zqzqz/AdvTrajectoryPrediction

Implementation of CVPR 2022 paper "On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles" https://arxiv.org/abs/2201.05057

36
/ 100
Emerging

This project helps automotive engineers and researchers understand how vulnerable autonomous vehicle trajectory prediction systems are to 'adversarial attacks.' It takes raw trajectory data from real-world driving datasets (like Apolloscape or NuScenes) and applies different attack methods to generate perturbed predictions. The output shows how much these attacks degrade the accuracy of predictions, helping developers build more robust self-driving car systems.

123 stars. No commits in the last 6 months.

Use this if you are developing or evaluating autonomous driving systems and need to assess the security and reliability of their trajectory prediction models against potential malicious interference.

Not ideal if you are looking for a general-purpose trajectory prediction model for deployment rather than a tool for adversarial robustness analysis.

autonomous-vehicles trajectory-prediction driving-safety automotive-security ADAS-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

123

Forks

22

Language

Python

License

Last pushed

Jul 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zqzqz/AdvTrajectoryPrediction"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.