Rethinking Robustness Assessment: Adversarial Attack on Learning-based Quadruped Locomotion Control

Опубликовано: 27 Февраль 2026
на канале: Robotic Systems Lab: Legged Robotics at ETH Zürich

9,380

268

In our RSS 2024 paper, we present a novel adversarial attack method designed to identify failuer cases in any type of locomotion controller, including state-of-the-art reinforcement learning (RL)-based controllers. Traditional heuristic tests, such as standard benchmarks or human experience, often fall short in uncovering these vulnerabilities. Our approach reveals the vulnerabilities of black-box neural network controllers, providing valuable insights that can be leveraged to enhance robustness through retraining.

Project website: https://fanshi14.github.io/me/rss24.html
Paper link: https://arxiv.org/abs/2405.12424