| |
Ph.D. Thesis |
| Title |
Emergent Control of Self-Reconfigurable Robots |
| Authors |
Kasper Støy |
| Published |
AdapTronics Group, The Maersk Mc-Kinney
Moller Institute for Production Technology, University of Southern
Denmark, 2003 |
|
|
Journal Papers (4) |
| Title |
Using cellular automata and gradients to control self-reconfiguration |
| Authors |
Kasper Stoy |
| Abstract |
Self-reconfigurable robots are built from modules, which are autonomously able to change the way they are connected. Such a robot can,cthrough this self-reconfiguration process, change its shape. The process has proved to be difficult to control, because it involves control of a distributed system of mechanically coupled modules connected in time-varying ways. In this paper we present an approach to the control problem where the desired configuration is grown from an initial seed module. Seeds produce growth by creating a gradient in the system, using localcommunication, which spare modules descend to locate the seed. The growth is guided by a cellular automaton, which is automatically generated on the basis of a three-dimensional CAD model or a mathematical description of the desired configuration. The approach is evaluated in simulation and we find that the self-reconfiguration process always converges and the time to complete a configuration scales approximately linearly with the number of modules. However, an open question is how the simulation results transfer to a physically realized self-reconfigurable robot. |
| Published |
Robotics and Autonomous Systems, Volume 54, January 2006, Pages 135-141, Special issue on the best papers presented at IAS-8 |
|
|
| Title |
A simple approach to the control of locomotion in self-reconfigurable robots |
| Authors |
Kasper Støy, Wei-Min Shen, and Peter Will |
| Abstract |
In this paper we present role-based control which is a general bottom-up approach to the control of locomotion in self-reconfigurable robots. We use role-based control to implement a caterpillar, a sidewinder, and a rolling track gait in the CONRO self-reconfigurable robot consisting of eight modules. Based on our experiments and discussion we conclude that control systems based on role-based control are minimal, robust to communication errors, and robust to reconfiguration. |
| Published |
Robotics and Autonomous Systems, Volume 44, Issues 3-4 , 30 September 2003, Pages 191-199, Special issue on the best papers presented at IAS-7 |
|
|
| Title |
Using Role Based Control to Produce Locomotion in Chain-Type
Self-Reconfigurable Robots |
| Authors |
Kasper Støy, Wei-Min Shen, and Peter Will |
| Abstract |
This paper presents a role based approach to the problem of
controlling locomotion of chain-type self-reconfigurable robots. In
role based control all modules are controlled by identical
controllers. Each controller consists of several playable roles
and a role selection mechanism. A role represents the motion of
a module and how it synchronizes with connected modules. A controller
selects which role to play depending on the local configuration of the
module and the roles being played by connected modules.
We use role based control to implement a sidewinder and a caterpillar
gait in the CONRO self-reconfigurable robot. The robot is made from up
to nine modules connected in a chain. We show that the locomotion
speed of the caterpillar gait is constant even with loss of 75\% of
the communication signals. Furthermore, we show that the speed of the
caterpillar gait decreases gracefully with a decreased number of
modules. We also implement a quadruped gait and show that without
changing the controller the robot can be extended with an extra pair
of legs and produce a hexapod gait.
