Embodied evolution: embodying an evolutionary algorithm in a population of robots

@article{Watson1999EmbodiedEE,
  title={Embodied evolution: embodying an evolutionary algorithm in a population of robots},
  author={Richard A. Watson and S.G. Ficiei and James B. Pollack},
  journal={Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406)},
  year={1999},
  volume={1},
  pages={335-342 Vol. 1}
}
  • R. Watson, S.G. Ficiei, J. Pollack
  • Published 6 July 1999
  • Computer Science
  • Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406)
We introduce Embodied Evolution (EE) as a methodology for the automatic design of robotic controllers. [...] Key Method In EE, an evolutionary algorithm is distributed amongst and embodied within a population of physical robots that reproduce with one another while situated in the task environment. We have built a population of eight robots and successfully implemented our first experiments. The controllers evolved by EE compare favorably to hand-designed solutions for a simple task. We detail our methodology…Expand
Embodied Evolution: Distributing an evolutionary algorithm in a population of robots
TLDR
Embodied Evolution is introduced as a new methodology for evolutionary robotics that uses a population of physical robots that autonomously reproduce with one another while situated in their task environment and designs a fully decentralized, asynchronous evolutionary algorithm. Expand
Situated and Embodied Evolution in Collective Evolutionary Robotics
Evolutionary robotics is a challenging technique for creation of autonomous robots based on the mechanism of Darwinian evolution. In the conventional evolutionary robotics, the “simulate-andtransfer”Expand
A framework for embodied evolution with pre-evaluation applied to a biped robot
TLDR
This article introduces pre-evaluation into the EE framework for a biped robot in order to restrain the behavior of a robot of which the fitness is estimated to be low, especially falling down onto the ground. Expand
Predation: an approach to improving the evolution of real robots with a distributed evolutionary controller
  • E. Simões, D. Barone
  • Engineering, Computer Science
  • Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292)
  • 2002
TLDR
It is described how the evolutionary system controls such a small robot population in Teal time and the effects of predation in avoiding local optimum and it is able to achieve obstacle avoidance behaviour with the robot population evolving while deployed in the field. Expand
Real-World Evolution of Robot Morphologies: A Proof of Concept
TLDR
Following a general system plan, a robotic habitat is implemented that contains all system components in the simplest possible form and provides a generic workflow for the creation of more complex incarnations. Expand
Automating the Incremental Evolution of Controllers for Physical Robots
TLDR
This article shows that it is possible, for the first time, to incrementally evolve a neural robot controller for different obstacle avoidance tasks with no human intervention and offers a high level of robustness and precision that could potentially open up the range of problems amenable to embodied evolution. Expand
Embedding a distributed evolutionary system into a population of autonomous mobile robots
  • E. Simões, K. Dimond
  • Computer Science
  • 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat.No.01CH37236)
  • 2001
TLDR
A fully embedded distributed evolutionary system that is able to achieve collision-free navigation in a few hundreds of trials is described and the influence of different mutation rates on the performance of the system is shown. Expand
odNEAT: An Algorithm for Distributed Online, Onboard Evolution of Robot Behaviours
TLDR
This work proposes and evaluates a novel approach to online distributed evolution of neural controllers called odNEAT, a completely distributed evolutionary algorithm for online learning in groups of embodied agents such as robots that approximates the performance of rtNEAT. Expand
Evolving Controllers for Real Robots: A Survey of the Literature
TLDR
A survey of recent methods in GEC-developed mobile robot controllers, focusing on those methods that include a physical robot at some point in the learning loop. Expand
EVOLUTIONARY ROBOTS : THE NEXT GENERATION
After reviewing current approaches in Evolutionary Robotics, we point to directions of research that are likely to bring interesting results in the future. We then address two crucial aspects forExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 76 REFERENCES
Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot
TLDR
The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot, and shows a number of emergent phenomena that are characteristic of autonomous agents. Expand
Explorations in Evolutionary Robotics
TLDR
Results demonstrate that robust visually guided control systems evolve from evaluation functions that do not explicitly require monitoring visual input, and propose an automatic design process involving artificial evolution, wherein the basic building blocks for evolving cognitive architectures are noise-tolerant dynamical neural networks. Expand
Automatic Creation of an Autonomous Agent : GeneticEvolution of a Neural-Network Driven
The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot. The evolutionary approach to the development of neural controllers for autonomous agentsExpand
Evolution Versus Design: Controlling Autonomous Robots
  • P. Husbands, I. Harvey
  • Computer Science
  • Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.
  • 1992
This paper sets out and justifies a methodology for the development of the control systems, or ‘cognitive architectures)) of autonomous mobile robots. It will be argued that the design b y hand ofExpand
Evolution of homing navigation in a real mobile robot
TLDR
The evolution of a discrete-time recurrent neural network to control a real mobile robot and it is shown that the autonomous development of a set of behaviors for locating a battery charger and periodically returning to it can be achieved by lifting constraints in the design of the robot/environment interactions. Expand
Using Emergent Modularity to Develop Control Systems for Mobile Robots
  • S. Nolfi
  • Computer Science
  • Adapt. Behav.
  • 1997
TLDR
It is shown that it is not possible to find simple correlations; rather, module switching and interaction are correlated with low-level sensorimotor mappings, which implies that the engineering-oriented approach to behavior-based robotics might have serious limitations. Expand
Artificial Life and Real Robots
TLDR
A new abstraction for behavior-based robot programming which is specially tailored to be used with genetic programming techniques is introduced, which will be necessary to automatically evolve programs that are one to two orders of magnitude more complex than those previously reported in any domain. Expand
Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis
TLDR
New ways of thinking about and building simulations upon which fitness assessments of evolving controllers can be performed are outlined and a potential methodology for building simulations in which evolving controllers are forced to satisfy these conditions if they are to be reliably fit is developed. Expand
Half-baked, Ad-hoc and Noisy: Minimal Simulations for Evolutionary Robotics
TLDR
A theoretical framework and formal language for understanding how simple, fast simulations can be used to evolve controllers for real robots is put forward and techniques are derived for ensuring that controllers which evolve to be reliably reliable within a simulation will transfer into the real world. Expand
Towards a Reliable Set-Up for Bio-Inspired Collective Experiments with Real Robots
TLDR
A set of tools developed at the laboratory that provide a reliable set-up for conducting bio-inspired experiments with real robots and propose concrete solutions to some of the main problems in collective robotics. Expand
...
1
2
3
4
5
...