DexGANGrasp: Dexterous Generative Adversarial Grasping Synthesis for Task-Oriented Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910711858331648 |
|---|---|
| author | Feng, Qian Lema, David S. Martinez Malmir, Mohammadhossein Li, Hang Feng, Jianxiang Chen, Zhaopeng Knoll, Alois |
| author_facet | Feng, Qian Lema, David S. Martinez Malmir, Mohammadhossein Li, Hang Feng, Jianxiang Chen, Zhaopeng Knoll, Alois |
| contents | We introduce DexGanGrasp, a dexterous grasping synthesis method that generates and evaluates grasps with single view in real time. DexGanGrasp comprises a Conditional Generative Adversarial Networks (cGANs)-based DexGenerator to generate dexterous grasps and a discriminator-like DexEvalautor to assess the stability of these grasps. Extensive simulation and real-world expriments showcases the effectiveness of our proposed method, outperforming the baseline FFHNet with an 18.57% higher success rate in real-world evaluation. We further extend DexGanGrasp to DexAfford-Prompt, an open-vocabulary affordance grounding pipeline for dexterous grasping leveraging Multimodal Large Language Models (MLLMs) and Vision Language Models (VLMs), to achieve task-oriented grasping with successful real-world deployments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17348 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DexGANGrasp: Dexterous Generative Adversarial Grasping Synthesis for Task-Oriented Manipulation Feng, Qian Lema, David S. Martinez Malmir, Mohammadhossein Li, Hang Feng, Jianxiang Chen, Zhaopeng Knoll, Alois Robotics We introduce DexGanGrasp, a dexterous grasping synthesis method that generates and evaluates grasps with single view in real time. DexGanGrasp comprises a Conditional Generative Adversarial Networks (cGANs)-based DexGenerator to generate dexterous grasps and a discriminator-like DexEvalautor to assess the stability of these grasps. Extensive simulation and real-world expriments showcases the effectiveness of our proposed method, outperforming the baseline FFHNet with an 18.57% higher success rate in real-world evaluation. We further extend DexGanGrasp to DexAfford-Prompt, an open-vocabulary affordance grounding pipeline for dexterous grasping leveraging Multimodal Large Language Models (MLLMs) and Vision Language Models (VLMs), to achieve task-oriented grasping with successful real-world deployments. |
| title | DexGANGrasp: Dexterous Generative Adversarial Grasping Synthesis for Task-Oriented Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2407.17348 |