Téma:Humanoid robot autonomous body exploration
Vedoucí:Mgr. Matěj Hoffmann Ph.D., Ing. Zdeněk Straka
Vypsáno jako:Práce v týmu a její organizace
Popis:This project will be conducted on the Nao humanoid robot. The main idea is that the robot will explore its own body by self-observation and in particular self-touch.
The main tasks will be:
1. Get acquainted with the Nao robot simulator (Webots or Gazebo).
2. Study the robot kinematics and inverse kinematics and investigate controllers that would generate self-touch configurations.
3. Get acquainted with the real Nao robot.
4. Test safe self-touch behaviors on the real robot employing closed-loop control (relying on motor loads as feedback, for example).
5. Explore the possibilities of different sensory modalities in delivering information about the robot’s kinematic configuration: cameras, infra-red sensors, ultra-sonic sensors, joint encoders.
6. Optional: The robot will have an artificial skin array mounted on it. If this is delivered as planned, the students will be able to work with this new modality as well.
Literatura:Hoffmann, M.; Marques, H.; Hernandez Arieta, A.; Sumioka, H.; Lungarella, M. & Pfeifer, R. (2010), 'Body schema in robotics: a review', IEEE Trans. Auton. Mental Develop. 2 (4), 304-324. Roncone, A.; Hoffmann, M.; Pattacini, U. & Metta, G. (2014), Automatic kinematic chain calibration using artificial skin: self-touch in the iCub humanoid robot, in 'Robotics and Automation (ICRA), 2014 IEEE International Conference on', pp. 2305-2312. Video for illustration:
Realizace:Code development (probably C++ or Python), Experiments on robot, Evaluation, Documentation
Vypsáno dne:10.02.2017
Max. počet studentů:6
Přihlášení studenti:František Puciow, Martin Jílek, Tomáš Pivoňka

Upozornění: toto je závazné přihlášení. Zrušit ho může pouze vedoucí práce