Simultaneous localization and mapping (SLAM) by using multiple cameras

• Main Author: He, Calvin Jia Jie
• Other Authors: Loke Yuan Ren
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering::Computer systems organization::Computer system implementation
• Online Access: https://hdl.handle.net/10356/148047
• Institution: Nanyang Technological University

As global warming is becoming more apparent, more natural disasters are occuring at an alarming rate, one of the most deadly disaster is earthquakes. As cities are laid to ruin, more rescuers are risking their lives than ever before. Different ideas have been introduced to help increase the safety and response, one of them is robots. Robots are mostly remote controlled and viewed through cameras, but the scene of robot SLAM has emerged recently and gaining traction among researchers. Cameras have been around for a very long time, but in the world of SLAM, they are not regarded as the best sensors to use. As technology improves, cameras these days are becoming more powerful and cheaper at the same time. In this paper, we will evaluate the readiness of only stereo cameras with different \out-of-the-box" SLAM algorithms to determine the viability of employing robots with SLAM that can safely search buildings and relay information to the user at the same time. We will be using the Jetson Nano B01 as the platform and two Raspberry Pi camera modules as the camera sensors, this allows us to evaluate a mobile, embedded GPU computer instead of an high-performance workstation.