Sense of touch is central for interaction with our environment. In contrast to humans, robots are still far from performing seamless haptic interaction with 3D objects. In this project we employ reinforcement learning to teach a robot equipped with a tactile sensor array to explore its environment and to estimate basic structural properties of 3D objects, such as volume or curvature. The project is based on the previous work introduced under the following link: https://my.hidrive.com/lnk/lpgGER0I.
In case this would not find enough interest for a team project, this project proposal would be also offered (in reduced/modified form)
[x] as individual project
[x] as project for 2-3 students
- mandatory : machine learning and reinforcement learning methods
- desired : experience with tensorflow
Frequency | Weekday | Time | Format / Place | Period | |
---|---|---|---|---|---|
weekly | Mo | 06.04.-17.07.2020 |
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-GP Grundlagenprojekt Intelligente Systeme | Gruppenprojekt | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.