: 95% grasp reliability on novel objects (ABB YuMi)
  • HW: ~300 mean picks per hour (MPPH)
  • Commercialized as Ambidextrous Robotics → Ambi Robotics

SIM = simulation result · HW = physical hardware. Image-wise accuracy is detection quality, not real-robot pick success. Figures cited from Mahler et al., Science Robotics 2019.

Related benchmarks

← Back to the grasping register
Parallel-jaw

GraspNet-1Billion

De-facto clutter benchmark · AnyGrasp current SOTA (AP)

Suction

SuctionNet-1Billion

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

Parallel-jaw

Dex-Net 2.0

HW: 93% on adversarial · 99% precision on 40 novel objects (YuMi)

Suction

Dex-Net 3.0

HW: 98% basic · 82% typical · 58% adversarial