pith. sign in

arxiv: 2605.21168 · v1 · pith:TE3P3BVKnew · submitted 2026-05-20 · 💻 cs.AI

ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving

Qiyu Ruan , Yuxuan Wang , He Li , Zhenning Li , Cheng-zhong Xu This is my paper

Pith reviewed 2026-05-21 04:21 UTC · model grok-4.3

classification 💻 cs.AI
keywords critical scenario generationautonomous drivingsafety validationreinforcement learningphysical feasibilityboundary-driven generationadversarial testingSafeBench
0
0 comments X

The pith

ScenePilot generates scenarios at the physical feasibility boundary to expose autonomous vehicle failures more reliably than prior methods.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper aims to show that safety-critical scenario generation can be improved by explicitly targeting the boundary band: trajectories that obey vehicle-road physical limits yet still cause a deployed AV planner to crash. It does so by casting generation as constrained multi-objective reinforcement learning that balances an RSS-derived physical-feasibility score against an online-learned risk predictor, kept inside the target band by step-level shielding. A reader should care because existing generators either produce physically impossible crashes that waste evaluation effort or stay too far inside safe regions, leaving real edge cases untested. If the approach works, downstream adversarial fine-tuning on the generated scenarios can measurably lower real crash rates for the tested planners.

Core claim

ScenePilot formulates generation as constrained multi-objective reinforcement learning that combines an RSS-derived physical-feasibility score σ with an online-learned AV-risk predictor Φ and applies step-level feasibility-aware shielding so that produced trajectories remain inside the boundary band—physically solvable in principle yet capable of inducing failures in the deployed autonomy stack.

What carries the argument

The boundary band, the set of trajectories that satisfy vehicle-road physical constraints yet still cause the target AV stack to fail, maintained by a constrained multi-objective RL objective that trades off the RSS-derived feasibility score σ against the learned risk predictor Φ under step-level shielding.

If this is right

  • Evaluations on SafeBench with multiple planners produce collision rates 6.2 percentage points higher than prior methods while physical validity is preserved.
  • Adversarial fine-tuning of the tested planners on the generated boundary-band scenarios reduces their crash rates in subsequent testing.
  • The same generation pipeline can be applied to different autonomy stacks without changing the core feasibility-plus-risk formulation.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the boundary-band property transfers across simulation environments, the method could serve as a standardized stress-test suite for regulatory AV safety assessment.
  • Extending the shielding mechanism to include additional kinematic constraints could further tighten the generated scenarios around controller-agnostic failure modes.
  • The online-learned risk predictor could be reused as a cheap surrogate for expensive closed-loop simulation during early-stage AV development.

Load-bearing premise

The combination of the learned AV-risk predictor, the RSS feasibility score, and step-level shielding is enough to keep generated trajectories inside the intended boundary band without controller-specific artifacts or later filtering.

What would settle it

Run the generated scenarios on a planner never seen during generation and measure whether collision rates stay at least 6 percentage points above baselines while the fraction of physically invalid trajectories remains near zero.

Figures

Figures reproduced from arXiv: 2605.21168 by Cheng-zhong Xu, He Li, Qiyu Ruan, Yuxuan Wang, Zhenning Li.

Figure 1
Figure 1. Figure 1: Illustration of four interaction regimes relative to AV controller and physical feasibility. 1. Introduction Safety-critical scenarios are rare in real traffic but decisive for autonomous vehicles (AVs). Large-scale naturalistic driving logs cover everyday interactions, yet truly high￾consequence events occupy only a tiny fraction of the data ( [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of our ScenePilot framework. We characterize each rollout with an AV risk signal and a physics feasibility signal, and train a scenario policy to produce scenarios concentrated on the physically feasible yet AV policy-infeasible boundary band. antees, but it is counterproductive for critical scenario explo￾ration. Many near-crash yet still physically avoidable frames would be flagged as unsafe and… view at source ↗
Figure 3
Figure 3. Figure 3: Visualization of a near-boundary scenario generated by ScenePilot. To further examine whether ScenePilot remains effective across heterogeneous AV stacks, we conduct an additional study beyond the standard SafeBench RL-controller evalu￾ation. We generate 100 SafeBench Scenario 6 cases using CARLA Autopilot as the ego stack, and replay the gener￾ated cases on Autopilot, AIM-BEV, TransFuser, Behavior￾Agent, … view at source ↗
Figure 4
Figure 4. Figure 4: Quantitative characterization of the AV–physics gap between ScenePilot and ChatScene. (a) Physically invalid frame rate under different AV-risk thresholds. (b) Coverage ratio of ScenePilot to ChatScene in the AV-risk–physical-feasibility space. To better understand the generated scenarios, we analyze their AV–physics characteristics [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Aggregated value loss during ScenePilot training [PITH_FULL_IMAGE:figures/full_fig_p019_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Aggregated policy loss during ScenePilot training. B.5. AV Policy Fine-tuning We follow the adversarial fine-tuning procedure of ChatScene to adapt the surrogate AV policy under generated adversarial scenarios. Concretely, we start from the publicly released SAC-trained surrogate AV checkpoint from Chatscene and fine-tune it in the same simulator setting without modifying the architecture. We run fine-tuni… view at source ↗
read the original abstract

