Generating Adversarial Driving Scenarios in High-Fidelity Simulators

By Yasasa Abeysirigoonawardena, Florian Shkurti, G. Dudek. 2019

149 citations recorded by the source corpus.

In recent years self-driving vehicles have become more commonplace on public roads, with the promise of bringing safety and efficiency to modern transportation systems. Increasing the reliability of these vehicles on the road requires an extensive suite of software tests, ideally performed on highfidelity simulators, where multiple vehicles and pedestrians interact with the self-driving vehicle. It is therefore of critical importance to ensure that self-driving software is assessed against a wide range of challenging simulated driving scenarios. The state of the art in driving scenario generation, as adopted by some of the front-runners of the self-driving car industry, still relies on human input [1]. In this paper we propose to automate the process using Bayesian optimization to generate adversarial self-driving scenarios that expose poorly-engineered or poorly-trained self-driving policies, and increase the risk of collision with simulated pedestrians and vehicles. We show that by incorporating the generated scenarios into the training set of the self-driving policy, and by fine-tuning the policy using vision-based imitation learning we obtain safer self-driving behavior.

Subfields: Artificial Intelligence, Automotive Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ibrahim Sobh
2. B. R. Kiran
3. Patrick Pérez
4. Peng Wu
5. Bernhard Jaeger
6. Li Chen
7. Senthil Kumar Yogamani
8. Ahmad A. Al Sallab

In Automotive Engineering

1. Kashyap Chitta
2. Andreas Geiger
3. Hongyang Li
4. Li Chen
5. Peng Wu
6. Bernhard Jaeger
7. Ibrahim Sobh
8. B. R. Kiran

Citations in the corpus

• Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, background): “Authors in [119] proposed automated generation of challenging and rare driving scenarios in highfidelity photo-realistic simulators.”
• A Survey on Multimodal Large Language Models for Autonomous Driving (2023, background): “For example, generating adversarial safety-critical scenarios for training autonomous driving systems such that the system is more capable of handling cases with low probability [1, 36].”
• End-to-End Autonomous Driving: Challenges and Frontiers (2023, methodology): “In [258], Bayesian Optimization is employed to generate adversarial scenarios.”