An Evolutionary Artificial Nervous System for Animat Locomotion
نویسنده
چکیده
This paper describes the results of current research into an artificial nervous system for animats, a class of robots based on animals. The system is based on a hierarchical model and has been implemented using evolutionary artificial neural networks. A new neuron model has been developed for use in the system. The artificial neural networks are combined in a flexible manner to create central pattern generators which control the gait of the animat during locomotion. Bipedal walking gaits have successfully been created using this model.
منابع مشابه
Using evolutionary artificial neural networks to design hierarchical animat nervous systems
متن کامل
Bio-inspired Cognitive Architecture for Adaptive Agents based on an Evolutionary Approach
In this work, an hybrid, self-configurable, multilayered and evolutionary subsumption architecture for cognitive agents is developed. Each layer of the multilayered architecture is modeled by one different Reinforcement Machine Learning System (RMLS) based on bio-inspired techniques. In this research an evolutionary mechanism based on Gene Expression Programming to self-configure the behaviour ...
متن کاملSwimming Animats with Musculoskeltal Structure
Animats are artificial creature studied in Alife. Musculo-skeltal structure is a skeleton control model usually used for humanoids. We apply the musculo-skeltal structure to simple swimming animats. The purpose of this study is to acquire proper locomotion of animats in a virtual water environment. The locomotion control is acquired by use of neuro-evolution. The evolved locomotion, swimming, i...
متن کاملThe Evolution of Reaction-Diffusion Controllers for Minimally Cognitive Agents
This article describes work carried out to investigate whether a classic reaction-diffusion (RD) system could be used to control a minimally cognitive animat. The RD system chosen was that first described by Gray and Scott, and the minimally cognitive behaviors were those used by Beer et al. involving the fixation and discrimination of diamond and circle shapes by a whiskered animat. A further ...
متن کاملMultilayered Evolutionary Architecture for Behaviour Arbitration in Cognitive Agents
In this work, an hybrid, self-configurable, multilayered and evolutionary subsumption architecture for cognitive agents is developed. Each layer of the multilayered architecture is modeled by one different Machine Learning System (MLS) based on bio-inspired techniques such as Extended Classifier Systems (XCS), Artificial Immune Systems (AIS), Neuro Connectionist Q-Learning (NQL) and Learning Cl...
متن کامل