Safety-critical scenarios are central to evaluating autonomous driving systems, yet their rarity in naturalistic logs makes simulation-based stress testing indispensable. Most scenario generation methods treat surrounding agents as adversaries, but they either (i) induce failures without explicitly modeling vehicle-road physical limits, yielding visually extreme yet physically unsolvable crashes, or (ii) enforce physical feasibility or policy feasibility in isolation, which can over-focus on aggressive maneuvers or remain tied to a controller-dependent capability boundary. We propose ScenePilot, a feasibility-guided, boundary-driven framework that targets the boundary band: scenarios that are physically solvable in principle yet still cause the deployed autonomy stack to fail. We formulate generation as constrained multi-objective reinforcement learning, combining an RSS-derived physical-feasibility score $\sigma$ with an online-learned AV-risk predictor $\Phi$, and introduce step-level feasibility-aware shielding to keep exploration near the feasibility boundary while avoiding infeasible artifacts. Experiments on SafeBench with multiple planners show that ScenePilot yields substantially higher collision rates (+6.2 percentage points) while preserving physical validity, and that adversarial fine-tuning on these boundary-band scenarios consistently reduces downstream crash rates. The code is available at https://github.com/QiyuRuan/ScenePilot.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. ScenePilot is a feasibility-guided framework for generating safety-critical scenarios in autonomous driving. It formulates scenario generation as constrained multi-objective reinforcement learning that combines an RSS-derived physical-feasibility score σ with an online-learned AV-risk predictor Φ, augmented by step-level feasibility-aware shielding. The method targets the 'boundary band' of scenarios that are physically solvable in principle yet cause deployed autonomy stacks to fail. On SafeBench with multiple planners, the paper reports a +6.2 percentage point increase in collision rates while preserving physical validity, and shows that adversarial fine-tuning on the generated scenarios reduces downstream crash rates. Code is released at https://github.com/QiyuRuan/ScenePilot.

Significance. If the central claims hold after addressing validation gaps, the work would offer a meaningful advance in simulation-based stress testing for autonomous vehicles by producing controllable, physically grounded scenarios that lie between overly aggressive and trivially solvable extremes. The open-source release and the reported downstream benefit from adversarial fine-tuning are concrete strengths that could support reproducibility and practical adoption in AV safety pipelines.

major comments (2)
  1. [Abstract / Experiments] Abstract and Experiments section: the headline +6.2 percentage point collision-rate lift is reported without error bars, confidence intervals, the number of independent runs, or explicit description of any data-exclusion or shielding rules applied to produce the number. This detail is load-bearing for the claim of a 'substantially higher' and reproducible improvement.
  2. [Method] Method section (formulation of σ, Φ, and shielding): the central claim that the combination of the RSS-derived feasibility score σ, the online-learned risk predictor Φ, and step-level shielding keeps trajectories inside the intended boundary band without controller-dependent artifacts or implicit post-hoc filtering lacks an independent solvability check (e.g., against an oracle planner with perfect information). Without such verification, it remains unclear whether observed failures reflect genuine boundary-band stress or artifacts of the generation process itself; this assumption is load-bearing for interpreting the +6.2 pp result.
minor comments (2)
  1. [Method] Notation for the multi-objective reward and the precise definition of the boundary band could be stated more formally (e.g., with an explicit mathematical characterization) to aid reproducibility.
  2. [Experiments] Figure captions and table legends should explicitly state the number of trials, random seeds, and any post-processing steps used to compute reported metrics.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below and have revised the manuscript to improve statistical reporting and validation of the boundary-band claim.

read point-by-point responses

  1. Referee: [Abstract / Experiments] Abstract and Experiments section: the headline +6.2 percentage point collision-rate lift is reported without error bars, confidence intervals, the number of independent runs, or explicit description of any data-exclusion or shielding rules applied to produce the number. This detail is load-bearing for the claim of a 'substantially higher' and reproducible improvement.

