# Improving the Generalization of End-to-End Driving through Procedural Generation

arXiv: https://arxiv.org/abs/2012.13681 · HTML: https://mlsanity.com/paper/2012.13681/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [Safe Driving via Expert Guided Policy Optimization](https://mlsanity.com/paper/2110.06831/) (2021)
- [From Model-Based to Data-Driven Simulation: Challenges and Trends in Autonomous Driving](https://mlsanity.com/paper/2305.13960/) (2023)
- [GPD-1: Generative Pre-training for Driving](https://mlsanity.com/paper/2412.08643/) (2024)
- [Procedural Generation of Complex Roundabouts for Autonomous Vehicle Testing](https://mlsanity.com/paper/2303.17900/) (2023)
- [Probabilistic Generative Modeling for Procedural Roundabout Generation for Developing Countries](https://mlsanity.com/paper/2310.03687/) (2023)

## Abstract (arXiv)

Over the past few years there is a growing interest in the learning-based self driving system. To ensure safety, such systems are first developed and validated in simulators before being deployed in the real world. However, most of the existing driving simulators only contain a fixed set of scenes and a limited number of configurable settings. That might easily cause the overfitting issue for the learning-based driving systems as well as the lack of their generalization ability to unseen scenarios. To better evaluate and improve the generalization of end-to-end driving, we introduce an open-ended and highly configurable driving simulator called PGDrive, following a key feature of procedural generation. Diverse road networks are first generated by the proposed generation algorithm via sampling from elementary road blocks. Then they are turned into interactive training environments where traffic flows of nearby vehicles with realistic kinematics are rendered. We validate that training with the increasing number of procedurally generated scenes significantly improves the generalization of the agent across scenarios of different traffic densities and road networks. Many applications such as multi-agent traffic simulation and safe driving benchmark can be further built upon the simulator. To facilitate the joint research effort of end-to-end driving, we release the simulator and pretrained models at https://decisionforce.github.io/pgdrive