neural networks research group
areas
people
projects
demos
publications
software/data
Evolving Obstacle Avoidance Behavior In A Robot Arm (1996)
David E. Moriarty
and
Risto Miikkulainen
Existing approaches for learning to control a robot arm rely on supervised methods where correct behavior is explicitly given. It is difficult to learn to avoid obstacles using such methods, however, because examples of obstacle avoidance behavior are hard to generate. This paper presents an alternative approach that evolves neural network controllers through genetic algorithms. No input/output examples are necessary, since neuro-evolution learns from a single performance measurement over the entire task of grasping an object. The approach is tested in a simulation of the OSCAR-6 robot arm which receives both visual and sensory input. Neural networks evolved to effectively avoid obstacles at various locations to reach random target locations.
View:
PDF
,
PS
Citation:
In Pattie Maes and Maja J. Mataric and Jean-Arcady Meyer and Jordan Pollack and Stewart W. Wilson, editors,
From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior
(AI96-243), 468-475, 1996. Cambridge, MA: MIT Press.
Bibtex:
@incollection{moriarty:sab96, title={Evolving Obstacle Avoidance Behavior In A Robot Arm}, author={David E. Moriarty and Risto Miikkulainen}, booktitle={From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior}, number={AI96-243}, editor={Pattie Maes and Maja J. Mataric and Jean-Arcady Meyer and Jordan Pollack and Stewart W. Wilson}, publisher={Cambridge, MA: MIT Press}, pages={468-475}, url="http://nn.cs.utexas.edu/?moriarty:sab96", year={1996} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
David E. Moriarty
Ph.D. Alumni
moriarty [at] alumni utexas net
Areas of Interest
Evolutionary Computation
Neuroevolution
Reinforcement Learning
Robotics
Applications