Based on these experiments we conclude that role based control is
robust to signal loss, scales with an increased number of modules, and
is a simple approach to the control of locomotion of chain-type
self-reconfigurable robots |
| Published |
IEEE Transactions on Mechatronics, special issue on self-reconfigurable robots, 7(4), pages 410-417, 2002. |
|
|
| Title |
LOST: Localization-Space Trails for Robot Teams |
| Authors |
Richard T. Vaughan, Kasper Støy, Gaurav S. Sukhatme and Maja J. Mataric |
| Abstract |
We describe Localization-Space Trails
(LOST), a method that enables a team of robots to navigate between
places of interest in an initially unknown environment using a trail
of landmarks. The landmarks are not physical; they are waypoint
coordinates generated on-line by each robot and shared with
team-mates. Waypoints are specified in each robot s local coordinate
system, and contain references to features in the world that are
relevant to the team s task and common to all robots. Using these
task-level references, robots can share waypoints without maintaining
a global coordinate system. The method is tested in a series of
real-world multi-robot experiments. The results demonstrate that the
method (i) copes with accumulating odometry error; (ii) is robust to
the failure of individual robots; (iii) converges to the best route
discovered by any robot in the team. In one experiment, a team of four
autonomous mobile robots performs a resource transportation task in
our uninstrumented office building. Despite significant divergence of
their local coordinate systems, the robots are able to share
waypoints, forming and following a common trail between two
predetermined locations for more than 3 hours, traveling a total of
8.2km (5.1 miles) before running out of power. Designed to scale to
large populations, LOST is fully distributed, with low cost in
processing, memory and bandwidth. It combines metric data about the
position of features in the world with instructions on how to get from
one place to another; producing something between a map and a
plan. |
| Published |
IEEE Transactions on Robotics and Automation, special issue on multi-robot systems, 18(5), pages 796-812, 2002. |
|
|
|
Refereed Conference Papers (18) and workshop papers (2) |
|
| Title |
Hierarchical Robots |
| Authors |
K. Stoy, A.Lyder, R.F.M. Garcia, and D. Christensen |
| Abstract |
This paper introduces the concept of hierarchical
robots, which is a type of modular robots assembled from a
hierarchy of modules, and a preliminary realization of this
concept: the Odin robot. Odin currently consists of ten modules
of two different classes, one class of modules provide structure
and the other actuation. We describe the mechanical design
of these modules and their electrical design with specific focus
on their hybrid communication system whose topology can be
changed on-line. We demonstrate the features of this communication
system in a simple experiment and also demonstrate
how the assembled Odin robot can produce locomotion. While
it is too early to make a conclusion regarding the usefulness of
hierarchical robots in general, we think that our work indicates
that we may be able to simplify the manufactured modules at
the bottom of the hierarchy while increasing the functionality
of the assembled hierarchical robot. |
| Published |
In Proceedings of the IROS Workshop on Self-Reconfigurable Modular Robots, San Diego CA, 2007 (to appear). |
|
|
|
| Title |
Hybrid Approach: A Self-Reconfigurable Communication Network for Modular Robots |
| Authors |
R.F.M. Garcia, K. Stoy, D.J. Christensen and A. Lyder |
| Abstract |
We present a novel hybrid communication system
for modular robots, based on inter-module buses that can connect
on-demand to form arbitrary network topologies.
In addition to describing the implementation of this hybrid
communication system, we analyse transfer rates and reliability,
validating the results using a Spice 1 simulation and a proof-ofconcept
experiment performed on a hardware prototype.
Thus, we find the system is fast, since it has a potential to
provide a maximum transfer rate of 9.9Mbps divided by the
maximum bus length measured in meters, with buses as large
as 256 modules. The system is also found to be small in size,
power saving and reliable. These features, in combination with
its flexibility, make hybrid communication suitable for modular
robots. |
| Published |
In Proceedings of the International Conference on Robots and Communication, Athens, Greece, 2007. (to appear). |
|
|
|
| Title |
Towards Artificial ATRON Animals: Scalable Anatomy for Self-Reconfigurable Robots |
| Authors |
D.J. Christensen, D. Brandt, and K. Stoy |
| Published |
In Proceedings of the RSS Workshop on Self-Reconfigurable Modular Robots, Philadelphia PA, August 2006. |
|
|
|
| Title |
The Deformatron Robot: a Biologically Inspired Homogeneous Modular Robot |
| Authors |
K. Stoy |
| Abstract |
The Deformatron robot is a homogeneous, modular
robot. The Deformatron modules can play one of three roles
in the physical structure of the robot: bone, tendon, and muscle.
These roles are inspired by their biological counterparts. This
combination of roles gives us a modular robot which potentially
may have enough structural strength and actuation power to
manipulate its environment and work in three dimension even in
the presence of gravity. In this paper we present our preliminary
LEGO-based prototype of the Deformatron robot. We measure
and analyse the properties of the system in terms of structural
strength and actuation power. Finally, we conclude that the
Deformatron concept may provide an avenue of research which
may make modular robots stronger and better suited for real
world task environments. |
| Published |
In proceedings of IEEE International Conference on Robotics and Automations, (ICRA), Orlando, USA, pages 2527-2531, May 16-18, 2006 |
|
|
|
| Title |
Selecting a Meta-Module to Shape-Change the ATRON Self-Reconfigurable Robot |
| Authors |
D.J. Christensen and K. Støy |
| Abstract |
The ATRON self-reconfigurable robot
consists of simple one degree of freedom ATRON modules.
