Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Grasping with a Humanoid Hand
This project is about robust grasping with a self adaptive humanoid hand. The goal is to evaluate and implement methods for gripping reliably handles and rails but also objects for pick and place tasks.
Keywords: Humanoid hand, grasp generation
Using a compliant and adaptive gripper is well suited for grasping a variety of objects with different shapes. Therefore, we utilize an anthropomorphic hand, which can adapt to the object shape through its underactuated and tendon based design [1]. We want to employ this gripper for several tasks in mobile manipulation and construction in unstructured environment. The aim of this project is to develop strategies on how we can achieve stable grasps on objects without prior knowledge. For this task, (depth-)cameras mounted to the wrist may be used to guide the hand to the object and force sensors could give feedback about the quality of the grasp. The proposed methods can be experimentally verified on our existing manipulator.
[1] http://www.qbrobotics.com/products/qbhand/
Using a compliant and adaptive gripper is well suited for grasping a variety of objects with different shapes. Therefore, we utilize an anthropomorphic hand, which can adapt to the object shape through its underactuated and tendon based design [1]. We want to employ this gripper for several tasks in mobile manipulation and construction in unstructured environment. The aim of this project is to develop strategies on how we can achieve stable grasps on objects without prior knowledge. For this task, (depth-)cameras mounted to the wrist may be used to guide the hand to the object and force sensors could give feedback about the quality of the grasp. The proposed methods can be experimentally verified on our existing manipulator.
[1] http://www.qbrobotics.com/products/qbhand/
- Setup of the simulation environment.
- Evaluation and integration of needed sensors (camera, depth camera, force sensor, tactile pads,...).
- Development of grasping strategies for variety of tasks.
- Evaluation and demonstration of the methods on the real robot.
- Setup of the simulation environment. - Evaluation and integration of needed sensors (camera, depth camera, force sensor, tactile pads,...). - Development of grasping strategies for variety of tasks. - Evaluation and demonstration of the methods on the real robot.
We seek a highly motivated student with skills in C++ programming. Experience with ROS is beneficial.
We seek a highly motivated student with skills in C++ programming. Experience with ROS is beneficial.
Please contact Martin Wermelinger (martin.wermelinger@mavt.ethz.ch) for any questions. Your application should include a very brief motivational statement, your transcript of records and your CV.
Please contact Martin Wermelinger (martin.wermelinger@mavt.ethz.ch) for any questions. Your application should include a very brief motivational statement, your transcript of records and your CV.