Realistic Extreme Behavior Generation for Improved AV Testing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913503452856320 |
|---|---|
| author | Dyro, Robert Foutter, Matthew Li, Ruolin Di Lillo, Luigi Schmerling, Edward Zhou, Xilin Pavone, Marco |
| author_facet | Dyro, Robert Foutter, Matthew Li, Ruolin Di Lillo, Luigi Schmerling, Edward Zhou, Xilin Pavone, Marco |
| contents | This work introduces a framework to diagnose the strengths and shortcomings of Autonomous Vehicle (AV) collision avoidance technology with synthetic yet realistic potential collision scenarios adapted from real-world, collision-free data. Our framework generates counterfactual collisions with diverse crash properties, e.g., crash angle and velocity, between an adversary and a target vehicle by adding perturbations to the adversary's predicted trajectory from a learned AV behavior model. Our main contribution is to ground these adversarial perturbations in realistic behavior as defined through the lens of data-alignment in the behavior model's parameter space. Then, we cluster these synthetic counterfactuals to identify plausible and representative collision scenarios to form the basis of a test suite for downstream AV system evaluation. We demonstrate our framework using two state-of-the-art behavior prediction models as sources of realistic adversarial perturbations, and show that our scenario clustering evokes interpretable failure modes from a baseline AV policy under evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10669 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Realistic Extreme Behavior Generation for Improved AV Testing Dyro, Robert Foutter, Matthew Li, Ruolin Di Lillo, Luigi Schmerling, Edward Zhou, Xilin Pavone, Marco Optimization and Control Robotics This work introduces a framework to diagnose the strengths and shortcomings of Autonomous Vehicle (AV) collision avoidance technology with synthetic yet realistic potential collision scenarios adapted from real-world, collision-free data. Our framework generates counterfactual collisions with diverse crash properties, e.g., crash angle and velocity, between an adversary and a target vehicle by adding perturbations to the adversary's predicted trajectory from a learned AV behavior model. Our main contribution is to ground these adversarial perturbations in realistic behavior as defined through the lens of data-alignment in the behavior model's parameter space. Then, we cluster these synthetic counterfactuals to identify plausible and representative collision scenarios to form the basis of a test suite for downstream AV system evaluation. We demonstrate our framework using two state-of-the-art behavior prediction models as sources of realistic adversarial perturbations, and show that our scenario clustering evokes interpretable failure modes from a baseline AV policy under evaluation. |
| title | Realistic Extreme Behavior Generation for Improved AV Testing |
| topic | Optimization and Control Robotics |
| url | https://arxiv.org/abs/2409.10669 |