# Boundary State Generation for Testing and Improvement of Autonomous Driving Systems

arXiv: https://arxiv.org/abs/2307.10590 · HTML: https://mlsanity.com/paper/2307.10590/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 67 references that are in the map.
- First posted on arXiv 20 Jul 2023.

## Builds on (most cited first, 15 of 15)

- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Misbehaviour Prediction for Autonomous Driving Systems](https://mlsanity.com/paper/1910.04443/) (2019)
- [Model-based Exploration of the Frontier of Behaviours for Deep Learning System Testing](https://mlsanity.com/paper/2007.02787/) (2020)
- [Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driving Systems](https://mlsanity.com/paper/2112.11255/) (2021)
- [A Survey on Automated Driving System Testing: Landscapes and Trends](https://mlsanity.com/paper/2206.05961/) (2022)
- [DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search](https://mlsanity.com/paper/2107.06997/) (2021)
- [Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Study](https://mlsanity.com/paper/1912.00805/) (2019)
- [Can Offline Testing of Deep Neural Networks Replace Their Online Testing?](https://mlsanity.com/paper/2101.11118/) (2021)
- [Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems](https://mlsanity.com/paper/2210.15432/) (2022)
- [DeepGuard: A Framework for Safeguarding Autonomous Driving Systems from Inconsistent Behavior](https://mlsanity.com/paper/2111.09533/) (2021)
- [Search-Based Testing of Reinforcement Learning](https://mlsanity.com/paper/2205.04887/) (2022)
- [Testing of Deep Reinforcement Learning Agents with Surrogate Models](https://mlsanity.com/paper/2305.12751/) (2023)
- [Digital Twins Are Not Monozygotic -- Cross-Replicating ADAS Testing in Two Industry-Grade Automotive Simulators](https://mlsanity.com/paper/2012.06822/) (2020)
- [Two is Better Than One: Digital Siblings to Improve Autonomous Driving Testing](https://mlsanity.com/paper/2305.08060/) (2023)
- [Self-driving scale car trained by Deep reinforcement learning](https://mlsanity.com/paper/1909.03467/) (2019)

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

- [Benchmarking Image Perturbations for Testing Automated Driving Assistance Systems](https://mlsanity.com/paper/2501.12269/) (2025)
- [Exploring Critical Testing Scenarios for Decision-Making Policies: An LLM Approach](https://mlsanity.com/paper/2412.06684/) (2024)
- [AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Tests](https://mlsanity.com/paper/2502.21100/) (2025)
- [Simulator Ensembles for Trustworthy Autonomous Driving Systems Testing](https://mlsanity.com/paper/2503.08936/) (2025)
- [Advancing Autonomous Driving System Testing: Demands, Challenges, and Future Directions](https://mlsanity.com/paper/2512.11887/) (2025)
- [Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles](https://mlsanity.com/paper/2604.07378/) (2026)

## Abstract (arXiv)

Recent advances in Deep Neural Networks (DNNs) and sensor technologies are enabling autonomous driving systems (ADSs) with an ever-increasing level of autonomy. However, assessing their dependability remains a critical concern. State-of-the-art ADS testing approaches modify the controllable attributes of a simulated driving environment until the ADS misbehaves. In such approaches, environment instances in which the ADS is successful are discarded, despite the possibility that they could contain hidden driving conditions in which the ADS may misbehave. In this paper, we present GENBO (GENerator of BOundary state pairs), a novel test generator for ADS testing. GENBO mutates the driving conditions of the ego vehicle (position, velocity and orientation), collected in a failure-free environment instance, and efficiently generates challenging driving conditions at the behavior boundary (i.e., where the model starts to misbehave) in the same environment instance. We use such boundary conditions to augment the initial training dataset and retrain the DNN model under test. Our evaluation results show that the retrained model has, on average, up to 3x higher success rate on a separate set of evaluation tracks with respect to the original DNN model.