Task-Context-Aware Diffusion Policy with Language Guidance for Multi-task Disassembly

Jeon Ho Kang, Sagar Joshi, Neel Dhanaraj, and Satyandra K. Gupta

University of Southern California

Baseline code for diffusion policy was derived from Diffusion Policy

Dependencies

Create Conda Environment (Recommended) and run:

$ pip install requirements.txt

Real Robot

For all demonstrations, we used KUKA IIWA 14 Robot

Training Your Own Policy

After loading your own zarr file or ours in real_robot_network.py

$ python train_real.py

You can select or create your own Config file for training configuration

Acknowledgement

• Diffusion policy was adapted from Diffusion Policy

For Demonstration Purposes use the regular folders that do not contain the Real tag

Those are for PushTEnv demonstration.

All Real tages are for real robot implementation

However, data_util.py is shared amongst them.

Also checkout modality for main implementation for the time being.