Project Details

Abstract

An ideal bridge inventory database is a structured, accessible repository of comprehensive information about bridges, such as their condition, inspection history, load capacities, design types, age, and other relevant attributes. Such database is essential to support data-informed bridge asset management to enable systematic and cost-effective preservation of bridge infrastructure. However, current practices for retrieving information/insights from and updating the databases lack automation, are slow and extremely expert-demanding. This issue is further intensified given the increasing amount and the heterogeneous (multi-modal) nature of the data, as manually synthesizing and distilling useful insights from and/or updating the databases becomes increasingly challenging. As a result, there is a pressing need for smart analytics technologies to automate the management, extraction, and interpretation of bridge inventory data, enabling timely decision-making. While large language models (LLMs) have shown the capability of comprehending multi-modal data, they remain significantly underutilized in bridge management. This project will investigate the viability of using LLMs to build artificial intelligence (AI) agents that can extract, memorize bridge condition from inspection records/reports, and enable standardized interpretation and organization of insights to support bridge preservation decision-making. Specifically, the AI agents will convert raw and semi-structured bridge inventory data (e.g., inspection narratives, images, sensor signals) into structured database entries, concise summaries, and actionable recommendations. Users can interact intuitively with the AI agents via natural language queries, enabling efficient retrieval and interpretation of critical insights for bridge management. The agentic AI framework has the benefit of coordinating multiple tasks and achieving specified goals with minimal human/expert intervention. The project will offer force multipliers in information extraction, management, and utilization for bridge preservation.

Project Word Files