Location Recognition in a Mobile Robot Using Self-organising Feature Maps 1
نویسندگان
چکیده
Self-organising structures are a dominant feature of the experimental mobile robots built in our \Really Useful Robots" project. This paper continues where Nehmzow & Smithers 90] nished. It explains some initial experiments using self-organising feature maps, and how those maps can be used by a mobile robot to recognise locations in its environment. This location recognition capability is achieved without using sensory information. Instead information derived from the motor actions of the robot is used, and shown to be suucient.
منابع مشابه
Steel Consumption Forecasting Using Nonlinear Pattern Recognition Model Based on Self-Organizing Maps
Steel consumption is a critical factor affecting pricing decisions and a key element to achieve sustainable industrial development. Forecasting future trends of steel consumption based on analysis of nonlinear patterns using artificial intelligence (AI) techniques is the main purpose of this paper. Because there are several features affecting target variable which make the analysis of relations...
متن کاملA framework for using self-organising maps to analyse spatio-temporal patterns, exemplified by analysis of mobile phone usage
A framework for using self-organising maps to analyse spatio-temporal patterns, exemplified by analysis of mobile phone usage Gennady Andrienkoa; Natalia Andrienkoa; Peter Bakb; Sebastian Bremmc; Daniel Keimb; Tatiana von Landesbergercd; Christian Pölitza; Tobias Schreckc a University of Bonn and Fraunhofer IAIS, Sankt Augustin 53754, Germany b University of Konstanz, Konstanz, Germany c Techni...
متن کاملDigital Realisation of Self-Organizing Maps
Kevin J. Moon A digital realisation of two-dimensional self-organising feature maps is presented. The method is based on subspace classification using an n-tuple technique. Weight vector approximation and orthogonal projections to produce a winnertakes-all network are also discussed. Over one million effective binary weights can be applied in 25ms using a conventional microcomputer. Details of ...
متن کاملDynamic Modeling and Construction of a New Two-Wheeled Mobile Manipulator: Self-balancing and Climbing
Designing the self-balancing two-wheeled mobile robots and reducing undesired vibrations are of great importance. For this purpose, the majority of researches are focused on application of relatively complex control approaches without improving the robot structure. Therefore, in this paper we introduce a new two-wheeled mobile robot which, despite its relative simple structure, fulfills the req...
متن کاملUsing Motor Actions for Location Recognition
We present a Behaviour-based mobile robot that is able to autonomously build internal representations of its environment and use these for location recognition. This is done by a process of self-organisation, no explicit world-model is given. The robot uses an artiicial neural network for mapbuilding and additional adaptive processes to achieve successful location recognition. The robot reliabl...
متن کامل