Evolutionary learning of a robot controller: effect of neural network topology (original) (raw)

2001

Abstract

In our research we evolve robot controllers for executing elementary behaviours. This paper focuses on the behaviour of pushing a box between two walls. Successful execution of this behaviour is critically dependent on the robot's ability to distinguish between the walls and the box. Using evolutionary algorithms, we optimised the box-pushing performances of two types of networks: feedforward networks and

Eric Postma hasn't uploaded this paper.

Let Eric know you want this paper to be uploaded.

Ask for this paper to be uploaded.