# Evolving Indoor Navigational Strategies Using Gated Recurrent Units In NEAT

## TL;DR

This paper investigates evolving control policies for indoor maze navigation using NEAT and NEAT with GRUs, demonstrating that NEAT-GRU outperforms other methods and can handle more complex tasks without bearing information.

## Contribution

The study extends NEAT with Gated Recurrent Units to improve maze navigation control policies and shows its superiority over traditional NEAT and I-Bug algorithms.

## Key findings

- NEAT-GRU outperforms NEAT and I-Bug in maze navigation tasks.
- NEAT-GRU can evolve controllers for tasks without bearing information.
- Both NEAT and NEAT-GRU reliably generate effective navigation controllers.

## Abstract

Simultaneous Localisation and Mapping (SLAM) algorithms are expensive to run on smaller robotic platforms such as Micro-Aerial Vehicles. Bug algorithms are an alternative that use relatively little processing power, and avoid high memory consumption by not building an explicit map of the environment. Bug Algorithms achieve relatively good performance in simulated and robotic maze solving domains. However, because they are hand-designed, a natural question is whether they are globally optimal control policies. In this work we explore the performance of Neuroevolution - specifically NEAT - at evolving control policies for simulated differential drive robots carrying out generalised maze navigation. We extend NEAT to include Gated Recurrent Units (GRUs) to help deal with long term dependencies. We show that both NEAT and our NEAT-GRU can repeatably generate controllers that outperform I-Bug (an algorithm particularly well-suited for use in real robots) on a test set of 209 indoor maze like environments. We show that NEAT-GRU is superior to NEAT in this task but also that out of the 2 systems, only NEAT-GRU can continuously evolve successful controllers for a much harder task in which no bearing information about the target is provided to the agent.