A Multi-model Approach for Video Data Retrieval in Autonomous Vehicle Development
This program is tentative and subject to change.
Autonomous driving softwares generates enormous amounts of data every second, which software development organizations save for future analysis and testing as logs. However, given the vast size of this data, locating specific scenarios within a collection of vehicle logs can be challenging. Writing the correct SQL queries to find these scenarios requires engineers to have a strong background in signal processing and databases, further complicating the search process. This paper presents and evaluates a pipeline that allows searching for specific scenarios in log collections using natural language descriptions instead of SQL. The generated descriptions were evaluated by engineers working with vehicle logs at the collaborating company on a scale of 1 to 5. Our approach achieved a mean score of 3.3, demonstrating the potential of using a multi-model architecture to improve the software development workflow. We also present an interface that can visualize the query process and visualize the results.
This program is tentative and subject to change.
Tue 3 DecDisplayed time zone: Athens change
16:00 - 17:30 | PROFES Session 5: AI for Software Engineering in Practice (I)Industry Papers / Short Papers and Posters / Research Papers at UT Library - Room 2 | ||
16:00 18mIndustry talk | A Multi-model Approach for Video Data Retrieval in Autonomous Vehicle Development Industry Papers Jesper Knapp Chalmers | University of Gothenburg, Klas Moberg Chalmers | University of Gothenburg, Yuchuan Jin Zenseact, Simin Sun Chalmers | University of Gothenburg, Miroslaw Staron University of Gothenburg | ||
16:18 12mShort-paper | Enhancing Transparency in Space Metrics Use: Insights from an Initial Study Short Papers and Posters Kseniia Vasylieva Reutlingen University, Thomas Brenner OHB System AG, Marco Kuhrmann Reutlingen University, Jürgen Münch Reutlingen University | ||
16:30 18mResearch paper | Supporting the Development of Oracle APEX Low-Code Applications With Large Language Models Research Papers | ||
16:48 18mIndustry talk | AI-based Automotive Test Case Generation: An Action Research Study on Integration of Generative AI into Test Automation Frameworks Industry Papers Albin Karlsson Chalmers | University of Gothenburg, Erik Lindmaa Chalmers | University of Gothenburg, Simin Sun Chalmers | University of Gothenburg, Miroslaw Staron University of Gothenburg | ||
17:06 24mTalk | Session 5 Discussion Research Papers |