Detour Behaviour in Evolving Robots: Are Internal Representations Necessary?
نویسندگان
چکیده
Internal representations of the environment are often invoked to explain performance in tasks in which an organism must make a detour around an obstacle to reach a target and the organism can lose sight of the target along the path to the target. By simulating a detour task in evolving populations of robots (Khepera) we show that neural networks with memory units perform better than networks without memory units in this task. However, the content of the memory units need not be interpreted as an internal representation of the position of target. The memory units send a time-varying internally generated input to the network’s hidden units that allows the network to generate the appropriate behavior even when there is no external input. Networks without memory units do not have this internal input and this explains their inferior
منابع مشابه
Replicating Experiments in "Detour Behavior" with Artifically Evolved Robots: An A-Life Approach to Comparative Psychology
To be useful in psychology "artificial organisms" have to perform tasks comparable to those performed by animals. One way to achieve this is to replicate actual animal experiments. Here we reproduce an experiment showing "detour behavior" in chicks a behavior usually explained in terms of "cognitive maps" or other forms of internal representation. We artificially evolve software-simulated robot...
متن کاملOn the Coupling Between Agent Internal and Agent/ Environmental Dynamics: Development of Spatial Representations in Evolving Autonomous Robots
In this paper we describe how a population of evolving robots can autonomously develop forms of spatial representation which allow them to self-localize and to discriminate different locations of their environment by integrating sensory-motor information over time. Evolving robots also display a remarkable ability to generalize their skill in new environmental conditions never experienced befor...
متن کاملEvolving Neuro - Modules and their Interfacesto Control
An evolutionary algorithm for the creation of recurrent network structures is presented. The aim is to develop neural networks controlling the behaviour of miniature robots. Two neuro-modules are created separately using this evolutionary approach. The rst neuro-module gives the agents the ability to move within an environment without colliding with obstacles. The second neuro-module provides t...
متن کاملDetour Monophonic Graphoidal Covering Number of Corona Product Graph of Some Standard Graphs with the Wheel
A chord of a path $P$ is an edge joining two non-adjacent vertices of $P$. A path $P$ is called a monophonic path if it is a chordless path. A longest $x-y$ monophonic path is called an $x-y$ detour monophonic path. A detour monophonic graphoidal cover of a graph $G$ is a collection $psi_{dm}$ of detour monophonic paths in $G$ such that every vertex of $G$ is an internal vertex of at most on...
متن کاملF Ur Mathematik in Den Naturwissenschaften Leipzig Evolving Neural Behaviour Control for Autonomous Robots Evolving Neural Behaviour Control for Autonomous Robots
An evolutionary algorithm for the creation of recurrent network structures is presented. The aim is to develop neural networks controlling the behaviour of miniature robots. Two diierent tasks are solved with this approach. For the rst, the agents are required to move within an environment without colliding with obstacles. In the second task, the agents are required to move towards a light sour...
متن کامل