Fusion of radar, LiDAR and thermal information for hazard detection in low visibility environments

Nowadays, mobile robots are widely used to support fire brigades in search and rescue missions. The utilization of those robots - especially under low visibility conditions due to smoke, fog or dust - is limited. Under these circumstances, environmental perception is still a huge challenge. In this work, we present an approach on using LiDAR, radar and thermal imaging in order to detect hazards that are potentially harmful to the robot or firefighters. We show the benefits of fusing LiDAR and radar before projecting temperatures recorded with a thermal imaging camera onto the range scans. Additionally, a hotspot detection method using the tempered range scans is presented. We demonstrate the functionality of our approach by teleoperating a robot through a smoky room.