WorldCat Identities

Husbands, Phil

Overview
Works: 25 works in 73 publications in 1 language and 2,240 library holdings
Genres: History  Conference proceedings 
Roles: Editor
Classifications: Q335, 006.309
Publication Timeline
Key
Publications about  Phil Husbands Publications about Phil Husbands
Publications by  Phil Husbands Publications by Phil Husbands
Most widely held works by Phil Husbands
The mechanical mind in history ( )
14 editions published in 2008 in English and held by 1,536 WorldCat member libraries worldwide
The idea of intelligent machines has become part of popular culture. Tracing the history of the actual science of machine intelligence reveals a rich network of cross-disciplinary contributions, and the origins of ideas now central to artifical intelligence, artificial life, cognitive science and neuroscience
Evolutionary robotics : First European Workshop, EvoRobot'98 : Paris, France, April 16-17, 1998 : proceedings by Phil Husbands ( Book )
20 editions published in 1998 in English and Undetermined and held by 336 WorldCat member libraries worldwide
This book constitutes the thorougly refereed and revised post-workshop proceedings of the First European Workshop on Evolutionary Robotics, EvoRobot '98, held in Paris, France in April 1998. The 15 revised full papers presented outline the state of the art in this new interdisciplinary area of research and development. The introductory paper gives a survey of the use of evolutionary computing techniques for the automatic design of adaptive robots
Fourth European Conference on Artificial Life by European Conference on Artificial Life ( Book )
8 editions published in 1997 in English and held by 143 WorldCat member libraries worldwide
The horizons of evolutionary robotics ( Book )
3 editions published in 2014 in English and held by 131 WorldCat member libraries worldwide
Evolutionary robotics (ER) aims to apply evolutionary computation techniques to thedesign of both real and simulated autonomous robots. This book soffers an authoritative overview of this rapidly developing field, presentingstate-of-the-art research by leading scholars. The result is a lively, expansive survey that will be of interest to computer scientists, robotics engineers, neuroscientists, and philosophers. The contributors discuss incorporating principles from neuroscience into ER; dynamical analysis ofevolved agents; constructing appropriate evolutionary pathways; spatial cognition; the coevolutionof robot brains and bodies; group behavior; the evolution of communication; translating evolvedbehavior into design principles; the development of an evolutionary robotics based methodology forshedding light on neural processes; an incremental approach to complex tasks; and the notion of mindless intelligence, complex processes from immune systems to social networks -- as a way forward for artificial intelligence
Genetic convergence in a species of evolved robot control architectures by Inman Harvey ( Book )
1 edition published in 1993 in English and held by 8 WorldCat member libraries worldwide
Incremental evolution of neural network architectures for adaptive behaviour by David Cliff ( Book )
1 edition published in 1992 in English and held by 7 WorldCat member libraries worldwide
Abstract: "This paper describes aspects of our ongoing work in evolving recurrent dynamical artificial neural networks which act as sensory-motor controllers, generating adaptive behaviour in artificial agents. We start with a discussion of the rationale for our approach. Our approach involves the use of recurrent networks of artificial neurons with rich dynamics, resilience to noise (both internal and external); and separate excitation and inhibition channels. The networks allow artificial agents (simulated or robotic) to exhibit adaptive behaviour. The complexity of designing networks built from such units leads us to use our own extended form of genetic algorithm, which allows for incremental automatic evolution of controller-networks. Finally, we review some of our recent results, applying our methods to work with simple visually-guided robots. The genetic algorithm generates useful network architectures from an initial set of randomly-connected networks. During evolution, uniform noise was added to the activation of each neuron. After evolution, we studied two evolved networks, to see how their performance varied when the noise range was altered. Significantly, we discovered that when the noise was eliminated, the performance of the networks degraded: the networks use noise to operate efficiently."
A comparison of optimization techniques for integrated manufacturing planning and scheduling by M McIlhagga ( Book )
2 editions published in 1996 in Undetermined and English and held by 7 WorldCat member libraries worldwide
Abstract: "We describe a comparison betwen Simulated Annealing (SA), Dispatch Rules (DR), and a Coevolutionary Distributed Genetic Algorithm (DGA) solving a random sample of integrated planning and scheduling (IPS) problems. We found that for a wide range of optimization criteria the DGA consistently outperformed SA and DR. The DGA finds 8-9 unique high quality solutions per run, whereas the other techniques find one. On average, each DGA solution is 10-15% better than SA solutions and 30-35% better than DR solutions."
Analysis of evolved sensory-motor controllers by Dave Cliff ( Book )
1 edition published in 1992 in English and held by 7 WorldCat member libraries worldwide
Unconstrained evolution and hard consequences by Adrian Thompson ( Book )
3 editions published in 1995 in English and held by 7 WorldCat member libraries worldwide
Abstract: "Artificial evolution as a design methodology for hardware frees many of the simplifying constraints normally imposed to make design by humans tractable. However, this freedom comes at some cost, and a whole fresh set of issues must be considered. Standard genetic algorithms are not generally appropriate for hardware evolution when the number of components need not be predetermined. The use of simulations is problematic, and robustness in the presence of noise or hardware faults is important. We present theoretical arguments, and illustrate with a physical piece of hardware evolved in the real-world ('intrinsically evolved' hardware). A simple asynchronous digital circuit controls a real robot, using a minimal sensorimotor control system of 32 bits of RAM and a few flip-flops to co-ordinate sonar pulses and motor pulses with no further processing. This circuit is tolerant to single-stuck-at-faults in the RAM. The methodology is applicable to many types of hardware, including Field-Programmable Gate Arrays (FPGA's)."
