Dynasto: Validity-Aware Dynamic-Static Parameter Optimization for Autonomous Driving Testing

• URL: http://arxiv.org/abs/2603.21427v1
• Date: Sun, 22 Mar 2026 22:35:30 GMT
• Title: Dynasto: Validity-Aware Dynamic-Static Parameter Optimization for Autonomous Driving Testing
• Abstract summary: We propose Dynasto, a two-step testing approach to uncover safety-critical failures in autonomous driving systems.<n>First, we train an adversarial agent using reinforcement learning with temporal-logic-based validity criteria.<n>Second, a genetic algorithm searches over initial conditions while replaying the adversary's failure-inducing behaviors to reveal additional failures that the RL agent alone does not uncover.
• Score: 6.969678532857503
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Extensive simulation-based testing is important for assuring the safety of autonomous driving systems (ADS). However, generating safety-critical traffic scenarios remains challenging because failures often arise from rare, complex interactions with surrounding vehicles. Existing automatic scenario-generation approaches frequently fail to distinguish genuine ADS faults from collisions caused by implausible or invalid adversarial behaviors, and they typically optimize either scenario initialization or agent behavior in isolation. We propose Dynasto, a two-step testing approach that jointly optimizes initial scenario parameters and dynamic adversarial behaviors to uncover realistic safety-critical failures. First, we train an adversarial agent using reinforcement learning (RL) with temporal-logic-based validity criteria and a safe-distance model inspired by ISO 34502 to promote behaviorally plausible failures. Second, a genetic algorithm (GA) searches over initial conditions while replaying the adversary's failure-inducing behaviors to reveal additional failures that the RL agent alone does not uncover. Finally, a graph-based clustering pipeline groups failures into representative modes based on semantic event sequences. Our evaluation experiments in HighwayEnv across two ADS controllers show that Dynasto finds 60%-70% more valid failures than an RL-only adversary under the same evaluation budget. With clustering, we obtain about 12 interpretable failure modes per system under test, revealing valid failures driven by weaknesses in ego-controller behavior. These results indicate that coordinated dynamic-static optimization with explicit validity constraints is effective for exposing safety-relevant failures in ADS testing.

Related papers

• From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving [56.30087557121323]
  AlignADV is a learnability-guided closed-loop adversarial training framework.<n>It converts adversarial scenarios into resolvable and capability-aligned curricula.<n> Experiments show it reduces training steps by up to 40.6 percent.
  arXiv  Detail & Related papers  (2026-06-12T02:13:55Z)
• Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles [14.04593970867671]
  CARS (Context-Aware, Responsibility-attributed Scenario generation) is a framework that integrates responsibility attribution directly into adversarial scenario generation.<n> CARS consistently discovers feasible collision scenarios with high attribution rates under regulation-prescribed careful and competent driver models.
  arXiv  Detail & Related papers  (2026-05-13T16:33:07Z)
• ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving [63.980630608984605]
  This paper presents ADV-0, a closed-loop min-max optimization framework that treats the interaction between driving policy (defender) and adversarial agent (attacker) as a zero-sum Markov game.<n>To make this tractable, we cast dynamic adversary evolution as iterative preference learning, efficiently approximating this optimum and offering an algorithm-agnostic solution to the game.<n> Experiments indicate that it effectively exposes diverse safety-critical failures and greatly enhances the generalizability of both learned policies and motion planners against unseen long-tail risks.
  arXiv  Detail & Related papers  (2026-03-16T12:58:31Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Steerable Adversarial Scenario Generation through Test-Time Preference Alignment [58.37104890690234]
  Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems.<n>We introduce a new framework named textbfSteerable textbfAdversarial scenario textbfGEnerator (SAGE)<n>SAGE enables fine-grained test-time control over the trade-off between adversariality and realism without any retraining.
  arXiv  Detail & Related papers  (2025-09-24T13:27:35Z)
• Anomalous Decision Discovery using Inverse Reinforcement Learning [3.3675535571071746]
  Anomaly detection plays a critical role in Autonomous Vehicles (AVs) by identifying unusual behaviors through perception systems.<n>Current approaches, which often rely on predefined thresholds or supervised learning paradigms, exhibit reduced efficacy when confronted with unseen scenarios.<n>We present Trajectory-Reward Guided Adaptive Pre-training (TRAP), a novel IRL framework for anomaly detection.
  arXiv  Detail & Related papers  (2025-07-06T17:01:02Z)
• Active Test-time Vision-Language Navigation [60.69722522420299]
  ATENA is a test-time active learning framework that enables a practical human-robot interaction via episodic feedback on uncertain navigation outcomes.<n>In particular, ATENA learns to increase certainty in successful episodes and decrease it in failed ones, improving uncertainty calibration.<n>In addition, we propose a self-active learning strategy that enables an agent to evaluate its navigation outcomes based on confident predictions.
  arXiv  Detail & Related papers  (2025-06-07T02:24:44Z)
• Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving [65.61999354218628]
  We take the first step toward designing black-box adversarial attacks specifically targeting vision-language models (VLMs) in autonomous driving systems.<n>We propose Cascading Adversarial Disruption (CAD), which targets low-level reasoning breakdown by generating and injecting semantics.<n>We present Risky Scene Induction, which addresses dynamic adaptation by leveraging a surrogate VLM to understand and construct high-level risky scenarios.
  arXiv  Detail & Related papers  (2025-01-23T11:10:02Z)
• Generating Critical Scenarios for Testing Automated Driving Systems [5.975915967339764]
  AVASTRA is a Reinforcement Learning-based approach to generate realistic critical scenarios for testing Autonomous Driving System.<n>Results show AVASTRA's ability to outperform the state-of-the-art approach by generating 30% to 115% more collision scenarios.
  arXiv  Detail & Related papers  (2024-12-03T16:59:30Z)
• BehAVExplor: Behavior Diversity Guided Testing for Autonomous Driving Systems [27.223488110349567]
  Testing autonomous driving systems (ADSs) is a critical task for ensuring their reliability and safety. Existing methods mainly focus on searching for safety violations while the diversity of the generated test cases is ignored. We present a novel behavior-guided fuzzing technique (BehAVExplor) to explore the different behaviors of the ego vehicle and detect diverse violations.
  arXiv  Detail & Related papers  (2023-07-14T17:24:39Z)
• Realistic Safety-critical Scenarios Search for Autonomous Driving System via Behavior Tree [8.286351881735191]
  We propose the Matrix-Fuzzer, a behavior tree-based testing framework, to automatically generate realistic safety-critical test scenarios. Our approach is able to find the most types of safety-critical scenarios, but only generating around 30% of the total scenarios compared with the baseline algorithm.
  arXiv  Detail & Related papers  (2023-05-11T06:53:03Z)
• Adaptive Failure Search Using Critical States from Domain Experts [9.93890332477992]
  Failure search may be done through logging substantial vehicle miles in either simulation or real world testing. AST is one such method that poses the problem of failure search as a Markov decision process. We show that the incorporation of critical states into the AST framework generates failure scenarios with increased safety violations.
  arXiv  Detail & Related papers  (2023-04-01T18:14:41Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.