Evolving Indoor Navigational Strategies Using Gated Recurrent Units In NEAT
This work addresses the need for efficient, evolved navigation policies for small robotic platforms like Micro-Aerial Vehicles, offering an incremental improvement over existing bug algorithms.
The authors tackled the problem of evolving control policies for indoor maze navigation in robots, showing that both NEAT and their NEAT-GRU extension outperform the I-Bug algorithm on 209 test environments, with NEAT-GRU achieving superior performance and handling a harder task without target bearing information.
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.