The motion capabilities of an individual module
are therefore quite limited. To compensate for this,
meta-modules composed of more than one module
are used to shape-change the system. Meta-modules
emerge from the environment created by other modules,
move on the surface of other modules and stop at a
new position. The flow of meta-modules, from one place
to another on the structure of modules, realizes the
desired self-reconfiguration. In this paper we compare
six different meta-module types composed of ATRON
modules. Variations of meta-module morphology and
meta-actions are investigated for its ability to shapechange
the robot. We conclude that two of the investigated
meta-module types are able to shape-change the
robot to an acceptable extent. |
| Published |
In proceedings of IEEE International Conference on Robotics and Automations, (ICRA), Orlando, USA, pages 2532-2538, May 16-18, 2006 |
|
|
|
| Title |
How to Construct Dense Objects with Self-Reconfigurable Robots |
| Authors |
K. Stoy |
| Abstract |
Self-reconfigurable robots can change their shape by rearranging the
modules from which they are built. This self-reconfiguration process has proven
difficult to control, because it involves control of a distributed system of autonomous,
but mechanically coupled modules connected in time-varying ways. In this work
we address this control problem and specifically look at how to construct dense
configurations.
The basic idea behind our solution is that holes inside the desired configuration
and modules outside attract each other. The effect is that holes propagate to the
surface of the desired configuration and modules outside move in to fill them. This
basic solution is augmented with a scaffold and gradient-based algorithm which
ensures that the robot does not get stuck in local minima or get disconnected during
self-reconfiguration.
The approach is evaluated in simulation and we find that the self-reconfiguration
process always converges and the time to complete a configuration scales approximately
linearly with the number of modules. This is, to the best of our knowledge,
the first time this result has been obtained for dense configuration. |
| Published |
In proceedings of European Robotics Symposium, (EUROS), Palermo, Italy, pages 27-37, May 12-15, 2006 |
|
|
|
| Title |
Self-Repair Through Scale Independent Self-Reconfiguration |
| Authors |
K. Stoy and R. Nagpal |
| Abstract |
Self-reconfigurable robots are built from modules
which are autonomously able to change the way they
are connected, thus changing the overall shape of the robot.
This self-reconfiguration process is difficult to control, because
it involves the distributed coordination of large numbers of
identical modules connected in time-varying ways.
We present an approach where a desired shape is grown
based on a scalable representation of the desired configuration
which is automatically generated from a 3D CAD model. The
size of the configuration is adjusted continually to match the
number of modules in the system. This has the advantage that
if modules are removed or added, the system automatically
adjusts its scale and thus self-repair is obtained as a side
effect. This capability is achieved by distributed, local rules
for module movement that are independent of the goal
configuration.
We compare the scale independent approach to one where
the desired configuration is grown directly at a fixed scale. We
find that the features of the scale independent approach come
at the expense of an increased number of moves, messages,
and time steps taken to reconfigure. |
| Published |
In proceedings of IEEE/RSJ International Conference on Robots and Systems, (IROS), Sendai, Japan, pages 2062-2067, Sep 30-Oct 2, 2004 |
|
|
|
| Title |
Self-Reconfiguration Using Directed Growth |
| Authors |
K. Stoy and R. Nagpal |
| Abstract |
Self-reconfigurable robots are built from modules which are
autonomously able to change the way they are connected, thus changing
the overall shape of the robot. This process is difficult to control
because it involves the distributed coordination of large numbers of
identical modules connected in time-varying ways.
We present an approach to self-reconfiguration where the desired
configuration is grown from an initial seed module. Seeds produce
growth by creating a recruitment gradient, using local communication,
which spare modules climb to locate the seed. The growth is guided by
a novel representation of the desired configuration, which is
automatically generated from a 3D CAD model. This approach has two
salient features: (1) the representation is concise, with a size
proportional to the global shape rather than the number of modules and
(2) there is a clean separation between the goal and the local, goal
independent rules used by the modules. We demonstrate three
implementations of the local rules for recruitment, and show how one
can trade-off the number of moves and messages, against time taken to
reconfigure. |
| Published |
In proceedings of the 7th International Symposium on
Distributed Autonomous Robotic Systems (DARS 2004), pages 1-10, Toulouse, France, June 23-25, 2004 |
|
|
|
| Title |
Controlling Self-Reconfiguration using Cellular Automata and Gradients |
| Selected to appear in Journal of Robotics and Autonomous Systems, special issue on the best of IAS-8 |
| Authors |
K. Støy |
| Abstract |
Self-reconfigurable robots are built from modules, which are
autonomously able to change the way they are connected. Such a robot
can, through this self-recon-figuration process, change its shape. The
process has proven to be difficult to control, because it involves
control of a distributed system of mechanically coupled modules
connected in time-varying ways.
