Modular Robot Control Environment – Testing Neural Control on Simulated and Real Robots
-
1
Georg-August-Universität Göttingen, Third Institute of Physics - Biophysics, Germany
-
2
Bernstein Focus Neurotechnology, Germany
-
3
Max Planck Institute for Mathematics in the Sciences, Germany
-
4
Bernstein Center for Computational Neuroscience, Germany
To develop new control approaches for robotic devices and evaluate their results it is important to be able to efficiently test them not only in simulated but also real environments. This means switching between simulated and real systems should be easily possible using the same controller code (without reprogramming). Furthermore, the development process should be able to continuously increase robot functionality in order to solve more complex tasks. This can be achieved based on modularity. A modular structure is considered as a major advantage, compared to many other approaches due to the following aspects: 1) It is flexible, allowing to simply rearrange, add, and/or remove modules for controlling different types of robots. 2) Each module is typically independent of other modules in its functioning and does not influence or become influenced by other modules.
Taking this into account, here we present a modular robot control environment relying on the C++ programming language and providing an artificial neural network library. It is used to develop neurocontrollers for different robots. The very same controller code can now be tested in simulation and on real hardware, which allows speeding up the development process. The modular robot control environment also allows to exchange robots and controller in a plug-and-play manner where parameters of the simulation and real robot can be observed and changed online.
We have applied the modular robot control environment to develop neural control of hexapod walking robots AMOSII. They are biologically inspired hardware platforms developed in collaboration with the Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS. They are used to study the coordination of many degrees of freedom, to perform experiments with neural control, memory, and learning. The robots were modeled using LPZRobots [1], a physically realistic simulation toolkit (freely available under GNU General Public License).
Employing iterated development cycles, including progression of a neural controller and tests on the simulated and real hexapod platform, a variety of biologically inspired walking gaits as well as orienting, taxis and their combinations have been successfully achieved. By recently developing another module for adaptive climbing behavior, the hexapod can now overcome obstacles of various heights (e.g., ~ 75% of its leg length, which is higher than those that other comparable legged robots have achieved so far). The presented modular robot control environment can also be applied to different types of robotic systems, like wheeled robots and manipulators (e.g., integration of the E-puck mobile robot and the KUKA-DLR Lightweight Robot arm in preparation).
Figure 1: Modular Robot Control Environment: The developed neural controllers can easily be transferred to and tested on real and simulated hardware platforms. Here a neural control for hexapod locomotion is depicted.
Acknowledgements
This research was supported by the BMBF-funded BFNT Göttingen with grant number 01GQ0811 (project 3B) and BCCN Göttingen with grant number 01GQ1005A (project D1), and the Emmy Noether Program (DFG, MA4464/3-1).
References
[1] Martius, G., Hesse, F., Güttler, F., and Der, R., LpzRobots: A free and powerfulrobot simulator (2012), http://robot.informatik.uni-leipzig.de/software.
Keywords:
Autonomous Robots,
motor control,
Neural control,
neural networks,
Robot control environment
Conference:
Bernstein Conference 2012, Munich, Germany, 12 Sep - 14 Sep, 2012.
Presentation Type:
Poster
Topic:
Motor control, movement, navigation
Citation:
Hesse
F,
Martius
G,
Manoonpong
P,
Biehl
M and
Wörgötter
F
(2012). Modular Robot Control Environment – Testing Neural Control on Simulated and Real Robots.
Front. Comput. Neurosci.
Conference Abstract:
Bernstein Conference 2012.
doi: 10.3389/conf.fncom.2012.55.00179
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
11 May 2012;
Published Online:
12 Sep 2012.
*
Correspondence:
Dr. Frank Hesse, Georg-August-Universität Göttingen, Third Institute of Physics - Biophysics, Göttingen, Germany, fhesse@physik3.gwdg.de