Generating Traffic Scenarios via In-Context Learning to Learn Better Motion Planner

TL;DR

This paper introduces a cost-effective approach to generate diverse, safety-critical traffic scenarios using large language models and simulation, improving the robustness of motion planners in autonomous driving.

Contribution

It presents a novel method that translates text descriptions into traffic scenarios via in-context learning, enabling the creation of synthetic data for training better motion planners.

Findings

Motion planners trained with generated scenarios outperform those trained only on real data.

The proposed method effectively produces diverse critical traffic scenarios.

Synthetic data enhances the robustness of autonomous driving systems.

Abstract

Motion planning is a crucial component in autonomous driving. State-of-the-art motion planners are trained on meticulously curated datasets, which are not only expensive to annotate but also insufficient in capturing rarely seen critical scenarios. Failing to account for such scenarios poses a significant risk to motion planners and may lead to incidents during testing. An intuitive solution is to manually compose such scenarios by programming and executing a simulator (e.g., CARLA). However, this approach incurs substantial human costs. Motivated by this, we propose an inexpensive method for generating diverse critical traffic scenarios to train more robust motion planners. First, we represent traffic scenarios as scripts, which are then used by the simulator to generate traffic scenarios. Next, we develop a method that accepts user-specified text descriptions, which a Large Language Model translates into scripts using in-context learning. The output scripts are sent to the simulator that produces the corresponding traffic scenarios. As our method can generate abundant safety-critical traffic scenarios, we use them as synthetic training data for motion planners. To demonstrate the value of generated scenarios, we train existing motion planners on our synthetic data, real-world datasets, and a combination of both. Our experiments show that motion planners trained with our data significantly outperform those trained solely on real-world data, showing the usefulness of our synthetic data and the effectiveness of our data generation method. Our source code is available at https://ezharjan.github.io/AutoSceneGen.