In this paper we present an approach to the self-reconfiguration
problem where the desired configuration is grown from an initial seed
module. Seeds produce growth by creating a gradient in the system,
using local communication, which spare modules climb to locate the
seed. The growth is guided by a cellular automaton, which is
automatically generated based on a three-dimensional CAD model or a
mathematical description of the desired configuration.
The approach is evaluated in simulation and we find that the
self-reconfiguration process always converges and the time to complete
a configuration scales approximately linearly with the number of
modules. However, an open question is how the simulation results
transfer to a physically realized self-reconfigurable robot. |
| Published |
In proceedings of the 8th international
conference on intelligent autonomous systems
(IAS-8), pages 693-702, Amsterdam, The Netherlands, March 10-13, 2004 |
|
|
|
| Title |
Implementing Configuration Dependent Gaits in a Self-Reconfigurable Robot |
| Authors |
K. Støy, W.-M. Shen, and P. Will |
| Abstract |
In this paper we examine locomotion in the context of self-reconfigurable robots. Self-reconfigurable robots are robots built from many connected modules. A self-reconfigurable robot can change its shape and configuration by changing the way these modules are connected. The focus of this paper is to understand how several locomotion gaits can be represented in such a robot and how the robot can select one of these gaits depending on its configuration. We implement a control system based on role based control in a physical self-reconfigurable robot built from seven modules. In several experiments we successfully demonstrate that the robot can change from a sidewinder snake gait to a quadruped walking gait when the robot is manually reconfigured from a chain to a quadruped configuration. We conclude that role based control is a promising control method for controlling locomotion of self-reconfigurable robots. |
| Published |
In proceedings of the 2003 IEEE international
conference on robotics and automation (ICRA'03), pages 3828-3833, Tai-Pei, Taiwan, september 16-18, 2003. |
|
|
|
| Title |
On the Use of Sensors in Self-Reconfigurable Robots |
| Awarded best philosophical paper of the conference |
| Authors |
K. Støy, W.-M. Shen, and P. Will |
| Abstract |
In this paper we investigate the use of sensors in self-reconfigurable
robots. We review several physically realized self-reconfigurable
robots and conclude that little attention has been paid to the use of
sensors. This is unfortunate since sensors can provide essential
feedback that can be used to guide self-reconfiguration and
control. In the systems that do use sensor feedback, the feedback is
used locally on each module. However we identify a need in some
situations to use sensor feedback globally. We therefore propose an
approach where raw sensor values are abstracted and propagated to all
modules. The sensor values are abstracted differently depending on the
position of the producing sensor on the robot. We combine this
approach with role based control, a control method for
self-reconfigurable robots that we have developed earlier. We
demonstrate that by combing these two approaches it is possible to
make a self-reconfigurable robot consisting of six modules walk and
avoid obstacles. However the reaction time of the robot is slow and
therefore we discus possible ways of reducing the reaction time. |
| Published |
In proceedings of the 7th international
conference on simulation of adaptive behavior (SAB'02), pages 48-57, Edinburgh, UK, August 4-9, 2002. |
|
|
|
| Title |
How to Make a Self-Reconfigurable
Robot Run |
| Authors |
K. Støy, W.-M. Shen, and P. Will |
| Abstract |
In this paper we present a multiagent based control algorithm for
self-reconfigurable robots. These robots are robots made from a
possibly large number of independent modules. In the proposed control
algorithm all modules run identical programs, but may play different
roles. The modules decide what role to play based on their local
configuration and information propagated down to them through the
configuration tree. A role consists of a cyclic motion, the period of
this motion, and a set of delays. The delays specify the phase delay
of the cyclic motions of the child modules compared to the
parent. These delays are used to coordinate the motions of the
individual module to obtain a coordinated global behavior. We use this
general algorithm to implement locomotion in a legged
self-reconfigurable robot. We demonstrate that this algorithm
successfully produces quadruped and hexapod gaits in a real
self-reconfigurable robot made from up to nine independent autonomous
modules. We show that the control algorithm scales and argue that the
algorithm is minimal, robust to module failures, to loss of
communication signals, and to interchange of modules.
