Dean F. Hougen, Paul E. Rybski, and Maria Gini,
"Repeatability of Real World Training Experiments: A Case Study",
Autonomous Robots, Vol. 6, No. 3, pp 281-292, 1999.
(compressed postscript) (pdf)
We present a case study of reinforcement learning on a real robot that
learns how to back up a trailer and discuss the lessons learned
about the importance of proper experimental procedure and design. We
identify areas of particular concern to the experimental robotics
community at large. In particular, we address concerns pertinent to
robotics simulation research, implementing learning algorithms on real
robotic hardware, and the difficulties involved with transferring
research between the two.
Dean F. Hougen, Maria Gini, and James Slagle,
"Rapid Unsupervised Connectionist Learning for Backing a Robot with Two
Trailers",
IEEE International Conference on Robotics and Automation, April 1997.
(postscript) (pdf)
This paper presents an application of a connectionist control-learning
system designed for use on an autonomous mini-robot.
This system was formerly shown to form useful two-dimensional mappings
rapidly when applied to backing a car with a single trailer.
In the current paper the learning system is extended to three
dimensions and applied to a similar but significantly more difficult problem.
The system is shown to be capable of rapid unsupervised learning of
output responses in temporal domains through the use of eligibility traces
and inter-neural cooperation within topologically defined neighborhoods.
Dean F. Hougen, Maria Gini, and James Slagle.
"Partitioning Input Space for Control-Learning",
International Conference on Neural Networks, June 1997.
(postscript) (pdf)
This paper considers the effect of input-space partitioning on reinforcement
learning for control. In many such learning systems, the input space is
partitioned by the system designer.
However, input-space partitioning could be learned.
Our objective is to compare learned and fixed input-space
partitionings in terms of the overall system learning speed and proficiency
achieved.
We present a system for unsupervised control-learning in temporal
domains with results for both fixed and learned input-space
partitionings. The trailer-backing task is used as an example problem.
Dean F. Hougen, John Fisher, Maria Gini, and James Slagle, "Fast
connectionist learning for trailer backing using a real robot."
IEEE International Conference on Robotics and Automation,
pp 1917-1922, 1996.
(postscript) (pdf)
This paper presents the application of a connectionist control-learning
system to an autonomous mini-robot.
The system's design is severely constrained by the computing power and memory
available on board the mini-robot and the on-board training time is greatly
limited by the short life of the battery.
The system is capable of rapid unsupervised learning of
output responses in temporal domains through the use of eligibility traces
and data sharing within topologically defined neighborhoods.
Dean F. Hougen, John Fischer, and Deva Johnam, "A neural network
pole-balancer that learns and operates on a real robot in real time,"
Proceedings of the MLC-COLT Workshop on Robot Learning, 73-80, 1994.
Abstract
and full paper.
