Recurrent Auto-Encoders for Enhanced Deep Reinforcement Learning in Wilderness Search and Rescue Planning

TL;DR

This paper introduces a novel combination of recurrent autoencoders and deep reinforcement learning to improve search efficiency in large wilderness rescue operations, outperforming existing methods in speed and accuracy.

Contribution

The study presents a new integrated architecture that enhances information throughput and control learning in complex, large-scale search tasks, with significant efficiency gains.

Findings

Proposed architecture outperforms benchmarks in search efficiency

Soft actor-critic achieves best performance among tested algorithms

Model trained faster with fewer parameters than previous approaches

Abstract

Wilderness search and rescue operations are often carried out over vast landscapes. The search efforts, however, must be undertaken in minimum time to maximize the chance of survival of the victim. Whilst the advent of cheap multicopters in recent years has changed the way search operations are handled, it has not solved the challenges of the massive areas at hand. The problem therefore is not one of complete coverage, but one of maximizing the information gathered in the limited time available. In this work we propose that a combination of a recurrent autoencoder and deep reinforcement learning is a more efficient solution to the search problem than previous pure deep reinforcement learning or optimisation approaches. The autoencoder training paradigm efficiently maximizes the information throughput of the encoder into its latent space representation which deep reinforcement learning is primed to leverage. Without the overhead of independently solving the problem that the recurrent autoencoder is designed for, it is more efficient in learning the control task. We further implement three additional architectures for a comprehensive comparison of the main proposed architecture. Similarly, we apply both soft actor-critic and proximal policy optimisation to provide an insight into the performance of both in a highly non-linear and complex application with a large observation Results show that the proposed architecture is vastly superior to the benchmarks, with soft actor-critic achieving the best performance. This model further outperformed work from the literature whilst having below a fifth of the total learnable parameters and training in a quarter of the time.