TrajRS: Towards Certified Robustness in Pedestrian Trajectory Prediction
Quick Answer
The paper introduces 'TrajRS', an extension of Randomized Smoothing for certified robustness in pedestrian trajectory prediction models, addressing vulnerabilities to adversarial attacks.
Quick Take
The paper introduces 'TrajRS', an extension of Randomized Smoothing for certified robustness in pedestrian trajectory prediction models, addressing vulnerabilities to adversarial attacks. Extensive experiments confirm TrajRS's effectiveness in providing robustness certification for smoothed predictors, crucial for enhancing safety in autonomous driving systems.
Key Points
- TrajRS extends Randomized Smoothing for improved robustness in trajectory prediction.
- Addresses vulnerabilities against sophisticated adversarial attacks in autonomous driving.
- Formal definitions of robustness in trajectory prediction are clarified and expanded.
- Experiments validate TrajRS's effectiveness for all smoothed pedestrian trajectory predictors.
- Accepted for presentation at the 2026 IEEE International Conference on Acoustics, Speech and Signal Processing.
Paper Resources
📖 Reader Mode
~2 min readAbstract:The robustness of trajectory prediction models is crucial for developing safe autonomous driving systems. Adversarial attacks on trajectory prediction can significantly impair the accuracy of predicted trajectories, leading to hazardous driving behaviors. While heuristic defense strategies have been implemented to enhance the robustness of trajectory prediction models, these measures often fail against more sophisticated, targeted adversarial attacks. Hence, there is a pressing need to establish verifiable safety assurances for trajectory prediction models. In this paper, we extend the traditional Randomized Smoothing framework to "TrajRS", which provides a certified robust radius for smoothed trajectory predictors. We clarify and expand the formal definitions of robustness in trajectory prediction and tailor the practical TrajRS scheme specifically to "robustness for the optimal prediction" and "robustness for all possible predictions". An extensive set of experiments demonstrates that TrajRS effectively achieves robustness certification for all smoothed pedestrian trajectory predictors in this work.
| Comments: | Accepted by 2026 IEEE International Conference on Acoustics, Speech and Signal Processing |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.28716 [cs.AI] |
| (or arXiv:2606.28716v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.28716 arXiv-issued DOI via DataCite |
Submission history
From: Liang Zhang [view email]
[v1]
Sat, 27 Jun 2026 03:45:26 UTC (834 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Verification Horizon: No Silver Bullet for Coding Agent Rewards
As coding agents evolve, verifying solutions becomes more challenging than generating them, necessitating a focus on scalable, faithful, and robust verification methods. The study reveals that no fixed reward function can sustain effectiveness as model capabilities advance, emphasizing the need for verification to evolve alongside solution generation.