Genetic robots – computer algorithm designed robots
Researchers from the Fraunhofer Institute for Manufacturing Engineering and Automation (IPA) in Stuttgart have successfully performed a process of genetic robotics where a moving robot was automatically designed without the intervention of a designing engineer. Genetic Robots are moving robots that can be created by using genetic software algorithms and additive manufacturing.
The important role robots play is not limited to industrial production in the automotive industry. They are also used for exploration, transportation and as service robots. Modeling the movements to make them mobile or enabling them to grip objects is a complex yet central challenge for engineers. The robot created in the process consists of cylinder-shaped tubes with ball-and-socket joints that can assume different shapes depending on external factors and the robot’s purpose at hand.
“The only input needed is: ‘Move forwards as efficiently as possible along a level surface’”, said Dipl.-Des. Andreas Fischer, industrial designer and product developer at IPA. “Another advantage is that the algorithm often spits out surprising variations – ‘mutations’ that would not necessarily have occurred to the designer.”
The basis for the development is a physic engine in which the most important environmental influences (such as the friction of the ground or gravity) are implemented. If the Genetic Robot has to withstand unevenness, climb stairs or swim in water, these environmental conditions can be simulated. The Genetic Robots system can also be used to design subcomponents such as gripping systems for robots in industry.
Fitness functions within the software algorithm select the movement elements with which the Genetic Robot can advance along this surface the software determines the shape of the tubes, the position of the movement points and the position of the drives (actuators). The final result is not always singular, and a designer can choose the final form from a multitude of solutions.
Bionics provides the basis for the movements implemented. Natures ‘ideas’ are decrypted, and natural laws are applied to the field of technology. The resulting bionic structures are then manufactured using additive technologies. The original genetic algorithm was developed by US scientists Hod Lipson and Jordan Pollack and originates from their GOLEM Project. The software was further developed by Ideas to Products (i2p) GmbH in Sankt Gallen, Switzerland, in order to make the robots’ geometries outputted directly as a CAD file for production by electronic tool machines. The mechatronics along with the capability to move about by means of an additively manufactured bellow drives (actuators) were created at IPA.
IPA will be demonstrating a fully genetically generated robot structure capable of moving by using the electronics attached to its legs and joints from December 1-4, 2010, at the Euromold trade fair in Frankfurt, Germany. Aside other applications, the researchers claim this research could lead to ultralight modules that reduce the weight of new robots without affecting their stability.