Visually identifying and interpreting everyday objects, such as furniture, provides interaction anchor points for low-cost robotic projects in home environments. Using the open source Deep Learning framework Keras (encapsulating TensorFlow and Theano), a mobile robot platform with the form factor of a robot vacuum cleaner should be enabled to detect and recognize everyday objects and furniture on living environments to create a labelled map of the environment. From the recognition information, the robot should be able to infer higher-level room labels autonomously. For this, the frameworks need to be setup with suitable neural networks. These need to be trained properly with a custom image set for a proof-of-concept demonstration.
Team members will:
1) Setup and extend a rudimentary mobile platform running Linux with ROS and/or RSB
2) Familiarize themselves with the framework and it workflow
3) Develop and train suitable networks for different use-cases
4) Cooperate with the teams SIeMoR and HAIMoR to make use of synergies
Please note that the teams will be selected by the supervisors on the basis of short applications that students are expected to send to them. Registering to the project in the ekVV will only be regarded as expression of interest; it will not secure a team membership.
Please get in touch with the supervisors for information on the application procedure.
- Required skills:
The programming will be done in C++ or Python
Rhythmus | Tag | Uhrzeit | Format / Ort | Zeitraum |
---|
Modul | Veranstaltung | Leistungen | |
---|---|---|---|
39-M-Inf-GP Grundlagenprojekt Intelligente Systeme | Gruppenprojekt | unbenotete Prüfungsleistung
|
Studieninformation |
Die verbindlichen Modulbeschreibungen enthalten weitere Informationen, auch zu den "Leistungen" und ihren Anforderungen. Sind mehrere "Leistungsformen" möglich, entscheiden die jeweiligen Lehrenden darüber.