Galerie of our robots

CoTeSys researchers work with a number of robots that all have special features. Here is a short introduction of our robot family: 


© LSR/TUM

ACE

The Autonomous City Explorer (ACE) was developed in the Institute of Automatic Control Engineering/TUM. The aim was to create a robot that will autonomously navigate in an unstructured urban environment and find its way through interaction with humans. This was achieved in 2008 when ACE found its way to the city center of Munich by asking pedestrians for help without being led by GPS or other devices. To achieve this, research results from the fields of autonomous navigation, path planning, environment modeling, and human-robot interaction are combined.

ACE is now further developed in the IURO project


© LSR/TUM

Eddie and co

At the moment, four similar robots are in the CoTeSys Multi-Robot Lab. Here they are used to investigate the human- robot as well robot-robot interaction. At the moment they work in a workshop scenario, mounting tires (watch video) and helping human workers with their tasks in the pitstop. The robots are all built in-house. The only difference is that one of the robots is equipped with KUKA-lightweight LWR-4 arms. Their key data are:

  • human-size height
  • omni-directional mobile platform
  • laser range finders at ground level
  • two anthropomorphic arms with 7-DoF, equipped with force sensors
  • different attachable end-effectors such as two- and three-finger grippers
  • emotion display head ‘EDDIE’ on an actuated neck and stereo camera head on pan/tilt unit respectively

© MMK/TUM

Elias

Elias is an assistance robot and its name stands for “Enhanced Living Assistant”. ELIAS serves as an integration platform and melting pot for innovative human-machine interfaces and information technologies. ELIAS is a robot that can perceive its environment and understand its user. Research focus is to enable communication on a true natural and intuitive way for humans. ELIAS therefore has to learn a lot – similar to the human itself in his first years. The platform has been enhanced with robotic eyes that move as fast as human eyes and can simulate human gaze together with the EyeSeeCam very authentically.

ELIAS is a Scitos robot and was developed by the company MetraLabs in Germany . It is about 60 kgs, has the size of a small human. It is equipped with sonar sensors and laser sensors to avoid collision.

A similar robot is also used in the CoTeSys' satellite project “ALIAS”.


© CoTeSys/Kurt Fuchs

ICub

The iCub is a small-size humanoid robot being designed by the RobotCub Consortium, consisting of several European universities. The main goal of this platform is to study cognition through the implementation of biological motivated algorithms. The project is open-source - both the hardware design and the software are freely available.

ICub has the size of a three-year old child in CoTeSys and he is imitating movements in as well as learning how to stack Lego bricks together.

 


© CoTeSys/Michael Memminger

Nao

Nao is a programmable 57 cm tall humanoid robot with the following key components:

  • A body with 25 degrees of freedom (DOF), whose key elements are electric motors and actuators.
  • A series of sensors – 2 cameras, 4 microphones, a Sonar distance sensor, 2 IR emitters and receivers, 1 inertial board, 9 tactile sensors, 8 pressure sensors.
  • Various devices to express itself – voice synthesizer, LED lights, 2 high quality speakers.

Nao is used in CoTeSys to optimize the robot’s biped walking using machine learning methods, such as reinforcement learning.  Furthermore,  the team also wants to calculate the human dynamics during the walking behavior and see if one can map the movement in the dynamics level.


Snookie

Snookie is an underwater robot built after the blind Mexican cave fish. This fish navigates in the dark without collision with the help of a lateral-line organ. The most important scientific innovation in Snookie is – analogue to fish’s organ - the electronic realization of the lateral-line sensory system. As the robot is supposed to dive into corridors of aquiferous caves and explore channels which are unknown or too narrow and dangerous for humans, it is of small dimensions and little weight. The next step is to equip Snookie with water velocity sensors on its yellow nose. The biomimetic velocity sensors mimic the lateral-line system which allows fish to detect and navigate around objects by observing water flow changes around the fish’s body.

The idea to develop Snookie first came up in a students’ project in October 2007 and was a cooperation of electrical engineering students together with the Chair of Biophysics and the Chair of Automatic Control Engineering (both TUM).

Details:

Weight: 32 kg

Length: 74 cm

Diameter: 25 cm


© CoTeSys/Kurt Fuchs

TUM-James

TUM-James is a PR2 robot developed by Willow Garage. The IAS group was selected as only one of 11 research groups worldwide to carry out their research on a PR2 in 2010. The aim of this 2-year project is to support the implementation of the Cognitive Robot Abstract Machine framework in the ROS environment.

James is the master of popcorn-making in the Assistive Kitchen, the robot also learns how to shop in a supermarket.

TUM-James and TUM-Rosie on video.


© CoTeSyS/Kurt Fuchs

TUM-Rosie

TUM-Rosie has been built around the KUKA-omnidirectional base and KUKA-lightweight LWR-4 arms. The robot works in the Assistive Kitchen environment of the Intelligent Autonomous Systems Group. The main objective of the research performed on- and around the robot is to develop a system with a very high degree of cognition involved. At present Rosie is able to bake pancakes, cook Bavarian sausages and make sandwiches. In most parts the robot was developed and built by the IAS team.

TUM-James and TUM-Rosie on video.