Repository files navigation

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

We make use of theGitpod Cloud IDE as infrastructure. Find out more onYARP-enabled Gitpod workspaces.

Here's below a quick how-to guide; please, refer to the section🚶🏻‍♂️ Walkthrough for an extensive video tutorial 🎥

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

   

2. Once the sandbox workspace is ready, build and install the project:

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

3. Run the grasping experiment:

   icub-grasp.sh

4. You can run a systematic test with always the same object in the same pose by specifying the optiontest:

   icub-grasp.sh test

   Afterward, inspect relevant quantities logged in/tmp/icub-gazebo-grasping-sandbox.INFO.

5. If needed, you can clean up hanging resources by specifying the optionclean:

   icub-grasp.sh clean

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

In case you use this sandbox for your work, pleasequote it within any resulting publication by citing thisrepository and/or the paper where you can find theoriginal 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.

This repository is maintained by:

	@pattacini

• This sandbox was made possible thanks toxEnVrE of theHSP@IIT group for his contributions torobotology/icub-models on simulating visuo-manipulation tasks in Gazebo.
• Inspired by the simplified simulation environment available inshadow-robot/smart_grasping_sandbox.

Check out ourCONTRIBUTING guidelines.