RAPID: Mobile Augmented Reality to Improve Rapid Assessments in Disasters

Carnegie Mellon University, Pittsburgh PA

Investigators

Abstract

Following an earthquake, or similar natural disaster, a key problem is rapid and accurate on-site damage assessment to support local first responders; however, trained experts are typically remote from the disaster and it can be time consuming and expensive to bring them onsite. Accessing remote experts to improve the accuracy of rapid assessments is a promising method to streamline provisioning of emergency shelters and other resources. This project focuses on new methods for improved rapid assessment of earthquake damaged building structures in Christchurch, New Zealand. The methods are based on collaboration using augmented-reality (AR) imagery, mobile phone based sensor technologies and crowdsourcing techniques for guided remote data collection. A key element of the system is intuitive remote collaboration. Our mobile AR system can be used to connect a user in the disaster zone to a remote expert via audio and shared still images and/or video, helping them to rapidly collect data on building structural integrity. A user evaluation will be performed to compare the performance between the prototype and more traditional approaches (e.g., waiting for an expert to arrive on the ground), and assessment based on imagery recorded from an untrained and unguided user. Two hypotheses will be tested: 1) a collaborative mobile AR system can improve the quality and type of data collected for structural assessment 2) the time to provide data from non-experts assisted by experts to decision makers in a digestible format is dramatically reduced as compared to traditional methods. The approach will enable rapid post-event damage assessment, streamline emergency provisioning of shelters by allowing people to stay in safe dwellings, and speed up emergency response and reconstruction. The resulting valuable dataset will assist development of rapid assessment forms, contribute to earthquake structural damage case studies, provide key baseline to test several computer science research projects on improved disaster response, and provide key data for development of life-saving tools. The international collaboration also provides engagement of underrepresented groups in this computing research.