    Authors: We agree that the headline result requires statistical context for reproducibility. In the revised manuscript we now report the +6.2 pp improvement as the mean over five independent runs with different random seeds, include error bars showing one standard deviation, and explicitly describe the shielding rules together with any data-exclusion criteria in the Experiments section. revision: yes

  2. Referee: [Method] Method section (formulation of σ, Φ, and shielding): the central claim that the combination of the RSS-derived feasibility score σ, the online-learned risk predictor Φ, and step-level shielding keeps trajectories inside the intended boundary band without controller-dependent artifacts or implicit post-hoc filtering lacks an independent solvability check (e.g., against an oracle planner with perfect information). Without such verification, it remains unclear whether observed failures reflect genuine boundary-band stress or artifacts of the generation process itself; this assumption is load-bearing for interpreting the +6.2 pp result.

    Authors: We acknowledge the value of an independent check. The revised manuscript adds a solvability verification against an oracle planner with perfect information. This analysis shows that the large majority of ScenePilot trajectories remain physically solvable by the oracle while still inducing failures in the tested autonomy stacks, confirming that the generated scenarios lie in the intended boundary band rather than being artifacts of the generation process. We also clarify that the RSS-derived σ is controller-independent by construction. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper formulates scenario generation as constrained multi-objective RL that combines an RSS-derived physical-feasibility score σ (external rule set) with an online-learned AV-risk predictor Φ and step-level shielding. No equations or claims in the abstract reduce a reported performance metric (e.g., +6.2 pp collision-rate lift) to a fitted parameter or self-citation by construction. The central experimental results on SafeBench are presented as empirical outcomes rather than tautological outputs of the generation process itself. The derivation chain therefore remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The framework rests on the external RSS physical-feasibility rules and on the assumption that an online-learned risk predictor can be trained without introducing bias into the boundary-band targeting. No explicit free parameters or invented entities are named in the abstract.

axioms (2)
  • domain assumption RSS-derived physical-feasibility score σ accurately captures vehicle-road physical limits.
    Invoked to define the feasible region that the generator must respect.
  • domain assumption Step-level feasibility-aware shielding prevents drift into infeasible states without distorting the risk signal.
    Central to keeping exploration near the boundary band.

pith-pipeline@v0.9.0 · 5750 in / 1411 out tokens · 24981 ms · 2026-05-21T04:21:14.938834+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

  • IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear
    ?
    unclear

    Relation between the paper passage and the cited Recognition theorem.

    We develop a constrained multi-objective adversarial generator that couples physical and policy signals (σ,Φ) with step-level feasibility-aware shielding and feasibility-threshold sweeping to concentrate on physically feasible yet policy-infeasible near-boundary scenarios.

  • IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear
    ?
    unclear

    Relation between the paper passage and the cited Recognition theorem.

    We formulate generation as constrained multi-objective reinforcement learning, combining an RSS-derived physical-feasibility score σ with an online-learned AV-risk predictor Φ, and introduce step-level feasibility-aware shielding

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

64 extracted references · 64 canonical work pages · 2 internal anchors

  1. [1]

    2005 , organization=

    An adaptive scheme to generate the pareto front based on the epsilon-constraint method , author=. 2005 , organization=

    work page 2005

  2. [2]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Generating useful accident-prone driving scenarios via a learned traffic prior , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    work page

  3. [3]

    ICML 2019 Workshop on Identifying and Understanding Deep Learning Phenomena , year=

    Adversarial Training Can Hurt Generalization , author=. ICML 2019 Workshop on Identifying and Understanding Deep Learning Phenomena , year=

    work page 2019

  4. [4]

    On a Formal Model of Safe and Scalable Self-driving Cars

    On a formal model of safe and scalable self-driving cars , author=. arXiv preprint arXiv:1708.06374 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  5. [5]