Evolving visually guided robots by David Cliff ( Book )
1 edition published in 1992 in English and held by 6 WorldCat member libraries worldwide
Abstract: "We have developed a methodology grounded in two beliefs: that autonomous agents need visual processing capabilities, and that the approach of hand-designing control architectures for autonomous agents is likely to be superseded by methods involving the artificial evolution of comparable architectures. In this paper we present results which demonstrate that neural-network control architectures can be evolved for an accurate simulation model of a visually guided robot. The simulation system involves detailed models of the physics of a real robot built at Sussex; and the simulated vision involves ray-tracing computer graphics, using models of optical systems which could readily be constructed from discrete components. The control-network architecture is entirely under genetic control, as are parameters governing the optical system. Significantly, we demonstrate that robust visually-guided control systems evolve from evaluation functions which do not explicitly involve monitoring visual input. The latter part of the paper discusses work now under development, which allows us to engage in long-term fundamental experiments aimed at thoroughly exploring the possibilities of concurrently evolving control networks and visual sensors for navigational tasks. This involves the construction of specialised visual-robotic equipment which eliminates the need for simulated sensing."
Evolutionary robotics : First European Workshop, EvoRobot'98 : Paris, France, April 1998 by EvoRobot'98 ( Book )
2 editions published in 1998 in English and held by 6 WorldCat member libraries worldwide
An ecosystems model for integrated production planning by Phil Husbands ( Book )
1 edition published in 1992 in English and held by 6 WorldCat member libraries worldwide
Abstract: "This paper re-evaluates the job-shop scheduling problem by showing how the standard definition is far more restrictive than necessary and by presenting a new technique capable of tackling a highly generalised version of the problem. This technique is based on a massively parallel distributed genetic algorithm and is capable of simultaneously optimising the process plans of a number of different components, at the same time a near-optimal schedule emerges. Underlying the evolutionary machinery is a specialised feature-based generative process planner."
Issues in evolutionary robotics by Inman Harvey ( Book )
2 editions published in 1992 in English and held by 6 WorldCat member libraries worldwide
Abstract: "In this paper we propose and justify a methodology for the development of the control systems, or 'cognitive architectures', of autonomous mobile robots. We argue that the design by hand of such control systems becomes prohibitively difficult as complexity increases. We discuss an alternative approach, involving artificial evolution, where the basic building blocks for cognitive architectures are adaptive noise- tolerant dynamical neural networks, rather than programs. These networks may be recurrent, and should operate in real time. Evolution should be incremental, using an extended and modified version of genetic algorithms. We finally propose that, sooner rather than later, visual processing will be required in order for robots to engage in non-trivial navigation behaviours. Time constraints suggest that initial architecture evaluations should be largely done in simulation. The pitfalls of simulations compared with reality are discussed, together with the importance of incorporating noise. To support our claims and proposals, we present results from some preliminary experiments where robots which roam office- like environments are evolved."
The application of a distributed genetic algorithm to a generic scheduling system by M McIlhagga ( Book )
1 edition published in 1997 in English and held by 6 WorldCat member libraries worldwide
General visual robot controller networks via artificial evolution by Dave Cliff ( Book )
1 edition published in 1994 in English and held by 6 WorldCat member libraries worldwide
From animals to animats 3 proceedings of the Third International Conference on Simulation of Adaptive Behavior by International Conference on Simulation of Adaptive Behavior ( Book )
1 edition published in 1994 in English and held by 5 WorldCat member libraries worldwide
Survival of the sickest : a site-specific recombination operator for accelerated function optimization by Stephen Drake ( Book )
1 edition published in 2001 in English and held by 3 WorldCat member libraries worldwide
An integrated approach to process planning and scheduling using genetic algorithms by Phil Husbands ( )
3 editions published between 1993 and 1995 in English and held by 3 WorldCat member libraries worldwide
This thesis presents a new integrated approach to process planning aad job-shop scheduling. The relationship between planning and scheduling is reassessed and the line between the two tasks is made significantly more blurred than in the usual treatment. Scheduling is traditionally seen as the task of finding an optimal way of interleaving a number of fixed plans which are to be executed concurrently and which must share resources. The implicit assumption is that once planning has finished scheduling takes over. In fact there are often many possible choices for the sub-operations in the plans. Very often the real optimisation problem is to simultaaeously optimise all the individual plans alzd the overall schedule. This thesis describes how manufa.cturing planning has been recast to allow solutions to the simultaneous plan and schedule optimisation problem, a problem traditionally considered too hard to tackle at all. A model based on simulated coevolution is developed and it is shown how complex interactions are handled in an emergent way. Results from various implementations are reported. Underlying this new approach is a feature based process planning system that is used to generate the space of all possible legal process plans for a given component. This space is then searched, in parallel with spaces for all other components, using an advanced form of genetic algorithm. The thesis describes the development of the ideas behind this technique and presents in detail the constituent parts of the whole system
Better living through chemistry : Evolving GasNets for robotic control by Phil Husbands ( Book )
1 edition published in 1998 in English and held by 2 WorldCat member libraries worldwide
Characterising fitness landscapes through evolvability by Charles Forster Smith ( Book )
1 edition published in 2001 in English and held by 2 WorldCat member libraries worldwide
 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  Kids General Special  
Audience level: 0.58 (from 0.00 for Better liv ... to 0.88 for Fourth Eur ...)
Alternative Names
Husbands Phil
Husbands, Philip
Languages
English (66)
Covers