用自然语言搜索自动驾驶日志，提升工程师检索效率。
A Multi-model Approach for Video Data Retrieval in Autonomous Vehicle Development
- 构建多模型管道，将自然语言转为日志查询。
- 工程师评分均值3.3，证明方法有效。
- 适合需要快速定位场景的自动驾驶开发人员。
自动驾驶软件每秒生成海量数据，开发团队以日志形式保存用于后续分析与测试。然而，面对如此庞大的数据量，从车辆日志中定位特定场景极具挑战性。编写精确的SQL查询需工程师具备扎实的SQL知识及对特定数据库的了解，进一步增加了难度。本文提出并评估了一种新流程，使工程师可通过自然语言描述在日志集合中搜索特定场景，无需编写SQL。该方法在Zenseact的工程师中进行评估，评分范围为1至5，平均得分为3.3，显示出多模型架构在改善软件开发流程方面的潜力。此外，我们还设计了一个可视化界面，支持查询过程与结果的直观展示。
原文摘要 · Abstract (English)
Autonomous driving software generates enormous amounts of data every second, which software development organizations save for future analysis and testing in the form of 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 SQL and the specific databases in question, 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 Zenseact on a scale from 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。