|
| Published |
In proceedings of the 1st international
joint conference on autonomous agents and
multiagent systems (AAMAS'02), pages 813 - 820, Bologna, Italy, July 15-19, 2002 |
|
|
|
| Title |
Exploiting Task Regularities to Transform Between Reference Frames in Robot Teams |
| Authors |
Richard T. Vaughan, Kasper Støy, Gaurav S. Sukhatme and Maja J. Mataric |
| Abstract |
We describe a team of robots that uses a
trail of landmarks to navigate between places of interest. The
landmarks are not physical; they are waypoint coordinates generated
online by each robot and shared with team-mates over the
network. Waypoints are specified with reference to features in the
world that are relevant to the team's task and common to all
robots. Using such task-level features as landmarks avoids the need to
sense and name physical landmarks. Using these common landmarks, each
robot can transform waypoint coordinates into its local reference
frame, avoiding the cost of maintaining a fixed global coordinate
system. The algorithm is tested in an experiment in which a team of 4
autonomous mobile robots run in our office building for more than 3
hours, traveling a total of 8.2km (5.1 miles). Despite signicant
divergence of their local coordinate systems, they are able to share
waypoints, forming and following a common trail between two fixed
locations. |
| Published |
In proceedings of the IEEE international
conference on Robotics and Automation (ICRA'02), pages 2599-2605, Washington DC, USA, May 11-15, 2002. |
|
|
|
| Title |
Global Locomotion from Local Interaction in Self-Reconfigurable Robots |
| Selected to appear in Journal of Robotics and Autonomous Systems, special issue on the best of IAS-7 |
| Authors |
K. Støy, W.-M. Shen, and P. Will |
| Abstract |
We present a general distributed control algorithm for
achieving locomotion of a self-reconfigurable robot. In this algorithm
each module continuously performs a cyclic sequence of actions with a period T. When a specified fraction of this period d has elapsed a signal is sent to all child modules. Upon receiving this signal the child module resets its action sequence making it delayed d compared to its parent.
The algorithm is minimal and robust to loss of
synchronization signals and change in the number of modules. We show in
three different experiments that the algorithm can be used to
implement a caterpillar, a sidewinder, and a rolling wheel gait in a
real self-reconfigurable robot consisting of eight modules. |
| Published |
In proceedings of the 7th international
conference on intelligent autonomous systems
(IAS-7), pages 309-316, Marina del Rey, California, USA, March 25-27, 2002 |
|
|
|
| Title |
Most Valuable Player: A Robot Device Server for Distributed Control |
| Authors |
B.P. Gerkey, R.T. Vaughan, K. Støy,
A. Howard, G.S. Sukhatme, and M.J. Mataric |
| Abstract |
Successful distributed sensing and control
require data to flow effectively between sensors,
processors and actuators on single robots, in
groups and across the Internet. We propose a
mechanism for achieving this flow which we have
found to be powerful and easy to use; we call it
Player. Player combines an eÆcient message
protocol with a simple device model. It is
implemented as a multi-threaded TCP socket
server that provides transparent network
access to a collection of sensors and actuators, often comprising a robot. The socket
abstraction enables platform and language
independent control of these devices, allowing
the system designer to use the best tool for the
task at hand. Player is freely available from http://robotics.usc.edu/player. |
| Published |
In proceedings of the International
Conference on Intelligent Robotic Systems, pages 1226-1231,
Maui, Hawaii, USA, 2001 |
|
Also appears in Proceedings of the Second
International Workshop on Infrastructure for Agents,
MAS, and Scalable MAS at Autonomous Agents 2001,
Montreal, Canada, May 29, 2001. |
|
|
|
| Title |
Using Situated Communication in Distributed
Autonomous Mobile Robots |
| Author |
Kasper Støy |
| Abstract |
When using communication in multi-robot systems it's often not
desirable to choose an abstract form of communication that separates
the messages from the physical environment in which they have
meaning. If the messages are separated from the environment
localization information has to be encoded into the messages in order
for the receiver to be able to situate the content of the
messages. Here we point out that if we instead use a situated form of
communication that exploits the physical properties of the signal
transferring the message localization information is not needed. We
demonstrate this idea by showing how an extremely simple control
system that uses short range communication can keep four LEGO
Mindstorms robots together in a group. It s also discussed how this
idea can be extended to make it possible to simplify path planning in
multi-robot systems. |
| Published |
