PROJECT NOT UNDER ACTIVE MANAGEMENT

This project will no longer be maintained by Intel.
Intel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project.
Intel no longer accepts patches to this project.
If you have an ongoing need to use this project, are interested in independently developing it, or would like to maintain patches for the open source software community, please create your own fork of this project.

ContactInsert

This repository has the training and deployment code as well as trained models for the paper

"Zero-Shot Transfer of Haptics-based Object Insertion Policies" - Samarth Brahmbhatt, Ankur Deka, Andrew Spielberg, and Matthias Müller, ICRA 2023.

The code is divided into directories.

• Simulation training:
  • rl (entry point): Simulation environment and training framework, including reproduction of the ICRA 2023 paper.
  • robosuite: Fork of robosuite which implements policy inference delay randomization.
• Real robot deployment:
  • ros_controllers (entry point): ROS package implementing operational space control for the Frank Emika Panda robot.
  • ros_drivers_utils: Soft Robotics mGrip gripper ROS driver, and some other utilities.
  • arduino: Soft Robotics mGrip gripper control circuit and Arduino code.

Code contributors

• Samarth Brahmbhatt
• Ankur Deka
• Andrew Spielberg

Citation

@InProceedings{Brahmbhatt_2023_ICRA,
author = {Brahmbhatt, Samarth and Deka, Ankur and Spielberg, Andrew and M{\"u}ller, Matthias},
title = {Zero-Shot Transfer of Haptics-based Object Insertion Policies},
booktitle = {International Conference on Robotics and Automation (ICRA)},
month = {June},
year = {2023}
}