Re: [ros-users] A small contribution related to teleoperatio…

Top Page
Attachments:
Message as email
+ (text/plain)
+ (text/html)
Delete this message
Reply to this message
Author: User discussions
Date:  
To: User discussions
Subject: Re: [ros-users] A small contribution related to teleoperation
Awesome, I'm looking forward to it! Please let me know when I can help test and demo your work, and do keep in touch :)

On Mar 9, 2011, at 12:33 AM, Marcus Liebhardt wrote:

> Dear ROS community,
>
> First of all, I want to thank all developers and contributors very much for all your efforts you put into the ROS project! Two months ago, I started to work with ROS and it was a pleasure to learn it. The wiki, the tutorials and the information provided by the mailing lists allowed me to progress very fast.
>
> I just submitted an enhancement patch (#5063) for the pr2_mechanism_model package, which adds a new helper class for trees. This class is derived from and structured like the one for chains written by Stuart Glaser and Wim Meeussen. I hope, it is a useful contribution. Please let me know, if you like me to apply changes!
>
> To give you an idea, where my motivation comes from and in which context that helper class fits, I would like to give you a short introduction to my work. My intent is also to get into contact with developers, who work on the same or related fields. I would be happy to share ideas, problems and hopefully solutions as well! :-)
>
> I am doing my master thesis on unilateral teleoperation here at PAL Robotics . More specific, I will focus on creating a controller to move the upper body of an humanoid robot. We use Microsoft's Kinect as the input device for the operator's commands.
> Similar projects have already been published in the ROS 3D Contest, like Halit Bener SUAY's "Humanoid Robot Control and Interaction" and the various contributions of Taylor Veltrop about "Humanoid teleoperation".
> Among the key problems, which I will address in the next four months, are adjustment to different users, joint limit avoidance and optimal configuration(s) concerning expressiveness and precision.
> To implement this controller I am working with ROS and KDL. For the above mentioned challenges there is still work to do with the utilised inverse kinematics solvers. Therefore I am also in contact with KDL developers (see related discussions on the KDL-users and KDL-developers mailing list).
>
> So, thanks for taking the time to read this long email and please let me know, if you have any questions and/or you would like me to provide more information about the project. I am looking forward to pool development efforts!
>
>
> With best wishes from Barcelona,
>
> Marcus Liebhardt
>
> _______________________________________________
> ros-users mailing list
>
> https://code.ros.org/mailman/listinfo/ros-users