Towards Automated Chicken Deboning via Learning-based Dynamically-Adaptive 6-DoF Multi-Material Cutting
Zhaodong Yang1,
Ai-Ping Hu1,2,
Harish Ravichandar1
1Georgia Institute of Technology
2Georgia Tech Research Institute
conda create -n deformable python=3.9.19
conda activate deformable
pip install matplotlib
pip install scipy
pip install taichi
pip install stable-baselines3
For hardware deploy on UR5 robot:
pip install math3d ikpy imutils pyserial bitstring pymodbus pyrealsense2 opencv-python
To run the simulation without residual policy:
python -m mpm3d.mpm3d_gym_wrapped.py
Run the residual policy training:
python train_residual.py
To train with specific training steps and without rendering:
python train_residual.py --training_steps=50000 --headless
To evaluate the trained model:
python train_residual.py --eval --model_dir=./replace/with/your/checkpoint/directory
python -m mpm2d.mpm2d.py
Drag the 2D "knife" with your mouse to cut through the material:
