A well known model of reinforcement learning is called Adap-tive Heuristic Critic learning. It is composed of two so called \neuronlike adaptive elements" and has been used to solve diicult learning control problems. In this paper we present an FPGA design and implementation of such algorithm, and, furthermore, we describe a neurocontroller system composed of a network of neuronlike adaptive el...

Presents an approach and a systematic design methodology to adaptive motion control based on neural networks (NNs) for high-performance robot manipulators, for which stability conditions and performance evaluation are given. The neurocontroller includes a linear combination of a set of off-line trained NNs, and an update law of the linear combination coefficients to adjust robot dynamics and pa...

Neurocontrol is a crucial area of fundamental research within the neural network eld. Adaptive Heuristic Critic learning is a key algorithm for real time adaptation in neurocontrollers. In this paper we present how an unsupervised neural network model with adaptable structure can be used to speed-up Adaptive Heuristic Critic learning, its FPGA design , and how it adapts the neurocontroller to t...

Synaptic plasticity for recurrent neural networks is derived by introducing neurons as self-regulating units. These neurons have homeostatic properties for certain parameter domains. Depending on its underlying connectivity a neurocontroller endowed with the derived synaptic plasticity rule can generate a variety of different behaviors. The structure of these networks can be developed by evolut...

Behaviors such as exploration and homing, that seemingly demand a complex control system, only require a perceptron that connects a robot’s sensors to its motors. This is shown by evolving such neurocontrollers for the Khepera robot. An exploitation of the robot’s perception of the environment’s geometrical shape allows the robot to encode time, even though explicitly it is not presented with t...

We introduce a model of cellular growth that generates neurocontrollers capable of guiding simple simulated agents in a harvesting task. The morphogenesis of the neurocontroller is itself controlled by an evolved artificial neural network. The neural network operates only on local variables and chemical concentrations and is thought as a flexible model of a gene regulatory system and cell metab...

A neurocontroller is described which generates the basic locomotion and controls the sensor-driven behavior ofa four-legged and a sixlegged walking machine. The controller utilizes discrete-time neurodynamics, and is ofmodular structure. One module isfor processing sensor signals, one is a neural oscillator network serving as a central pattern generator, and the third one is a so-called velocit...