We present an approach for creating adversarial jaywalkers, autonomous pedestrian models which intentionally act to create unsafe situations involving other vehicles. An adversarial jaywalker employs a hybrid state-model with social forces and state transition rules. The parameters (for social forces and state transitions) of this model are tuned via reinforcement learning to create risky situations faster with synthetic yet plausible behavior. The resulting jaywalkers are capable of realistic behavior while still engaging in sufficiently risky actions to be useful for testing. These adversarial pedestrian models are useful in a wide range of scenario-based tests for autonomous vehicles.
Adversarial jaywalker modeling for simulation-based testing of Autonomous Vehicle Systems
2022 IEEE Intelligent Vehicles Symposium (IV) ; 1697-1702
05.06.2022
570108 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Generating autonomous vehicle testing data through perturbations and adversarial loss functions
Europäisches Patentamt | 2025
|Adversarial scenarios for safety testing of autonomous vehicles
Europäisches Patentamt | 2023
|Adversarial scenarios for safety testing of autonomous vehicles
Europäisches Patentamt | 2024
|ADVERSARIAL SCENARIOS FOR SAFETY TESTING OF AUTONOMOUS VEHICLES
Europäisches Patentamt | 2023
|ADVERSARIAL SCENARIOS FOR SAFETY TESTING OF AUTONOMOUS VEHICLES
Europäisches Patentamt | 2021
|