Showing papers in "Robotics and Autonomous Systems in 1995"

TL;DR: The invention relates to a circuit for use in a receiver which can receive two-tone/stereo signals which is intended to make a choice between mono or stereo reproduction of signal A or of signal B and vice versa.

TL;DR: Techniques from the qualitative theory of dynamical systems can be used to design and tune autonomous robot architectures and are demonstrated in two implementations.

TL;DR: The most prominent directions of research are overviewed, key terms are defined, and the approach to controlling group behavior and its relation to the field as a whole is described.

TL;DR: As a starting point to study experimentally the development of robots' ‘social relationships’, the investigation of collection and use of body images by means of imitation is proposed, suggesting that it might be a general principle in the evolution of intelligence.

TL;DR: It is argued that the methodology is more appropriate than symbolic simulation for the kinds of problems raised in the investigation of sensorimotor behaviour in animals and robots.

TL;DR: A biologically inspired definition of intelligent autonomous agents is explored, related to whether behavior of a system contributes to its self-maintenance, when it is capable to create and use representations.

TL;DR: A new neural architecture called PerAc witch is a systematic way to decompose the control of an autonomous robot in perception and action flows and can be used for landmark-based navigation on a mobile robot to learn without any a priori symbolic representation.

TL;DR: The implementation of a possible solution (artificial neural networks and genetic algorithms) on a real mobile robot through a set of three different experiments shows that the combination of genetic algorithms and neural networks is a very interesting technique for the development of control structures in autonomous agents.

TL;DR: This book is based on an extraordinarily successful NATO Advanced Study Institute at which leading proponents of the new behavior-oriented approach to artificial intelligence met to establish a solid scientific foundation for the field of intelligent autonomous agents.

TL;DR: This paper describes an approach to learning an indoor robot navigation task through trial-and-error using the explanation-based neural network learning algorithm EBNN, which allows the robot to learn control using dynamic programming.

TL;DR: This paper discusses issues related to the design of the control architectures for an autonomous mobile robot capable of performing tasks efficiently and intelligently, i.e. in a manner adapted to its environment, to its own state and to the execution status of its task.

TL;DR: In this article, a model of a six-legged walking machine is introduced considering biological principles and principles from nature are used both for the geometry of the model and the architecture of the controller.

TL;DR: It is found that controller performance was the most sensitive to robot design parameters, given the leg design of the robot and its limitations in controlling the retraction velocity of its legs.

TL;DR: A new approach to the integration and control of continuously operating visual processes which permits a system to integrate a large number of perceptual processes and to dynamically compose sequences of such processes to perform visual tasks, and illustrated with a system which detects and fixates on different classes of moving objects.

TL;DR: An implementation of the extended CQ-L framework using the HME-CMAC architecture is used to perform task decomposition in a realistic simulation of a two-linked manipulator having non-linear dynamics.

TL;DR: An architecture which deals with complex— high-dimensional and/or continuous—situation and action spaces effectively is described, based on two main ideas: to organize the reactive component into a set of modules in such a way that each one of them codifies the prototypical action for a given cluster of situations.

TL;DR: This paper presents an analysis of an artificially evolved dynamical network-based control system for a simulated autonomous mobile robot engaged in simple visually guided tasks.

TL;DR: This work proposes an architecture based on dynamic neural fields which enhances the system's capability to escape from closed-in situations, and endows the system with cognitive features, and demonstrates how representation alleviates the problem of spurious states in potential field approaches.

TL;DR: In multi-agent systems two forms of learning can be distinguished: centralized learning, that is, learning done by a single agent independent of the other agents; and distributed learning, which becomes possible only because several agents are present.

TL;DR: The predominant paradigm in cognitive science has been the cognitivistic one, exemplified by the “Physical Symbol Systems Hypothesis”, but this chapter addresses the problems of interacting with a real physical world.

TL;DR: The works of Boers and Kuiper, Gruau, Cangelosi et al., Vaario, Dellaert and Beer, and Sims are described, which all evolve the developmental program of an artificial nervous system and their possible contributions to the fundamental issue of assessing the adaptive values of development, learning and evolution are described.

TL;DR: A new control scheme is proposed based on the well-known computed torque method and a neural network based, compensating controller and the neural network is trained on line based on Lyapunov theory and thus its convergence is guaranteed.

TL;DR: The background to and some initial results of an attempt to develop the basis for quantitative performance measures of robot behaviour are presented and an example of the application of one of the techniques proposed is presented.

TL;DR: Extensive closed-loop experiments with the full-scale mobile robot MACROBE proved robustness, accuracy and real-time capability of this localization scheme.

TL;DR: All the steps needed for the description of the environment, including the range image acquisition and processing, 3D surface reconstruction and the problem of merging multiple images in order to obtain a complete model are presented.

TL;DR: Some properties of value-dependent learning will be demonstrated by comparing it to two simulated mechanisms for synaptic change derived from Hebbian principles, and differences in performance are explained in terms of differences in the mechanisms governing the potentiation and depression of synaptic strength.

TL;DR: An intelligent control architecture is presented which integrates learning methods and available domain knowledge based on Reinforcement Learning and allows continuous input and output parameters, hierarchical learning, multiple goals, self-organized topology of the used networks and online learning.

TL;DR: It is argued that the following three properties are foundations of robust robot navigation: use of landmarks, use of a compass sense, and the use of topological rather than geometrical maps.

TL;DR: This paper presents and formally examines an architecture that incorporates the benefits of a deliberative component without compromising the reactive component, and provides the first set of performance statistics in the literature for this class of system.

TL;DR: A breaking and insulating clamp for tensioned electrical conductors is disclosed, and which comprises an elongate bar of an electrical insulating material, with the bar mounting separate clamping members at longitudinally spaced apart locations for separately securing an electrical conductor or the like at each location.