AdvDO: Realistic Adversarial Attacks for Trajectory Prediction

09/19/2022
by   Yulong Cao, et al.
27

Trajectory prediction is essential for autonomous vehicles (AVs) to plan correct and safe driving behaviors. While many prior works aim to achieve higher prediction accuracy, few study the adversarial robustness of their methods. To bridge this gap, we propose to study the adversarial robustness of data-driven trajectory prediction systems. We devise an optimization-based adversarial attack framework that leverages a carefully-designed differentiable dynamic model to generate realistic adversarial trajectories. Empirically, we benchmark the adversarial robustness of state-of-the-art prediction models and show that our attack increases the prediction error for both general metrics and planning-aware metrics by more than 50 attack can lead an AV to drive off road or collide into other vehicles in simulation. Finally, we demonstrate how to mitigate the adversarial attacks using an adversarial training scheme.

READ FULL TEXT

page 2

page 14

page 26

research
01/13/2022

On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles

Trajectory prediction is a critical component for autonomous vehicles (A...
research
07/29/2022

Robust Trajectory Prediction against Adversarial Attacks

Trajectory prediction using deep neural networks (DNNs) is an essential ...
research
05/27/2022

Semi-supervised Semantics-guided Adversarial Training for Trajectory Prediction

Predicting the trajectories of surrounding objects is a critical task in...
research
12/08/2022

Targeted Adversarial Attacks against Neural Network Trajectory Predictors

Trajectory prediction is an integral component of modern autonomous syst...
research
08/24/2021

Are socially-aware trajectory prediction models really socially-aware?

Our field has recently witnessed an arms race of neural network-based tr...
research
08/11/2023

TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models

Robust pedestrian trajectory forecasting is crucial to developing safe a...
research
04/09/2020

Reciprocal Learning Networks for Human Trajectory Prediction

We observe that the human trajectory is not only forward predictable, bu...

Please sign up or login with your details

Forgot password? Click here to reset