Geotab Ace: Enhancing Fleet Intelligence with Retrieval-Augmented Generative AI for Natural Language Data Interaction

Geotab is a global leader in IoT and connected transportation, providing data-driven insights for fleet management. Collecting over 4 billion data points daily from 4.5 million connected vehicles, Geotab’s AI Platform team focuses on leveraging machine learning to enhance data accessibility, fleet intelligence, and operational efficiency. A key challenge is improving user interaction with complex datasets, as traditional methods require manual report analysis and complex query navigation. To address this, Geotab is developing Geotab Ace, an AI assistant integrating Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to enable intuitive, natural language-based data access. This project aims to enhance query accuracy, data retrieval efficiency, and user experience. The anticipated benefits include improved customer decision-making, reduced support overhead, and optimized fleet operations. Additionally, AI-driven fleet intelligence contributes to safer, more efficient transportation, reducing costs and emissions through predictive maintenance and route optimization. The project also advances practical AI applications in telematics, pushing the boundaries of LLM-based conversational AI in real-world, data-intensive environments. By making data-driven decision-making more accessible, this research benefits both Geotab and the broader industry, driving AI innovation in fleet management and IoT analytics.

Faculty Supervisor:

Scott Sanner

Student:

Partner:

Geotab Inc

Discipline:

Computer science

Sector:

Information and cultural industries; Professional, scientific and technical services; Transportation and warehousing

University:

University of Toronto

Program: