Autonomous urban search robot

• Main Authors: Chan, Robert Keith C., Dacumos, Christian D., Estera, Erika Sheane T., Siy, Joshua Samuel P., Uy, Domingo S., Jr.
• Format: text
• Language: English
• Published: Animo Repository 2017
• Subjects: Rescue work > Automation
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/9936
• Institution: De La Salle University

The project describes the approach of the researchers in designing and fabricating a wirelessly controlled mobile robotic platform capable of navigating an unknown environment, creating a 3D reconstruction of said environment, all while detecting any human face it encounters. This purpose of this project is to assist rescue team in disaster scenarios by providing a computer-generated model of the environment, allowing rescue teams to analyze and learn the general layout of the area without immediately exposing themselves to the risks of traversing unknown environments, as well as identifying the presence of detected humans within the area, allowing the team to plan efficient searching routes that prioritize sections shown to potentially contain a survivor. This was done by using a mobile platform capable of traversing the area and avoid obstacles through either manual control or autonomous navigation, mounting an RGB-D camera to generate a graphical representation of the traversed area on the mobile platform, and running a face detection algorithm that uses a webcam to alert the viewer of any detected faces by playing an audial cue as well as output the recorded video of the platform's operations for review and analysis. Upon examination of the results, it was found that the fabricated platform is indeed, capable of exploring an unknown area, developing a close approximation of the area using a 3D map, detecting faces scattered throughout the area, all while performing wirelessly, separate from the viewing terminal. This research shows the potential that robots possess in assisting rescue operations.