    Accident Analysis & Prevention , volume=

    Efficiency performance and safety evaluation of the responsibility-sensitive safety in freeway car-following scenarios using automated longitudinal controls , author=. Accident Analysis & Prevention , volume=. 2022 , publisher=

    work page 2022

  6. [6]

    Nature , volume=

    Dense reinforcement learning for safety validation of autonomous vehicles , author=. Nature , volume=. 2023 , publisher=

    work page 2023

  7. [7]

    Nature communications , volume=

    Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment , author=. Nature communications , volume=. 2021 , publisher=

    work page 2021

  8. [8]

    IEEE Transactions on Intelligent Transportation Systems , volume=

    A survey on safety-critical driving scenario generation—a methodological perspective , author=. IEEE Transactions on Intelligent Transportation Systems , volume=. 2023 , publisher=

    work page 2023

  9. [9]

    Science robotics , volume=

    AADS: Augmented autonomous driving simulation using data-driven algorithms , author=. Science robotics , volume=. 2019 , publisher=

    work page 2019

  10. [10]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Unisim: A neural closed-loop sensor simulator , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    work page

  11. [11]

    Accident Analysis & Prevention , volume=

    Waymo simulated driving behavior in reconstructed fatal crashes within an autonomous vehicle operating domain , author=. Accident Analysis & Prevention , volume=. 2021 , publisher=

    work page 2021

  12. [12]

    2019 International Conference on Robotics and Automation (ICRA) , pages=

    Structured domain randomization: Bridging the reality gap by context-aware synthetic data , author=. 2019 International Conference on Robotics and Automation (ICRA) , pages=. 2019 , organization=

    work page 2019

  13. [13]

    IEEE Robotics and Automation Letters , volume=

    Multimodal safety-critical scenarios generation for decision-making algorithms evaluation , author=. IEEE Robotics and Automation Letters , volume=. 2021 , publisher=

    work page 2021

  14. [14]

    2019 IEEE Intelligent Vehicles Symposium (IV) , pages=

    Generating critical test scenarios for automated vehicles with evolutionary algorithms , author=. 2019 IEEE Intelligent Vehicles Symposium (IV) , pages=. 2019 , organization=

    work page 2019

  15. [15]

    Semantically Adversarial Scene Generation With Explicit Knowledge Guidance , year=

    Ding, Wenhao and Lin, Haohong and Li, Bo and Zhao, Ding , journal=. Semantically Adversarial Scene Generation With Explicit Knowledge Guidance , year=

    work page

  16. [16]

    2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI) , pages=

    Building safer autonomous agents by leveraging risky driving behavior knowledge , author=. 2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI) , pages=. 2021 , organization=

    work page 2021

  17. [17]

    Tsinghua Science and Technology , volume=

    Realistic Corner Case Generation for Autonomous Vehicles with Multimodal Large Language Model , author=. Tsinghua Science and Technology , volume=. 2026 , publisher=

    work page 2026

  18. [18]

    nature communications , volume=

    Curse of rarity for autonomous vehicles , author=. nature communications , volume=. 2024 , publisher=

    work page 2024

  19. [19]

    2019 International Conference on Robotics and Automation (ICRA) , pages=

    Generating adversarial driving scenarios in high-fidelity simulators , author=. 2019 International Conference on Robotics and Automation (ICRA) , pages=. 2019 , organization=

    work page 2019

  20. [20]

    1998 , publisher=

    Reinforcement learning: An introduction , author=. 1998 , publisher=

    work page 1998

  21. [21]

    2020 IEEE International Conference on Robotics and Automation (ICRA) , pages=

    Training adversarial agents to exploit weaknesses in deep control policies , author=. 2020 IEEE International Conference on Robotics and Automation (ICRA) , pages=. 2020 , organization=

    work page 2020

  22. [22]

    IEEE transactions on intelligent transportation systems , volume=

    Adversarial evaluation of autonomous vehicles in lane-change scenarios , author=. IEEE transactions on intelligent transportation systems , volume=. 2021 , publisher=

    work page 2021

  23. [23]

    Transportation research record , volume=

    Corner case generation and analysis for safety assessment of autonomous vehicles , author=. Transportation research record , volume=. 2021 , publisher=

    work page 2021

  24. [24]

