• Corpus ID: 14212342

Artificial Life and Real Robots

@inproceedings{Brooks1992ArtificialLA,
  title={Artificial Life and Real Robots},
  author={Rodney A. Brooks},
  year={1992}
}
The first part of this paper explores the general issues in using Artificial Life techniques to program actual mobile robots. In particular it explores the difficulties inherent in transferring programs evolved in a simulated environment to run on an actual robot. It examines the dual evolution of organism morphology and nervous systems in biology. It proposes techniques to capture some of the search space pruning that dual evolution offers in the domain of robot programming. It explores the… 

Figures from this paper

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.

Maze exploration behaviors using an integrated evolutionary robotics environment

Evolutionary, developmental neural networks for robust robotic control

TLDR
Three methods for improving the use of artificial evolution as a tool for generating controllers for physical robots are described, demonstrated, quantified, and compared to hand-designed controllers.

Evolving Mobile Robots in Simulated and Real Environments

TLDR
By evolving neural controllers for a Khepera robot in computer simulations and then transferring the agents obtained to the real environment, it is shown that an accurate model of a particular robot-environment dynamics can be built by sampling the real world through the sensors and the actuators of the robot.

Mobile Robot Path Planning Using Genetic Algorithms

TLDR
A new GA path-planning approach is described that proposes the evolution of a chromosome attitudes structure to control a simulated mobile robot, called Khepera, and demonstrates the controller’s adaptability, displaying near-optimal paths in different configurations of the environment.

Evolving Robots: from Simple Behaviours to Complete Systems

TLDR
This thesis examines the use of the evolutionary approach in designing robots; the explorations range from evolving simple behaviours for real robots, to complex behaviours (also for real Robots), and finally to complete robot systems — including controllers and body plans.

Evolutionary neurocontrollers for autonomous mobile robots

An On-Line Method to Evolve Behavior and to Control a Miniature Robot in Real Time with Genetic Programming

TLDR
This work presents an on-line control method that is evaluated in two different physical environments and applied to two tasks—obstacle avoidance and object following—using the Khepera robot platform and shows fast learning and good generalization.

Online Evolution for a Self-Adapting Robotic Navigation System Using Evolvable Hardware

TLDR
It is shown that a model-based evolution can reduce these interactions by two orders of magnitude, even when some of the robot's sensors are blinded, thus allowing us to apply evolutionary processes online to obtain a self-adaptive tracking system in the real world, when the implementation is accelerated by the utilization of evolvable hardware.

Issues in evolutionary robotics

TLDR
It is proposed that, sooner rather than later, visual processing will be required in order for robots to engage in non-trivial navigation behaviours, and time constraints suggest that initial architecture evaluations should be largely done in simulation.
...

References

SHOWING 1-10 OF 30 REFERENCES

New Approaches to Robotics

TLDR
The relationship to traditional academic robotics and traditional artificial intelligence is examined and the use of representations, expectations, plans, goals, and learning is demonstrated, but without resorting to the traditional uses of central, abstractly manipulable or symbolic representations.

A robot that walks; emergent behaviors from a carefully evolved network

  • R. Brooks
  • Computer Science
    Proceedings, 1989 International Conference on Robotics and Automation
  • 1989
TLDR
This paper suggests one possible mechanism for analagous robot evolution by describing a carefully designed series of networks, each one being a strict augmentation of the previous one, which control a six-legged walking machine capable of walking over rough terrain and following a person passively sensed in the infrared spectrum.

A robust layered control system for a mobile robot

  • R. Brooks
  • Computer Science
    IEEE J. Robotics Autom.
  • 1986
TLDR
A new architecture for controlling mobile robots is described, building a robust and flexible robot control system that has been used to control a mobile robot wandering around unconstrained laboratory areas and computer machine rooms.

Learning in embedded systems

TLDR
This dissertation addresses the problem of designing algorithms for learning in embedded systems using Sutton's techniques for linear association and reinforcement comparison, while the interval estimation algorithm uses the statistical notion of confidence intervals to guide its generation of actions.

Learning to Coordinate Behaviors

TLDR
An algorithm which allows a behavior-based robot to learn on the basis of positive and negative feedback when to activate its behaviors has been described and tested successfully on an autonomous 6-legged robot.

Evolution and co-evolution of computer programs to control independently-acting agents

TLDR
The genetic programming paradigm is extended to a "co-evolution" algorithm which operates simultaneously on two populations of independently-acting hierarchical computer programs of various sizes and shapes.

Intelligence without Representation

A Distributed Model for Mobile Robot Environment-Learning and Navigation

TLDR
A distributed method for mobile robot navigation, spatial learning, and path planning is presented and the main issues addressed are: distributed, procedural, and qualitative representation and computation, emergent behaviors, dynamic landmarks, minimized communication.