Evolving Spiking Neural Network Controllers for Autonomous Robots (original) (raw)
Related papers
A multi-agent evolutionary robotics framework to train spiking neural networks
2020
A novel multi-agent evolutionary robotics (ER) based framework, inspired by competitive evolutionary environments in nature, is demonstrated for training Spiking Neural Networks (SNN). The weights of a population of SNNs along with morphological parameters of bots they control in the ER environment are treated as phenotypes. Rules of the framework select certain bots and their SNNs for reproduction and others for elimination based on their efficacy in capturing food in a competitive environment. While the bots and their SNNs are given no explicit reward to survive or reproduce via any loss function, these drives emerge implicitly as they evolve to hunt food and survive within these rules. Their efficiency in capturing food as a function of generations exhibit the evolutionary signature of punctuated equilibria. Two evolutionary inheritance algorithms on the phenotypes, Mutation and Crossover with Mutation, are demonstrated. Performances of these algorithms are compared using ensembl...
Evolving spiking neural networks for robot control
Procedia Computer Science, 2011
We describe a sequence of experiments in which a robot "brain" was evolved to mimic the behaviours captured under control of a heuristic rule program (imitation learning). The task was light-seeking while avoiding obstacles using binocular light sensors and a trio of IR proximity sensors. The "brain" was a spiking neural network simulator whose parameters were tuned by a genetic algorithm, where fitness was assessed by the closeness to target output spike trains. Spike trains were frequency encoded. The network topology was manually designed, and then modified in response to observed difficulties during evolution. We noted that good performance seems best approached by judicious mixing of excitation and inhibition. Besides robotic applications, the domain of "smart" prosthetics also appears promising.
Evolving Spiking Neural Networks for Control of Artificial Creatures
To understand and analysis behavior of complicated and intelligent organisms, scientists apply bio-inspired concepts including evolution and learning to mathematical models and analyses. Researchers utilize these perceptions in different applications, searching for improved methods and approaches for modern computational systems. This paper presents a genetic algorithm based evolution framework in which Spiking Neural Network (SNN) of artificial creatures are evolved for higher chance of survival in a virtual environment. The artificial creatures are composed of randomly connected Izhikevich spiking reservoir neural networks using population activity rate coding. Inspired by biological neurons, the neuronal connections are considered with different axonal conduction delays. Simulations results prove that the evolutionary algorithm has the capability to find or synthesis artificial creatures which can survive in the environment successfully.
Evolution of spiking neural circuits in autonomous mobile robots
International Journal of Intelligent Systems, 2006
We describe evolution of spiking neural architectures to control navigation of autonomous mobile robots. Experimental results with simple fitness functions indicate that evolution can rapidly generate spiking circuits capable of navigating in textured environments with simple genetic representations that encode only the presence or absence of synaptic connections. Building on those results, we then describe a low-level implementation of evolutionary spiking circuits in tiny micro-controllers that capitalizes on compact genetic encoding and digital aspects of spiking neurons. The implementation is validated on a sugar-cube robot capable of developing functional spiking circuits for collision-free navigation.
Evolutionary approaches to neural control in mobile robots
SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218)
| This article is centered on the application of evolutionary techniques to the automatic design of neural controllers for mobile robots. About 30 papers are reviewed and classi ed in a framework that takes into account the speci c robots involved, the behaviors that are evolved, the characteristics of the corresponding neural controllers, how these controllers are genetically encoded, and whether or not an individual learning process complements evolution. Related research e orts in evolutionary robotics are occasionally cited. If it is yet unclear whether such approaches will scale up with increasing complexity, foreseeable bottlenecks and prospects of improvement are discussed in the text.
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.
Neuro-Evolution of Mobile Robot Controller
MENDEL
We present a neuro-evolution design for control of a mobile robot in 2D simulation environment. The mobile robot is moving in unknown environment with obstacles from the start position to the goal position. The trajectory of the robot is controlled by a neural network – based controller which inputs are information from several laser beam sensors. The learning of the neural network controller is based on an evolutionary approach, which is provided by genetic algorithm.
Lecture Notes in Computer Science, 2014
The Artificial Neural Networks (ANNs) have been used for solving problems in many theoretical and practical areas. Advances on the field of ANNs have derived in Spiking Neural Networks (SNNs); which are considered as the third generation of ANNs. SNNs receive/send the information by timing of events (spikes) instead by the spike rate; as their predecessors do. Although SNNs are capable to solve some functions with fewer neurons than networks of previous generations, there aren't rules to set the architecture of any kind of ANN for solving a specific task; usually the architecture is set empirically based on the designer's experience and the neural network's performance over the problem. Recently, metaheuristic algorithms are being implemented to optimize some aspect on ANNs such as weight, connections and even the architecture. This work proposes a generic framework for automatic construction of Fully-Connected Feed-Forward Spiking Neural Networks through an indirect representation by means of Grammatical Evolution (GE) based on Evolutionary Strategy (ES) algorithm. Two well-known benchmarks datasets of pattern recognition were used for testing the proposal of this paper.
Biologically Inspired Agent System Based on Spiking Neural Network
Lecture Notes in Computer Science, 2010
The paper presents an architecture of a biologically inspired agent. Its physical body is described first. The agent's movement is directly controlled by Spiking Neural Network. To achieve this goal, the network is trained by a genetic algorithm. The agents move in a 3D physical environment. Their main goal is to effectively translocate themselves using a virtual body structure and muscles. This approach is inspired by a biological assumptions, where the neural network receives signals from sensors and directly controls the muscles. The application of Spiking Neural Network needs a suitable signal encoding method, which is also described. The system is flexible and it allows to create agents with various body structures and different neural controllers. Experiments presented in the paper refer to a simple snake-like creature. The effectiveness of controllers based on a standard threshold network and the spiking one are compared.