A Customizable Dynamic Scenario Modeling and Data Generation Platform for Autonomous Driving

TL;DR

This paper introduces a comprehensive platform for modeling, simulating, and generating synthetic dynamic scenarios to enhance training datasets for autonomous driving systems, especially for rare and complex interactions.

Contribution

It presents the first integrated platform tailored for autonomous driving that models, simulates, and generates diverse dynamic scenarios with labeled sensor data for data augmentation.

Findings

Enables generation of realistic synthetic data for rare scenarios.

Supports multiple modalities of sensor data in simulation.

Facilitates improved training of autonomous driving modules.

Abstract

Safely interacting with humans is a significant challenge for autonomous driving. The performance of this interaction depends on machine learning-based modules of an autopilot, such as perception, behavior prediction, and planning. These modules require training datasets with high-quality labels and a diverse range of realistic dynamic behaviors. Consequently, training such modules to handle rare scenarios is difficult because they are, by definition, rarely represented in real-world datasets. Hence, there is a practical need to augment datasets with synthetic data covering these rare scenarios. In this paper, we present a platform to model dynamic and interactive scenarios, generate the scenarios in simulation with different modalities of labeled sensor data, and collect this information for data augmentation. To our knowledge, this is the first integrated platform for these tasks specialized to the autonomous driving domain.