pith. sign in

arxiv: 1703.09312 · v3 · pith:R2OHHUETnew · submitted 2017-03-27 · 💻 cs.RO

Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics

classification 💻 cs.RO
keywords graspsdex-netgraspdatasetobjectscloudspointrobust
0
0 comments X
read the original abstract

To reduce data collection time for deep learning of robust robotic grasp plans, we explore training from a synthetic dataset of 6.7 million point clouds, grasps, and analytic grasp metrics generated from thousands of 3D models from Dex-Net 1.0 in randomized poses on a table. We use the resulting dataset, Dex-Net 2.0, to train a Grasp Quality Convolutional Neural Network (GQ-CNN) model that rapidly predicts the probability of success of grasps from depth images, where grasps are specified as the planar position, angle, and depth of a gripper relative to an RGB-D sensor. Experiments with over 1,000 trials on an ABB YuMi comparing grasp planning methods on singulated objects suggest that a GQ-CNN trained with only synthetic data from Dex-Net 2.0 can be used to plan grasps in 0.8sec with a success rate of 93% on eight known objects with adversarial geometry and is 3x faster than registering point clouds to a precomputed dataset of objects and indexing grasps. The Dex-Net 2.0 grasp planner also has the highest success rate on a dataset of 10 novel rigid objects and achieves 99% precision (one false positive out of 69 grasps classified as robust) on a dataset of 40 novel household objects, some of which are articulated or deformable. Code, datasets, videos, and supplementary material are available at http://berkeleyautomation.github.io/dex-net .

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. HITL-D: Human In The Loop Diffusion Assisted Shared Control

    cs.RO 2026-05 unverdicted novelty 6.0

    HITL-D combines diffusion policies with human input for shared robotic control, reducing required joystick axes and improving speed and workload in manipulation tasks per a 12-participant study.

  2. GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data

    cs.RO 2025-05 unverdicted novelty 6.0

    GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer.

  3. $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

    cs.LG 2025-04 unverdicted novelty 6.0

    π_{0.5} is a VLA model that achieves long-horizon dexterous manipulation in entirely new homes through co-training on heterogeneous tasks and multi-source data including web and semantic predictions.

  4. PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction

    cs.RO 2026-05 unverdicted novelty 5.0

    PointACT proposes a 3D-aware dual-system VLA policy using multi-scale point-action interaction with bottleneck window self-attention, achieving 10% higher success rates on RLBench-10Tasks over prior pretrained VLAs.

  5. NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)

    cs.CV 2022-10 unverdicted novelty 2.0

    A literature survey of NeRF and neural field methods from 2020-2025, organized by architecture and application taxonomies with benchmarks and dataset overviews, covering both pre- and post-Gaussian Splatting periods.

  6. Object Perception and Grasping in Open-Ended Domains

    cs.RO 2019-07 unverdicted novelty 2.0

    Research agenda posing questions on open-ended object perception and grasping for robots that learn categories and affordances gradually from experiences rather than from complete upfront training sets.