DriveSceneGen: Generating Diverse and Realistic Driving Scenarios from Scratch

TL;DR

DriveSceneGen is a novel data-driven method that generates diverse, realistic driving scenarios from scratch, aiding autonomous vehicle development by overcoming data limitations.

Contribution

It introduces the first approach to generate complete driving scenarios with static and dynamic elements from scratch, learned from real-world data.

Findings

Generated scenarios match real-world data distribution

High diversity and fidelity in generated scenarios

Scalable generation of 5,000 scenarios

Abstract

Realistic and diverse traffic scenarios in large quantities are crucial for the development and validation of autonomous driving systems. However, owing to numerous difficulties in the data collection process and the reliance on intensive annotations, real-world datasets lack sufficient quantity and diversity to support the increasing demand for data. This work introduces DriveSceneGen, a data-driven driving scenario generation method that learns from the real-world driving dataset and generates entire dynamic driving scenarios from scratch. DriveSceneGen is able to generate novel driving scenarios that align with real-world data distributions with high fidelity and diversity. Experimental results on 5k generated scenarios highlight the generation quality, diversity, and scalability compared to real-world datasets. To the best of our knowledge, DriveSceneGen is the first method that generates novel driving scenarios involving both static map elements and dynamic traffic participants from scratch.