A Simple Aplysia-Like Spiking Neural Network to Generate Adaptive Behavior in Autonomous Robots

  title={A Simple Aplysia-Like Spiking Neural Network to Generate Adaptive Behavior in Autonomous Robots},
  author={Fady S. Alnajjar and Kazuyuki Murase},
  journal={Adaptive Behavior},
  pages={306 - 324}
In this article, we describe an adaptive controller for an autonomous mobile robot with a simple structure. [] Key Method The synaptic weights were modified dependent on the firing rates of the presynaptic modulation signal and that of the hidden-layer neuron by STDP. In experiments using a real robot, which uses a similar simple SNN controller, the robot adapted quickly to the given environment in a single trial by organizing the weights, acquired navigation and obstacle-avoidance behavior. In addition, it…

Figures from this paper

An Aplysia-like Spiking Neural Network Implementation of Sensory Fusion on an Autonomous Robot
Experimental results show that a physical robot Khepera with the proposed controller quickly adapted into an open environment by evolving obstacle avoidance behavior while locating a target object using both its IR sensors and liner-camera.
Experimental Study of Reinforcement Learning in Mobile Robots Through Spiking Architecture of Thalamo-Cortico-Thalamic Circuitry of Mammalian Brain
Experimental studies prove that through the proposed method, thalamo-cortical structure could be trained successfully to learn to perform various robotic tasks.
Classical conditioning in different temporal constraints: an STDP learning rule for robots controlled by spiking neural networks
This work investigates adaptive behaviours for an intelligent robotic agent when subjected to temporal stimuli consisting of associations of contextual cues and simple reflexes. This is made possible
The development of bio-inspired cortical feature maps for robot sensorimotor controllers
A method of autonomous regulation of the map development process which adapts the learning dependent upon input activity is developed, showing that distinct directionally selective maps for both the motor and visual modalities are produced under a range of experimental scenarios.
An Artificial Synaptic Plasticity Mechanism for Classical Conditioning with Neural Networks
We present an artificial synaptic plasticity (ASP) mechanism that allows artificial systems to make associations between environmental stimuli and learn new skills at runtime. ASP builds on the
FPGA Implementation of Simplified Spiking Neural Network
A simpler and computationally efficient SNN model is described and it is demonstrated that the proposed model analyzes a fully connected network consisting of 800 neurons and 12,544 synapses in real-time.
A Spiking Neural Network Model of the Medial Superior Olive Using Spike Timing Dependent Plasticity for Sound Localization
A Spiking Neural Network (SNN) based model of the MSO is presented, trained using the Spike Timing Dependent Plasticity learning rule and able to perform sound localization with an accuracy of 91.82% when an error tolerance of ±10° is used.
A Novel Hierarchical Constructive BackPropagation with Memory for Teaching a Robot the Names of Things
This study investigates a new idea to develop incremental learning and memory model, a Hierarchical Constructive BackPropagation with Memory (HCBPM), which indicates the efficiency of the model to build a social learning environment between the user and the robot.
Motor Control System for Adaptation of Healthy Individuals and Recovery of Poststroke Patients: A Case Study on Muscle Synergies
It is revealed that computed muscle synergy characteristics changed after healthy participants were introduced to the unfamiliar environment, compared with those initially observed in the familiar environment, and exhibited an increased neural response to unpredictable inputs.
Muscle Synergy Features in Behavior Adaptation and Recovery
The results revealed that the dimension of the resulting synergies of the healthy participants when introduced to an unfamiliar task was initially lower than the original; causing a restriction in the range of the joint motions and resulting in abnormal movements.


Self-organization of Spiking Neural Network that Generates Autonomous Behavior in a Real Mobile Robot
A self-organization algorithm based on a use-dependent synaptic potentiation and depotentiation at synapses of input layer to hidden layer and of hidden layer to output layer was formulated and implemented into the robot and incrementally organized the network.
Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots
It is shown that evolution finds relatively quickly functional spiking controllers capable of navigating in irregularly textured environments without hitting obstacles using a very simple genetic encoding and fitness function.
Unsupervised learning and self-organization in networks of spiking neurons
This chapter investigates possible mechanisms of unsupervised learning and self-organization in networks of spiking neurons, and describes a biologically plausible algorithm for these networks to find clusters in a high dimensional input space or a subspace of it.
Networks of Spiking Neurons: The Third Generation of Neural Network Models
  • W. Maass
  • Computer Science
    Electron. Colloquium Comput. Complex.
  • 1996
Evolving spike-timing-dependent plasticity for single-trial learning in robots.
  • E. D. Di Paolo
  • Biology
    Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
  • 2003
Experimental single-trial learning in an evolved robot model of synaptic spike-timing-dependent plasticity shows that plasticity is used to sustain the neural activity corresponding both to the normal phototaxis condition and to the learned behaviour.
Networks of spiking neurons: the third generation of neural network models
  • W. Maas
  • Biology, Computer Science
  • 1997
Genetic algorithm for a fuzzy spiking neural network of a mobile robot
  • N. Kubota, H. Sasaki
  • Computer Science
    2005 International Symposium on Computational Intelligence in Robotics and Automation
  • 2005
This paper applies a steady-state genetic algorithm for acquiring the suitable network structure through the interaction with the environment and shows the robot can update the network structure and learn the weights of FSNN according to the spatio-temporal context of the facing environment.
An Evolutionary Ecological Approach to the Study of Learning Behavior Using a Robot-Based Model
This article explores the applicability of integrated neural networks with fixed connection weights and simple 'leaky-integrator' neurons as controllers for autonomous learning robots and shows that such a control system is capable of integrating reactive and learned behaviour without explicitly needing hand-designed modules, dedicated to a particular behavior, or an externally introduced reinforcement signal.
Functional significance of long-term potentiation for sequence learning and prediction.
It is found that, due to a temporal asymmetry in the induction of NMDA-mediated LTP, firing patterns in a neuronal array that initially represent the current value of a sensory input will, after training, provide an experienced-based prediction of that input instead.
From Wheels to Wings with Evolutionary Spiking Circuits
The motivation and methodology used to reach the EPFL indoor flying project goal are described as well as the results of a number of preliminary experiments on vision-based wheeled and flying robots.