    2024 IEEE International Conference on Robotics and Automation (ICRA) , pages=

    Safety-critical scenario generation via reinforcement learning based editing , author=. 2024 IEEE International Conference on Robotics and Automation (ICRA) , pages=. 2024 , organization=

    work page 2024

  25. [25]

    Conference on Robot Learning , pages=

    FREA: Feasibility-Guided Generation of Safety-Critical Scenarios with Reasonable Adversariality , author=. Conference on Robot Learning , pages=. 2025 , organization=

    work page 2025

  26. [26]

    Icml , volume=

    Policy invariance under reward transformations: Theory and application to reward shaping , author=. Icml , volume=. 1999 , organization=

    work page 1999

  27. [27]

    International Joint Conference on Artificial Intelligence , year=

    Failure-scenario maker for rule-based agent using multi-agent adversarial reinforcement learning and its application to autonomous driving , author=. International Joint Conference on Artificial Intelligence , year=

    work page

  28. [28]

    The Thirteenth International Conference on Learning Representations , year=

    Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning , author=. The Thirteenth International Conference on Learning Representations , year=

    work page

  29. [29]

    International Conference on Machine Learning , pages=

    Safe reinforcement learning using advantage-based intervention , author=. International Conference on Machine Learning , pages=. 2021 , organization=

    work page 2021

  30. [30]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Scalability in perception for autonomous driving: Waymo open dataset , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    work page

  31. [31]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    nuscenes: A multimodal dataset for autonomous driving , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    work page

  32. [32]

    IEEE Transactions on Intelligent Transportation Systems , year=

    Llm-attacker: Enhancing closed-loop adversarial scenario generation for autonomous driving with large language models , author=. IEEE Transactions on Intelligent Transportation Systems , year=

    work page

  33. [33]

    Conference on robot learning , pages=

    CARLA: An open urban driving simulator , author=. Conference on robot learning , pages=. 2017 , organization=

    work page 2017

  34. [34]

    Advances in Neural Information Processing Systems , volume=

    Safebench: A benchmarking platform for safety evaluation of autonomous vehicles , author=. Advances in Neural Information Processing Systems , volume=

    work page

  35. [35]

    Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method , year=

    Ding, Wenhao and Chen, Baiming and Xu, Minjun and Zhao, Ding , booktitle=. Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method , year=

    work page

  36. [36]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Advsim: Generating safety-critical scenarios for self-driving vehicles , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    work page

  37. [37]

    2019 , howpublished =

    work page 2019

  38. [38]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    On adversarial robustness of trajectory prediction for autonomous vehicles , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    work page

  39. [39]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    Chatscene: Knowledge-enabled safety-critical scenario generation for autonomous vehicles , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    work page

  40. [40]

    Proximal Policy Optimization Algorithms

    Proximal policy optimization algorithms , author=. arXiv preprint arXiv:1707.06347 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  41. [41]

    International conference on machine learning , pages=

    Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor , author=. International conference on machine learning , pages=. 2018 , organization=

    work page 2018

  42. [42]

    International conference on machine learning , pages=

    Addressing function approximation error in actor-critic methods , author=. International conference on machine learning , pages=. 2018 , organization=

    work page 2018

  43. [43]

    Advances in Neural Information Processing Systems , volume=

    Towards safe reinforcement learning with a safety editor policy , author=. Advances in Neural Information Processing Systems , volume=

    work page

  44. [44]

    2018 IEEE Intelligent Vehicles Symposium (IV) , pages=

    Adaptive stress testing for autonomous vehicles , author=. 2018 IEEE Intelligent Vehicles Symposium (IV) , pages=. 2018 , organization=

    work page 2018

  45. [45]

    2021 IEEE Intelligent Vehicles Symposium (IV) , pages=

    Generating and characterizing scenarios for safety testing of autonomous vehicles , author=. 2021 IEEE Intelligent Vehicles Symposium (IV) , pages=. 2021 , organization=

    work page 2021

  46. [46]

    ACM Transactions on Privacy and Security , volume=

    Safe driving adversarial trajectory can mislead: Toward more stealthy adversarial attack against autonomous driving prediction module , author=. ACM Transactions on Privacy and Security , volume=. 2025 , publisher=

    work page 2025

  47. [47]

    Learning for Dynamics and Control Conference , pages=

    Targeted adversarial attacks against neural network trajectory predictors , author=. Learning for Dynamics and Control Conference , pages=. 2023 , organization=

    work page 2023

  48. [48]

