IKI Research Projects

3DRobust

3D cameras based on time-of-flight PMD image sensors (Photonic Mixing Device) are a cost-effective technology for active, pixel-resolved distance measurement and already a key technology for assistance systems in mobile robotics. PMD cameras can effectively suppress the disturbing but constant proportion of extraneous light, such as sunlight. However, often an insufficient accuracy occurs when measuring the distance, for e.g. due to the influence of the reflectivity of the obstacle, the…

RobotKoop

Aim of Intelligent Machines

Developing an intelligent machine which boasts artificial intelligence aims to generate software in this way that it can imitate the human brain as far as possible. The algorithm learns based on what it has already leant, such as the human brain. The more efficient the system and the richer the set of data, the wiser the machine.

Roboter Kurt

Since June 2018 the Institute for Artificial Intelligence (IKI) has been doing research in developing an intelligent robot…

RABE

The Intelligent Walking Frame

It is about the development of an intelligent walking frame particularly used in residential long-term medical care in order to reduce the work load of the nursing staff as well as allowing a more self-determined life in residential care homes for the elderly. An electric motor supports the user of the RABE walking frame, while managing longer distances or slopes and also makes transportation easier.  Furthermore, the walking frame is supposed to autonomously…

RobotKoop

Aim of Intelligent Machines

Developing an intelligent machine which boasts artificial intelligence aims to generate software in this way that it can imitate the human brain as far as possible. The algorithm learns based on what it has already leant, such as the human brain. The more efficient the system and the richer the set of data, the wiser the machine.

Roboter Kurt

Since June 2018 the Institute for Artificial Intelligence (IKI) has been doing research in developing an intelligent robot…

"Enigma-Project"

For the lecture “Data Security” by Prof. Ertel an Enigma, a historical cipher machine, is being reconstructed. 

The intention of this project is to illustrate the students a vivid example how the race between encryption, i.e. data security, and cracking the secret, i.e. the attackers, works.  As original working Enigmas are very expensive, years ago this project of reconstruction had been started.  Important to mention is that the modern cryptography consists exclusively of abstract…

Ertrag

The ergonomically correct execution of care measures is highly relevant in order to provide an ideal patient centered care and to avoid secondary health damage of the nursing staff. Unfortunately, there is a shortage of ergonomics experts, who are needed for the proper training of caregivers.

In this project, a virtual trainer will be developed that supports individual learning of ergonomically correct movements in the field of medical care. The movements performed by the experts will be…

Smart3D

The joint research project Smart3D with the IFM group is developing innovative AI-based sensor fusion and object classification. Autonomous driving uses for example PMD cameras which generate three-dimensional photos by using the so called “Time of Flight”-methods. Unfortunately, the resolution of those cameras in outdoor use is too low for a reliable object classification.

The Smart3D project aims to improve such a low-resolution 3D image by the information of a high-resolution 2D color image…

WILLE

Supported by research assistants working in the field of service robots, students are supposed to technically enhance the service robots Kate and Marvin enabling them to participate in the annual national and international contest RoboCup@Home where service robots of universities from all over the world are competing. Service robots have to make sure that they can manage “real-life” problems. Like that, RoboCup@Home is from learning and teaching point of view an ideal mock up. The studying…

RoboCup

Marvin the Paranoid Robot

Our current service robot Marvin has been developed within the context of the AsRoBe project (Assistant Robot for People with Physical Disabilities).

The MPO-700 by Neobotix is used as mobile base. Due to its four omnidirectional drive, it allows movement in all directions and offer because of its 120 kg tare weight a stable standing.  Two Sick S300-B 2D laser scanners and a belt of SRF08 ultrasonic sensors are used for navigation, collision avoidance and self…

AsRoBe

Assistive Robot for People with Physical Disability

Against the background of demographic change research is taking place if mobile service robots for people with physical disabilities can be a help. Those following fascinating questions are main focus:  :

• What kind of help does people with physical disability need?
• To what extent can service robots which are available in the medium term deliver this help cost-effectively (i.e. economically viable and accepted by the user)?
• How should…

Festo Learning Gripper

Festo Learning Gripper successfully on Hanover Fair

On behalf of the company Festo the so called Learning Gripper was developed by KIDS. It is a robot gripper with four fingers which learns independently to rotate a ball in raised position in any given orientation.

Here are only fundamental operations and possible positions of the fingers as well as feedback features of the environment defined in advance. The Learning Gripper only receives…

ZAFH -Service Robotics

Center for Applied Science at University of Applied Sciences (ZAFH)

The ZAFH Autonomous Mobile Service Robot is a project for developing intelligent mobile service robots which is ran by the collaboration with the University of Applied Sciences of Ravensburg-Weingarten, Ulm and Mannheim and promoted by the state of Baden-Württemberg.

The University of Applied Sciences of Ravensburg-Weingarten participates with two out of five work groups.

The work group of Prof. Wolfgang Ertel carries out…

Learning by Reinforcement – Crawling Robot

The little Crawling Robot poles through the laboratory. Its first movements are chubby and clumsy. According of the principle of “Reinforcement Learning” the little fellow should learn to walk. Like a little child it tries out. Successfully it optimizes its walk through trial and error. The movements become quickly more elegant and defined, the little thing gets sure-footed. Only that, the little chap is not of flesh and blood, but has little metallic arms and rubber cap on its lanky legs.
The…

LEXMED – Computer-Assisted Diagnosis of Appendicitis

LEXMED developed under the guidance of Prof. Ertel at the University of Applied Sciences of Ravensburg-Weingarten is a medical diagnostic system which is capable of learning. It is easy to handle and provides the doctor on the basis of the patient’s symptoms a well-founded diagnoses for the existence of appendicitis. It is based on software for developing knowledge-based systems which specially suit for handling uncertain and incomplete knowledge.
Contrary to wide-spread opinion diagnosis off…