Skip to content

PopeyePxx/MKA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Multi-Keypoint Affordance Representation for Functional Dexterous Grasping (MKA)

RAL-25-0680.mp4

Usage

Affordance (CMKA)

1. Requirements

Code is tested under Pytorch 1.12.1, python 3.7, and CUDA 11.6

pip install -r funcgra/requirements.txt 

You can download the sam_vit modles (Baidu Pan). The extraction code is: ca8a.

2. Dataset

You can download the FAH from Baidu Pan (3.35G). The extraction code is: a6nv.

3. Train

Run following commands to start training:

python train.py --data_root <PATH_TO_DATA> 

####4. You can download the pretrained modles Baidu Pan). The extraction code is: 8qvk.

Simulation (KGT)

1. Requirements

The simulation code was tested on Pytorch 1.13.1, Python 3.7, and CUDA 9.1

pip install -r requirements_sim.txt 

2. Run

cd isaacgym/python python hand_move_to_drill_hold_no_pengzhuang.py python hand_move_to_drill_press_test.py python hand_move_to_flashlight_click python hand_move_to_flashlight_hold.py 

Experiments

1. Requirements

The experiments code was tested on Pytorch 1.12.0, Python 3.9, and CUDA 11.3

pip install -r requirements_exp.txt 

2. Run

cd fungra/ python robot_control_click_the_flashlight.py python robot_control_press_the_spraybottle.py python robot_control_press_the_drill.py python robot_control_hold_the_kettle.py 

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published