On the Generalization Capability of Evolved Counter-propagation Neuro-controllers for Robot Navigation

04/25/2020
by   Amiram Moshaiov, et al.
0

Evolving Counter-Propagation Neuro-Controllers (CPNCs), rather than the traditional Feed-Forward Neuro-Controllers (FFNCs), has recently been suggested and tested using simulated robot navigation. It has been demon-strated that both convergence rate and final performance obtained by evolving CPNCs are superior to those obtained by evolving FFNCs. In this paper the maze generalization features of both types of evolved navigation controllers are examined. For this purpose the controllers are tested in an environment that drastically differs from the one used for their training. Moreover, a comparison is carried out of results obtained by single-objective and multi-objective evolution approaches. Using a simulated case-study, the maze generalization capability of the evolved CPNCs is highlighted in both the single and multi-objective cases. In contrast, the evolved FFNCs are found to lack such capabilities in both approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/26/2023

Evolving Multi-Objective Neural Network Controllers for Robot Swarms

Many swarm robotics tasks consist of multiple conflicting objectives. Th...
research
05/26/2019

A Staged Approach to Evolving Real-world UAV Controllers

A testbed has recently been introduced that evolves controllers for arbi...
research
02/14/2019

Multi-Objective Policy Generation for Multi-Robot Systems Using Riemannian Motion Policies

In the multi-robot systems literature, control policies are typically ob...
research
04/07/2021

Co-optimising Robot Morphology and Controller in a Simulated Open-Ended Environment

Designing robots by hand can be costly and time consuming, especially if...
research
02/25/2021

Neuroevolution of a Recurrent Neural Network for Spatial and Working Memory in a Simulated Robotic Environment

Animals ranging from rats to humans can demonstrate cognitive map capabi...
research
04/15/2013

Multiobjective optimization in Gene Expression Programming for Dew Point

The processes occurring in climatic change evolution and their variation...
research
08/17/2021

Monolithic vs. hybrid controller for multi-objective Sim-to-Real learning

Simulation to real (Sim-to-Real) is an attractive approach to construct ...

Please sign up or login with your details

Forgot password? Click here to reset