Intelligent Systems

Master Project - Intelligent Systems

MP

 

Exercise  (infMPInS-01a)

4 SWS, ECTS-Credits: 10
Suitable for ERASMUS / exchange students, language of instruction: English
Time: Thursday 09:30-11:00
Lecture period SS 2021: Thursday, April 22th, 2021 - Friday, July 9th, 2021
For more information UnivIS or Modulinformationssystem Informatik



Title: "Collaborative classification with Turtle Bots"


KickOff Meeting (online): Monday, April 12th at 2 pm
via https://uni-kiel.zoom.us/j/83011387731?pwd=LzgzTHNRV0tYOTM2Y3BmaUozVUtvdz09

Important: The team size is restricted - the KickOff Meeting is used to register participants


Description

There are two robots with different abilities. One robot can visually perceive objects, while the other robot can determine the weight and transport the object. Based on a collaborative feature determination, manually provided objects are to be correctly classified and sorted into appropriate containers. The learning technique for classification starts with no prior knowledge - it must independently and continuously evaluate its knowledge and specifically question the human user.

This requires the following steps and techniques:
- Setting up a laboratory environment incl. unloading mechanisms
- Individual feature determination of the individual robots
- Fusion of information and data representation
- Continuous training and evaluation of a classifier with Active Learning techniques
- Control of robot behaviour in ROS

Depending on the availability of hardware, the loading step can also be automated using a robot arm.

As a result of the task, the following artefacts are foreseen:
- Code base
- Short technical documentation
- Scientific description (IEEE Template, double Column, 8 pages)

The task requires that at least parts are done locally at the group's lab (i.e. robot-based tasks). Other parts can be done remotely. It will be subject to the team's discussion how this is organised.

For any questions, please contact Prof. Dr.-Ing. Sven Tomforde via e-mail: st@informatik.uni-kiel.de