Evolved homogeneous neuro-controllers for robots with different sensory capabilities: coordinated motion and cooperation (original) (raw)
Related papers
Strengths and synergies of evolved and designed controllers: A study within collective robotics
Artificial Intelligence, 2009
This paper analyses the strengths and weaknesses of self-organising approaches, such as evolutionary robotics, and direct design approaches, such as behaviour-based controllers, for the production of autonomous robots' controllers, and shows how the two approaches can be usefully combined. In particular, the paper proposes a method for encoding evolved neural-network based behaviours into motor schemabased controllers and then shows how these controllers can be modified and combined to produce robots capable of solving new tasks. The method has been validated in the context of a collective robotics scenario in which a group of physically assembled simulated autonomous robots are requested to produce different forms of coordinated behaviours (e.g., coordinated motion, walled-arena exiting, and light pursuing).
Philosophical Transactions of The Royal Society A: Mathematical, Physical and Engineering Sciences, 2003
We report on recent work in which we employed arti¯cial evolution to design neural network controllers for small, homogeneous teams of mobile autonomous robots. The robots were evolved to perform a formation-movement task from random starting positions, equipped only with infrared sensors. The dual constraints of homogeneity and minimal sensors make this a non-trivial task. We describe the behaviour of a successful system in which robots adopt and maintain functionally distinct roles in order to achieve the task. We believe this to be the¯rst example of the use of arti¯cial evolution to design coordinated, cooperative behaviour for real robots.
Structure and Function of Evolved Neuro-Controllers for Autonomous Robots
Connection Science, Vol. 16, No. 4, 2004
The Artificial Life approach to Evolutionary Robotics is used as a fundamental framework for the development of a modular neural control of autonomous mobile robots. The applied evolutionary technique is especially designed to grow different neural structures with complex dynamical properties. This is due to a modular neurodynamics approach to cognitive systems, stating that cognitive processes are the result of interacting dynamical neuro-modules. The evolutionary algorithm is de- scribed, and a few examples for the the versatility of the procedures are given. Besides solutions for standard tasks like exploration, obsta- cle avoidance, and tropism, also the sequential evolution of morphology and control of a biped is demonstrated. A further example describes the co-evolution of different neuro-controllers cooperating to keep a gravita- tionally driven art-robot in constant rotation.
Evolution of Neuro-Controllers for Robots' Alignment using Local Communication
2009
In this paper, we use artificial evolution to design homogeneous neural network controller for groups of robots required to align. Aligning refers to the process by which the robots managed to head towards a common arbitrary and autonomously chosen direction starting from initial randomly chosen orientations. The cooperative interactions among robots require local communications that are physically implemented using infrared signalling. We study the performance of the evolved controllers, both in simulation and in reality for different group sizes. In addition, we analyze the most successful communication strategy developed using artificial evolution.
Artificial Life, 2013
Organisms that live in groups, from microbial symbionts to social insects and schooling fish, exhibit a number of highly efficient cooperative behaviours, often based on role taking and specialisation. These behaviours are relevant not only for the biologist but also for the engineer interested in decentralized collective robotics. We address these phenomena by carrying out experiments with groups of two simulated robots controlled by neural networks whose connection weights are evolved by using genetic algorithms. These algorithms and controllers are well suited to autonomously find solutions to decentralized collective robotic tasks based on principles of self-organization. The paper first presents a taxonomy of role taking and specialisation mechanisms related to evolved neuralnetwork controllers. Then it introduces two cooperation tasks which can be accomplished by either role taking or specialisation and uses these tasks to compare four different genetic algorithms to evaluate their capacity to evolve a suitable behavioural strategy which depends on the task demands.
Neuro-evolved Agent-based Cooperative Controller for a Behavior-based Autonomous Robot
Proc. of First Workshop on Automatics, Vision and …, 2004
we present in this work a cooperative control paradigm for the autonomous navigation of a mobile robot and demonstrate that the cooperative controller learns faster and better than a centralized one. Behaviors emerge from the neuro-evolved controller, in order to achieve a designed task and without been defined at design stage. In our proposal, a robotic agent is divided into sub-agents, each one controlling one sensor or actuator element of the robot. Meanwhile the sub-agent learns to handle the element, it also learns to cooperate with the other ones. The emergence of behaviors happens when the coevolution of several sub-agents embodied into the single robotic agent stabilizes. A distributed version of the ESP neuro-evolving algorithm is used for the evolution of the overall distributed controller.
Behavioral control through evolutionary neurocontrollers for autonomous mobile robot navigation
Robotics and Autonomous …, 2009
This paper deals with the study of scaling up behaviors in evolutive robotics (ER). Complex behaviours were obtained from simple ones. Each behavior is supported by an artificial neural network (ANN)-based controller or neurocontroller. Hence, a method for the generation of a hierarchy of neurocontrollers, resorting to the paradigm of Layered Evolution (LE), is developed and verified experimentally through computer simulations and tests in a Kheperamicro-robot. Several behavioral modules are initially evolved using specialized neurocontrollers based on different ANN paradigms. The results show that simple behaviors coordination through LE is a feasible strategy that gives rise to emergent complex behaviors. These complex behaviors can then solve real-world problems efficiently. From a pure evolutionary perspective, however, the methodology presented is too much dependent on user’s prior knowledge about the problem to solve and also that evolution take place in a rigid, prescribed framework. Mobile robot’s navigation in an unknown environment is used as a test bed for the proposed scaling strategies.
Evolution of signalling in a group of robots controlled by dynamic neural networks
2007
Communication is a point of central importance in swarms of robots. This paper describes a set of simulations in which artificial evolution is used as a means to engineer robot neuro-controllers capable of guiding groups of robots in a categorisation task by producing appropriate actions. Communicative behaviour emerges, notwithstanding the absence of explicit selective pressure (coded into the fitness function) to favour signalling over non-signalling groups.