    32nd USENIX Security Symposium (USENIX Security 23) , pages=

    Discovering adversarial driving maneuvers against autonomous vehicles , author=. 32nd USENIX Security Symposium (USENIX Security 23) , pages=

    work page

  49. [49]

    IEEE Robotics and Automation Letters , volume=

    Seal: Towards safe autonomous driving via skill-enabled adversary learning for closed-loop scenario generation , author=. IEEE Robotics and Automation Letters , volume=. 2025 , publisher=

    work page 2025

  50. [50]

    IEEE Transactions on Intelligent Vehicles , year=

    Adversarial safety-critical scenario generation using naturalistic human driving priors , author=. IEEE Transactions on Intelligent Vehicles , year=

    work page

  51. [51]

    IEEE Transactions on Intelligent Transportation Systems , year=

    Crash-based safety testing of autonomous vehicles: Insights from generating safety-critical scenarios based on in-depth crash data , author=. IEEE Transactions on Intelligent Transportation Systems , year=

    work page

  52. [52]

    IEEE Transactions on Intelligent Vehicles , year=

    Adversarial stress test for autonomous vehicle via series reinforcement learning tasks with reward shaping , author=. IEEE Transactions on Intelligent Vehicles , year=

    work page

  53. [53]

    IEEE Transactions on Software Engineering , volume=

    Learning configurations of operating environment of autonomous vehicles to maximize their collisions , author=. IEEE Transactions on Software Engineering , volume=. 2022 , publisher=

    work page 2022

  54. [54]

    2023 IEEE Intelligent Vehicles Symposium (IV) , pages=

    (Re) 2 H2O: Autonomous driving scenario generation via reversely regularized hybrid offline-and-online reinforcement learning , author=. 2023 IEEE Intelligent Vehicles Symposium (IV) , pages=. 2023 , organization=

    work page 2023

  55. [55]

    IEEE transactions on intelligent transportation systems , volume=

    Scenario-based test automation for highly automated vehicles: A review and paving the way for systematic safety assurance , author=. IEEE transactions on intelligent transportation systems , volume=. 2021 , publisher=

    work page 2021

  56. [56]

    2020 IEEE intelligent vehicles symposium (IV) , pages=

    Fundamental considerations around scenario-based testing for automated driving , author=. 2020 IEEE intelligent vehicles symposium (IV) , pages=. 2020 , organization=

    work page 2020

  57. [57]

    Accident Analysis & Prevention , volume=

    A dynamic test scenario generation method for autonomous vehicles based on conditional generative adversarial imitation learning , author=. Accident Analysis & Prevention , volume=. 2024 , publisher=

    work page 2024

  58. [58]

    IEEE Transactions on Intelligent Vehicles , year=

    Interactive critical scenario generation for autonomous vehicles testing based on in-depth crash data using reinforcement learning , author=. IEEE Transactions on Intelligent Vehicles , year=

    work page

  59. [59]

    No More Traffic Tickets: A Tutorial to Ensure Traffic-Rule Compliance of Automated Vehicles , year=

    Althoff, Matthias and Maierhofer, Sebastian and Würsching, Gerald and Lin, Yuanfei and Lercher, Florian and Stolz, Roland , journal=. No More Traffic Tickets: A Tutorial to Ensure Traffic-Rule Compliance of Automated Vehicles , year=

    work page

  60. [60]

    , journal=

    Althoff, Matthias and Dolan, John M. , journal=. Online Verification of Automated Road Vehicles Using Reachability Analysis , year=

    work page

  61. [61]

    2025 , url=

    Nigar Doga Karacik and Yingjie Xu and Xinyi Li and Yingbai Hu and Yinlong Liu , booktitle=. 2025 , url=

    work page 2025

  62. [62]

    Proceedings of the AAAI Conference on Artificial Intelligence , volume=

    Adversarial generation and collaborative evolution of safety-critical scenarios for autonomous vehicles , author=. Proceedings of the AAAI Conference on Artificial Intelligence , volume=

    work page

  63. [63]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Multi-modal fusion transformer for end-to-end autonomous driving , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    work page

  64. [64]

    European Conference on Computer Vision , pages=

    King: Generating safety-critical driving scenarios for robust imitation via kinematics gradients , author=. European Conference on Computer Vision , pages=. 2022 , organization=

    work page 2022