Timezone: »

Robust Trajectory Prediction against Adversarial Attacks
Yulong Cao · Danfei Xu · Xinshuo Weng · Zhuoqing Morley Mao · Anima Anandkumar · Chaowei Xiao · Marco Pavone

Trajectory prediction using deep neural networks (DNNs) is an essential component of autonomous driving (AD) systems. However, these methods are vulnerable to adversarial attacks, leading to serious consequences such as collisions. In this work, we identify two key ingredients to defend trajectory prediction models against adversarial attacks including (1) designing effective adversarial training methods and (2) adding domain-specific data augmentation to mitigate the performance degradation on clean data. We demonstrate that our method is able to improve the performance by 46% on adversarial data and at the cost of only 3% performance degradation on clean data, compared to the model trained with clean data. Additionally, compared to existing robust methods, our method can improve performance by 21% on adversarial examples and 9\% on clean data. Our robust model is evaluated with a planner to study its downstream impacts. We demonstrate that our model can significantly reduce the severe accident rates (e.g., collisions and off-road driving).

Author Information

Yulong Cao (University of Michigan)
Danfei Xu (Georgia Tech)
Xinshuo Weng (Carnegie Mellon University)

Xinshuo Weng is a Ph.D. student (2018-) at Robotics Institute of Carnegie Mellon University (CMU) supervised by Kris Kitani. She received Masters (2016-17) also at CMU, where she worked with Yaser Sheikh and Kris Kitani. Prior to CMU, she worked at Oculus Research Pittsburgh (now Facebook Reality Lab) as a research engineer. Her Bachelor's degree was received from Wuhan University. Her primary research interest lies in 3D computer vision and Graph Neural Networks for autonomous systems. She was awarded a Qualcomm Innovation Fellowship for 2020-2021.

Zhuoqing Morley Mao (University of Michigan)
Anima Anandkumar (NVIDIA/Caltech)
Chaowei Xiao (ASU/NVIDIA)

I am Chaowei Xiao, a third year PhD student in CSE Department, University of Michigan, Ann Arbor. My advisor is Professor Mingyan Liu . I obtained my bachelor's degree in School of Software from Tsinghua University in 2015, advised by Professor Yunhao Liu, Professor Zheng Yang and Dr. Lei Yang. I was also a visiting student at UC Berkeley in 2018, advised by Professor Dawn Song and Professor Bo Li. My research interest includes adversarial machine learning.

Marco Pavone (Stanford University)

More from the Same Authors