Sandbox to Simulate Grasping in Gazebo with the iCub

🚶🏻‍♂️ Walkthrough

This sandbox allows you to experiment with iCub performing basic object grasping within the Gazebo simulator.

☁ Instructions to run the sandbox on the web

Here's below a quick how-to guide. For a more detailed description of the grasping pipeline, please refer to the 🚶🏻‍♂️ Walkthrough.

1. To get started with the sandbox, click on the following badge:

   

2. Once the sandbox workspace is ready, do the following:

   1. Click on the PORTS tab.
   2. Click on the browser icon 🌐 next to the nvc port 6080 to open the desktop view.

3. Within the terminal, build and install the project:

   cmake -S . -B build
   cmake --build build/ --target install

4. Run the grasping experiment:

   icub-grasp.sh

   You will see the robot in action in the desktop view.

Also:

• You can run a systematic test with always the same object in the same pose by specifying the option test:

  icub-grasp.sh test

  Afterward, inspect relevant quantities logged in /tmp/icub-gazebo-grasping-sandbox.INFO.
• If needed, you can clean up hanging resources by specifying the option clean:

  icub-grasp.sh clean

🔽 Instructions to run the sandbox locally

ℹ Manual installation

If you want to install the sandbox manually to perform specific customization (e.g., enable GPU), please refer to the recipe contained in the Dockerfile.

📚 Cite the sandbox

In case you use this sandbox for your work, please quote it within any resulting publication by citing this repository and/or the paper where you can find the original implementation of the grasping method:

• P. D. H. Nguyen, F. Bottarel, U. Pattacini, M. Hoffmann, L. Natale and G. Metta, "Merging Physical and Social Interaction for Effective Human-Robot Collaboration," 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), Beijing, China, 2018, pp. 1-9, doi: 10.1109/HUMANOIDS.2018.8625030.

🔘 Click to show other papers describing foundamental components used in the sandbox

Motion control of iCub in the operational space:

• U. Pattacini, F. Nori, L. Natale, G. Metta and G. Sandini, "An experimental evaluation of a novel minimum-jerk cartesian controller for humanoid robots," 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei, 2010, pp. 1668-1674, doi: 10.1109/IROS.2010.5650851.
• A. Roncone, U. Pattacini, G. Metta and L. Natale, "A Cartesian 6-DoF Gaze Controller for Humanoid Robots", Proceedings of Robotics: Science and Systems, Ann Arbor, MI, June 18-22, 2016, doi: 10.15607/RSS.2016.XII.022.

Interoperability between iCub and Gazebo:

• M. Hoffman E., S. Traversaro, A. Rocchi, M. Ferrati, A. Settimi, F. Romano, L. Natale, A. Bicchi, F. Nori and N. G. Tsagarakis, "Yarp Based Plugins for Gazebo Simulator". In: Hodicky J. (eds) Modelling and Simulation for Autonomous Systems. MESAS 2014. Lecture Notes in Computer Science, vol 8906. Springer, Cham. pp 333-346, doi: 10.1007/978-3-319-13823-7_29.

📃 List of works built on the sandbox

👨🏻‍💻 Maintainers

This repository is maintained by:

	@pattacini

🙏 Acknowledgements

• This sandbox was made possible thanks to xEnVrE of the HSP@IIT group for his contributions to robotology/icub-models on simulating visuo-manipulation tasks in Gazebo.
• Inspired by the simplified simulation environment available in shadow-robot/smart_grasping_sandbox.

🆕 Contributing

Check out our CONTRIBUTING guidelines.