Sie sind hier:



Evolutionary Robotics

Lehrstuhl: Lehrstuhl für Regelungssystemtechnik

Betreuer: Frank Hoffmann,

Beginn ab: 01.10.2013

Maximale Anzahl der Teilnehmer: 8

Beschreibung: Evolutionary robotics is an emerging area of research within the much larger field of fully-autonomous robots. One of the primary goals of evolutionary robotics is to develop automatic methods for creating intelligent autonomous robot controllers, and to do so in a way that does not require direct programming by humans. The primary advantage of robot design methods that do not require hand coding or in depth human knowledge is that they might one day be used to produce controllers or even whole robots that are capable of functioning in environments that humans do not understand well.

Evolutionary robotics uses population-based artificial evolution (fogel-1966, holland-1975) to evolve autonomous robot controllers (i.e. robot brains) and sometimes robot morphologies (i.e. robot bodies)(lipson-n-2000). Generally, the robots are evolved to perform tasks requiring some level of intelligence, for example moving around in an environment without running into things.

The process of controller evolution consists of repeating cycles of controller fitness testing and selection that are roughly analogous generations in natural evolution. Evolution is initialized by creating a population of randomly configured robots (or robot controllers). During each subsequent cycle, or generation, each of the robot controllers competes in an environment to perform the task for which the robots are being evolved. This process involves placing each controller into a robot and then allowing the robot to interact with its environment for a period of time. Following this, each controller’s performance is evaluated using a fitness selection function (objective function) that measures how well the task was performed. The controllers in the better performing robots are selected, altered and propagated in a repeating process that mimics natural evolution. The alteration process is also inspired by natural evolution and may include mutation and trading of genetic material. Cycles are repeated for many generations to train populations of robot controllers to perform a given task.

Not only controllers can be evolved. In addition, it is possible to find a way to encode the physical structure of a robot and evolve that also. Although there were attempts to do this in the early years of ER research, it has only be in the past five or six years that such methods have lead to robots able to function in the real world. These recent results were accomplished by formulating a set of modular building units that could be easily simulated and fabricated, but that could also be configured and combined into an almost infinite variety of non-trivial robot bodies.

This project group is concerned to evolve a vision system in symbiosis with training a neural controller for vision based navigation of a mobile robot. The goal is to combine learning on an evolutionary scale with individual supervised learning from demonstration.
Training examples are generated by the human guiding the mobile robot through the environment while recording control commands and images. A neural network with internal dynamics is trained on these demonstrations. The evolutionary algorithm is supposed to "design" the vision system that extracts the relevant visual features that serve as input to the neural controller. The approach is supposed to be implemented, evaluated and analysed in a virtual reality simulation as well as on a Pioneer 3DX mobile robot with an omnidirectional camera. The algorithms are mainly developed in Matlab, potentially using precompiled libraries from OpenCV. Students should have a background in mobile robotics, machine learning and computer vision.