Realistic adversarial scenario generation via human-like pedestrian model for autonomous vehicle control parameter optimisation

2026-01-05

arXiv.org

AI Summary

This work addresses the limited behavioral realism in adversarial scenarios commonly used in autonomous driving simulation, which often leads to overly conservative or poorly generalizable controllers in real-world human–vehicle interactions. To this end, the paper proposes a cognition-inspired human pedestrian model that, for the first time, incorporates both inter- and intra-individual behavioral variability into adversarial scenario generation, enhancing behavioral plausibility while preserving challenge. The approach enables closed-loop controller optimization and demonstrates more realistic gap-acceptance behavior and smoother deceleration profiles in CARLA simulations. Unsafe interactions are triggered only under specific pedestrian types and conditions, thereby effectively guiding the tuning of controller parameters toward safer and more efficient performance.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Adversarial Agents
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Autonomous vehicles (AVs) are rapidly advancing and are expected to play a central role in future mobility. Ensuring their safe deployment requires reliable interaction with other road users, not least pedestrians. Direct testing on public roads is costly and unsafe for rare but critical interactions, making simulation a practical alternative. Within simulation-based testing, adversarial scenarios are widely used to probe safety limits, but many prioritise difficulty over realism, producing exaggerated behaviours which may result in AV controllers that are overly conservative. We propose an alternative method, instead using a cognitively inspired pedestrian model featuring both inter-individual and intra-individual variability to generate behaviourally plausible adversarial scenarios. We provide a proof of concept demonstration of this method's potential for AV control optimisation, in closed-loop testing and tuning of an AV controller. Our results show that replacing the rule-based CARLA pedestrian with the human-like model yields more realistic gap acceptance patterns and smoother vehicle decelerations. Unsafe interactions occur only for certain pedestrian individuals and conditions, underscoring the importance of human variability in AV testing. Adversarial scenarios generated by this model can be used to optimise AV control towards safer and more efficient behaviour. Overall, this work illustrates how incorporating human-like road user models into simulation-based adversarial testing can enhance the credibility of AV evaluation and provide a practical basis to behaviourally informed controller optimisation.

Problem

• adversarial scenario generation
• autonomous vehicles
• human-like pedestrian model
• simulation-based testing
• behavioral realism

Innovation

• human-like pedestrian model
• adversarial scenario generation
• behavioral variability
• autonomous vehicle control optimisation
• simulation-based testing