Efficient learning of reactive robot behaviors with a Neural-Q_learning approach

The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed

Real-Time software control of neural stimulation in a closed loop Animat system

A recent area for investigation into the development of adaptable robot control is the use of living neuronal networks to control a mobile robot. The so-called Animat paradigm comprises a neuronal network (the ‘brain’) connected to an external embodiment (in this case a mobile robot), facilitating potentially robust, adaptable robot control and increased understanding of neural processes. Sensory input from the robot is provided to the neuronal network via stimulation on a number of electrodes embedded in a specialist Petri dish (Multi Electrode Array (MEA)); accurate control of this stimulation is vital. We present software tools allowing precise, near real-time control of electrical stimulation on MEAs, with fast switching between electrodes and the application of custom stimulus waveforms. These Linux-based tools are compatible with the widely used MEABench data acquisition system. Benefits include rapid stimulus modulation in response to neuronal activity (closed loop) and batch processing of stimulation protocols.

Neural systems in the visual control of steering

Visual control of locomotion is essential for most mammals and requires coordination between perceptual processes and action systems. Previous research on the neural systems engaged by self-motion has focused on heading perception, which is only one perceptual subcomponent. For effective steering, it is necessary to perceive an appropriate future path and then bring about the required change to heading. Using function magnetic resonance imaging in humans, we reveal a role for the parietal eye fields (PEFs) in directing spatially selective processes relating to future path information. A parietal area close to PEFs appears to be specialized for processing the future path information itself. Furthermore, a separate parietal area responds to visual position error signals, which occur when steering adjustments are imprecise. A network of three areas, the cerebellum, the supplementary eye fields, and dorsal premotor cortex, was found to be involved in generating appropriate motor responses for steering adjustments. This may reflect the demands of integrating visual inputs with the output response for the control device.

Adaptive control of event integration

Identifying 2 target stimuli in a rapid stream of visual symbols is much easier if the 2nd target appears immediately after the 1st target (i.e., at Lag 1) than if distractor stimuli intervene. As this phenomenon comes with a strong tendency to confuse the order of the targets, it seems to be due to the integration of both targets into the same attentional episode or object file. The authors investigated the degree to which people can control the temporal extension of their (episodic) integration windows by manipulating the expectations participants had with regard to the time available for target processing. As predicted, expecting more time to process increased the number of order confusions at Lag 1. This was true for between-subjects and within-subjects (trial-to-trial) manipulations, suggesting that integration windows can be adapted actively and rather quickly.

Predictive control using feedback linearization based on dynamic neural models

This paper presents a hybrid control strategy integrating dynamic neural networks and feedback linearization into a predictive control scheme. Feedback linearization is an important nonlinear control technique which transforms a nonlinear system into a linear system using nonlinear transformations and a model of the plant. In this work, empirical models based on dynamic neural networks have been employed. Dynamic neural networks are mathematical structures described by differential equations, which can be trained to approximate general nonlinear systems. A case study based on a mixing process is presented.

Conceptualisation of an application of adaptive synthetic socioeconomic agents for intelligent network control

The deployment of Quality of Service (QoS) techniques involves careful analysis of area including: those business requirements; corporate strategy; and technical implementation process, which can lead to conflict or contradiction between those goals of various user groups involved in that policy definition. In addition long-term change management provides a challenge as these implementations typically require a high-skill set and experience level, which expose organisations to effects such as “hyperthymestria” [1] and “The Seven Sins of Memory”, defined by Schacter and discussed further within this paper. It is proposed that, given the information embedded within the packets of IP traffic, an opportunity exists to augment the traffic management with a machine-learning agent-based mechanism. This paper describes the process by which current policies are defined and that research required to support the development of an application which enables adaptive intelligent Quality of Service controls to augment or replace those policy-based mechanisms currently in use.

Autonomous intelligent cruise control using a novel multiple-controller framework incorporating fuzzy-logic-based switching and tuning

This paper presents a novel intelligent multiple-controller framework incorporating a fuzzy-logic-based switching and tuning supervisor along with a generalised learning model (GLM) for an autonomous cruise control application. The proposed methodology combines the benefits of a conventional proportional-integral-derivative (PID) controller, and a PID structure-based (simultaneous) zero and pole placement controller. The switching decision between the two nonlinear fixed structure controllers is made on the basis of the required performance measure using a fuzzy-logic-based supervisor, operating at the highest level of the system. The supervisor is also employed to adaptively tune the parameters of the multiple controllers in order to achieve the desired closed-loop system performance. The intelligent multiple-controller framework is applied to the autonomous cruise control problem in order to maintain a desired vehicle speed by controlling the throttle plate angle in an electronic throttle control (ETC) system. Sample simulation results using a validated nonlinear vehicle model are used to demonstrate the effectiveness of the multiple-controller with respect to adaptively tracking the desired vehicle speed changes and achieving the desired speed of response, whilst penalising excessive control action. Crown Copyright (C) 2008 Published by Elsevier B.V. All rights reserved.

Invasive neural prosthesis for neural signal detection and nerve stimulation

This paper specifically examines the implantation of a microelectrode array into the median nerve of the left arm of a healthy male volunteer. The objective was to establish a bi-directional link between the human nervous system and a computer, via a unique interface module. This is the first time that such a device has been used with a healthy human. The aim of the study was to assess the efficacy, compatibility, and long term operability of the neural implant in allowing the subject to perceive feedback stimulation and for neural activity to be detected and processed such that the subject could interact with remote technologies. A case study demonstrating real-time control of an instrumented prosthetic hand by means of the bi-directional link is given. The implantation did not result in infection, and scanning electron microscope images of the implant post extraction have not indicated significant rejection of the implant by the body. No perceivable loss of hand sensation or motion control was experienced by the subject while the implant was in place, and further testing of the subject following the removal of the implant has not indicated any measurable long term defects. The implant was extracted after 96 days. Copyright © 2004 John Wiley & Sons, Ltd.

Cultured neural networks

This special section contains papers addressing various aspects associated with the issue Of Cultured neural networks. These are networks, that are formed through the monitored growth of biological neural tissue. In keeping with the aims of the International Journal of Adaptive Control and Signal Processing, the key focus of these papers is to took at particular aspects of signal processing in terms of both stimulating such a network and in assigning intent to signals collected as network outputs. Copyright (C) 2009 John Wiley & Sons, Ltd.

Simplified parameter adaptive control

A simple parameter adaptive controller design methodology is introduced in which steady-state servo tracking properties provide the major control objective. This is achieved without cancellation of process zeros and hence the underlying design can be applied to non-minimum phase systems. As with other self-tuning algorithms, the design (user specified) polynomials of the proposed algorithm define the performance capabilities of the resulting controller. However, with the appropriate definition of these polynomials, the synthesis technique can be shown to admit different adaptive control strategies, e.g. self-tuning PID and self-tuning pole-placement controllers. The algorithm can therefore be thought of as an embodiment of other self-tuning design techniques. The performances of some of the resulting controllers are illustrated using simulation examples and the on-line application to an experimental apparatus.

Adaptive deadbeat control of stochastic systems

This paper considers the use of a discrete-time deadbeat control action on systems affected by noise. Variations on the standard controller form are discussed and comparisons are made with controllers in which noise rejection is a higher priority objective. Both load and random disturbances are considered in the system description, although the aim of the deadbeat design remains as a tailoring of reference input variations. Finally, the use of such a deadbeat action within a self-tuning control framework is shown to satisfy, under certain conditions, the self-tuning property, generally though only when an extended form of least-squares estimation is incorporated.