Reinforcement Learning Based Escape Route Generation in Low Visibility Environments

TL;DR

This paper presents a reinforcement learning approach to generate safe escape routes in low visibility environments during fires, utilizing environmental sensing and mapping techniques for real-time decision making.

Contribution

It introduces a novel RL-based system that processes environmental data to determine optimal evacuation paths in low visibility fire scenarios.

Findings

RL method outperforms complex competitors in robustness and speed

System effectively merges LiDAR and sensor data for environment mapping

Proposed approach enhances real-time evacuation planning in low visibility conditions

Abstract

Structure fires are responsible for the majority of fire-related deaths nationwide. In order to assist with the rapid evacuation of trapped people, this paper proposes the use of a system that determines optimal search paths for firefighters and exit paths for civilians in real time based on environmental measurements. Through the use of a LiDAR mapping system evaluated and verified by a trust range derived from sonar and smoke concentration data, a proposed solution to low visibility mapping is tested. These independent point clouds are then used to create distinct maps, which are merged through the use of a RANSAC based alignment methodology and simplified into a visibility graph. Temperature and humidity data are then used to label each node with a danger score, creating an environment tensor. After demonstrating how a Linear Function Approximation based Natural Policy Gradient RL methodology outperforms more complex competitors with respect to robustness and speed, this paper outlines two systems (savior and refugee) that process the environment tensor to create safe rescue and escape routes, respectively.