Environment classification using Kohonen self‐organizing maps

  title={Environment classification using Kohonen self‐organizing maps},
  author={Kevin Burn and Geoffrey Home},
  journal={Expert Systems},
Abstract: This paper describes a new method for classifying three‐dimensional environments in real time using Kohonen self‐organizing maps (SOMs). The method has been developed to enable autonomous underwater vehicles (AUVs) to navigate without human intervention in previously unexplored subsea environments, but can be generalized to unmanned aircraft equipped with appropriate sensors flying over unchartered terrains, or spacecraft exploring remote planets, subject to appropriate pre‐mission… 

AI tools for use in assembly automation and some examples of recent applications

Seven artificial intelligence tools that are useful in assembly automation are reviewed: knowledge‐based systems, fuzzy logic, automatic knowledge acquisition, neural networks, genetic algorithms, case‐based reasoning and ambient‐intelligence.

Analysis of Wetland Landcover Change in Great Lakes Urban Areas Using Self-Organizing Maps

Changing landcover and the flood mitigation attributes of wetland areas over a 15-year period in Toronto and Chicago are explored with landcover change data, digital elevation models (DEM), and self-organizing maps (SOM).

Ambient-intelligence, rapid-prototyping and where real people might fit into factories of the future

Although the introduction of ambient-intelligence into assembly and manufacturing is slow, it promises to bring improvements in flexibility, reconfigurability and reliability.

Towards a framework for multiple artificial neural network topologies validation by means of statistics

An integral framework is proposed for the optimization of different ANN classifiers based on statistical hypothesis testing and results show the relevance of this framework, proving that its application improves the performance and efficiency of multiple classifiers.

Heuristic particle filter: applying abstraction techniques to the design of visual tracking algorithms

A general framework to hybridize heuristics/metaheuristics with particle filters properly and to devise effective hybrid visual tracking algorithms naturally, guided by the use of abstraction techniques is proposed.

Benchmarking environmental efficiency of ports using data mining and RDEA: the case of a U.S. container ports

It can be inferred that the step-wise benchmarking process using two combined methodologies substantiates that a more applicable benchmarking target set of decision-making units is be projected, which consider the similarity of the physical and operational characteristics of homogenous ports for improving environmental efficiency.

Progress in machine intelligence

In the coming decades, humanity may create a powerful artificial intelligence but that said, back in 1999 I suggested in this journal that machine intelligence was just around the corner (Sanders,

Introducing AI into MEMS can lead us to brain-computer interfaces and super-human intelligence

I addressed new applications and technologies such as merging machines with human beings, micro-electromechanics, electro-mechanical systems that can be personalized, smarter than human intelligence and swarms of smart sensors.



A self-organizing map based navigation system for an underwater robot

  • K. IshiiS. NishidaT. Ura
  • Computer Science
    IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004
  • 2004
A supervised learning algorithm is introduced into SOM and a method to adapt the local map to its environment by learning and evaluating the trajectory of robot is proposed, which enables the map to have both the effect of dynamics of robot and environmental information.

Data mining using rule extraction from Kohonen self-organising maps

This paper presents a technique which can be used to extract propositional IF..THEN type rules from the SOM network’s internal parameters and can provide a human understandable description of the discovered clusters.

Learning systems in intelligent control: an appraisal of fuzzy, neural and genetic algorithm control applications

Parts of fuzzy logic, neural networks and genetic algorithms that pertain to realisation of intelligent control systems are reviewed, providing a compact reference for their application.

On AUV control architecture

  • P. RidaoJ. YuhJ. BatlleK. Sugihara
  • Computer Science
    Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113)
  • 2000
A control architecture that is being developed for a semi-autonomous underwater vehicle for intervention missions (SAUVIM) at the University of Hawaii is described, being able to show a predictable response while keeping rapid reactivity to the dynamic environment.

Artificial Intelligence: A Guide to Intelligent Systems

The book demonstrates that most ideas behind intelligent systems are simple and straightforward, and the reader needs no prerequisites associated with knowledge of any programming language.

Adaptive and Nonlinear Fuzzy Force Control Techniques Applied to Robots Operating in Uncertain Environments

Using simulation and an experimental robot, the design of two nonlinear, fuzzy force controllers are described, developed primarily using analytical methods, which overcome the problems of conventional control.

Development of a non-linear force controller using fuzzy logic techniques

The design of a fuzzy logic controller to replace a conventional controller in a force control loop is described, which combines an analytical approach to controller tuning, with the intuitive properties and self-adjusting gain characteristics associated with fuzzy logic systems.

Introduction to AI Robotics

From the Publisher: This text covers all the material needed to understand the principles behind the AI approach to robotics and to program an artificially intelligent robot for applications

Control architectures for autonomous underwater vehicles

The four types of control architectures being used for AUVs (hierarchical, heterarchicals, subsumption, and hybrid architecture) are reviewed and a new sensor-based embedded AUV control system architecture is described and its implementation is discussed.