This repository contains the code and documentation for the research paper titled "Teleoperating a Kinova Robot Arm Through Real-time Human Arm Motion Imitation." This project develops two advanced algorithms for teleoperating a Kinova Gen-3 robotic arm by mimicking human arm movements in real-time. The algorithms are validated through both simulation and physical experiments, demonstrating their effectiveness in various teleoperation tasks.
- Overview
- Project Structure
- Installation
- Usage
- Results
- Poster and Paper
- Acknowledgments
- License
- Contact
The repository is organized as follows:
src/
: Contains the source code, including teleoperation algorithms, ROS nodes, and simulation scripts.docs/
: Documentation files related to the project, including this README.figures/
: Figures used in the research paper, including diagrams and experiment results.config/
: Configuration files for ROS and other setup details.experiments/
: Scripts and data for the experiments conducted with the Kinova Gen-3 robot arm.poster/
: The poster presented at conferences or workshops.paper/
: The research paper published as part of this project.
Ensure you have the following installed:
- ROS (Robot Operating System): Tested with ROS Noetic on Ubuntu 20.04.
- Kinova SDK: For controlling the Kinova Gen-3 robotic arm.
- Python 3.8+: Required for running the scripts in this repository.
-
Clone the repository:
git clone https://github.com/HannahSu6/kinova-teleoperation.git cd kinova-teleoperation
-
Install the required Python packages:
pip install -r requirements.txt
-
Set up ROS workspace:
source /opt/ros/noetic/setup.bash catkin_make source devel/setup.bash
-
Configure the Kinova Gen-3 robot and motion capture system as per the documentation in the config/ directory.
-
To run the teleoperation simulation using RViz:
roslaunch kinova_teleoperation simulation.launch
For physical experiments with the Kinova Gen-3 robot arm:
-
Ensure the robot is powered on and properly connected to your system.
-
Launch the teleoperation node:
roslaunch kinova_teleoperation teleoperation.launch
-
Follow the instructions provided in the experiments/ directory to conduct specific experiments.
The experimental results demonstrate the effectiveness of the developed algorithms in mimicking human arm postures and achieving precise end-effector control. The results are documented in the results/ directory and include both simulation data and real-world experiment logs.
You can find the poster and paper related to this project in the respective directories:
Poster: Available in the poster/ directory. Paper: Available in the paper/ directory.
This project was supported by [funding agency]. Special thanks to the team at [Institution Name] for their contributions and support throughout the project.
This project is licensed under the GNU General Public License v3.0. See the LICENSE file for more information.
For any questions or collaboration inquiries, please contact:
Author1: [Qin.Su@uky.edu] Author2: [email@address.edu]
You can also watch a video demonstration of our experiments on YouTube here:
https://youtu.be/FRdjwJsbVTM?feature=shared