In proceedings of the 7th Scandinavian
Conference on Artificial Intelligence (SCAI-7), pages 44-52, Odense, Denmark,
Feb 19-21, 2001 |
|
|
|
| Title |
Blazing a Trail: Insect-inspired Resource Transportation by a Robot Team |
| Author |
R.T. Vaughan, K. Støy, G.S. Sukhatme and M.J. Mataric |
| Abstract |
We demonstrate a team of real robots that
cooperate to robustly transport resource between
two locations in an unknown environment. The
robots use a trail laying and following
algorithm inspired by the trail following of
ants and the waggle dance of honey bees. Rather
than directly marking their environment, the
robots announce landmarks in their odometric
localization space. The system tolerates
significant odometric drift before it breaks down. |
| Published |
In proceedings of the 5th international
symposium on distributed autonomous robot
systems (DARS), pages 111-120, Knoxville, Tennessee, USA,
October 4-6, 2000 |
|
|
|
| Title |
Whistling in the Dark: Cooperative Trail Following in Uncertain Localization Space |
| Author |
R.T. Vaughan, K. Støy, G.S. Sukhatme and M.J. Mataric |
| Abstract |
We demonstrate that a simulated group of
robots can cooperate to robustly transport
resource between two areas in an unknown
environment using an algorithm inspired by the
trail following of ants and the waggle dance of
honey bees. Rather than directly marking the
environment, the robots announce their
successful paths through a common localization
space. It is found that the algorithm is robust
to significant localization error, suggesting
that the method will be viable for teams of real
robots. |
| Published |
In proceedings of the 4th international
conference on autonomous agents, pages 187-194, Barcelona,
Spain, June 3-7, 2000 |
|
|
|
| Title |
Go ahead, make my day: robot conflict resolution by aggressive competition |
| Author |
R.T. Vaughan, K. Støy, G.S. Sukhatme and M.J. Mataric |
| Abstract |
We examine a simulated but realistic
multi-robot transport task that suffers from
spatial interference. Previously described
techniques to reduce interference are not
appropriate for this and related tasks. We
demonstrate the utility of an aggressive
competition to reduce interference and increase
efficiency in our system. A controller is
described which breaks deadlocks in favour of
the most 'aggressive' robot. Sumulation trials
are performed to evaluate a variaty of
aggression functions. Our results and subsequent
discussion sugest that neither a linear
domonance hierarchy nor a simple sensor bias
method offer any advantage over a random
outcome. Finally we discuss some strategies that
might favour the 'correct' outcome of competions
to increase the effieciency of the system. We
are currently implementing these controllers on
a real robot team. |
| Published |
In proceedings of the 6th international
conference on the simulation of adaptive
behavior, pages 491-500, Paris, France, September 11-16, 2000 |
|
|
|
| Title |
Adaptive LEGO Robots. A Robot=Human View on Robotics |
| Author |
H.H. Lund, C. Bjerre, J.H. Nielsen, M. Nielsen, K. Støy |
| Abstract |
In many applications, robots were viewed as a machine. This has resulted in interaction and actuation which is characteristic for machines. When constructing adaptive LEGO robots, we take another view, namely that the robot should resemble a human (or a biological creature) rather than a machine. This has implication on the interaction, the actuation and the control of the robot. Here, I will describe how the robot-as-human approach is in-vestigated in a number of LEGO Mindstorms robot applications. These include making facial expressions, which allows a LEGO robot to express internal "moods", and thereby we might achieve a better human-robot interaction. Another application is the Adaptive LEGO Pet Robot. The Adaptive LEGO Pet Robot's control is based on a modular behaviour system, where a number of the modules are evolved neural networks. Further, the Adaptive LEGO Pet Robot has a number of internal drives such as restlessness and hunger, which allow the robot to react on the internal drives. The human-robot interaction is facilitated by allowing the human to train the LEGO pet robot (rather than to program the robot) to make associations between spoken words (via speech recognition) and evolved behaviours. The Adaptive LEGO Pet Robot is an example of scaling up evolutionary robotics to complex behaviours by combining evolutionary robotics with behaviour-based robotics. |
| Published |
In proceedings of IEEE Systems, Man, and
Cybernetics, 1999 |
|
|
|
Tech Reports and Workshop Proceedings |
| Title |
Player Robot Server |
| Authors |
B. Gerkey, K. Støy, and R.T. Vaughan |
| Published |
In institute for robotics and intelligent
systems technical report IRIS-00-391, University
of Southern California, 2000 |
|
|
|
Master's Thesis |
| Title |
Adaptive Control Systems for Autonomous Robots |
| Author |
K. Støy |
| Published |
1999 |
|
|
