Pith. sign in

REVIEW 5 cited by

Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.12424 v2 pith:FNHPARUW submitted 2024-05-21 cs.RO cs.LG

Fan Shi , Chong Zhang , Takahiro Miki , Joonho Lee , Marco Hutter , Stelian Coros This is my paper
classification cs.ROcs.LG
keywords controllerslocomotionadversarialattackslearningrobustnesssequentialvulnerabilities
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Legged locomotion has recently achieved remarkable success with the progress of machine learning techniques, especially deep reinforcement learning (RL). Controllers employing neural networks have demonstrated empirical and qualitative robustness against real-world uncertainties, including sensor noise and external perturbations. However, formally investigating the vulnerabilities of these locomotion controllers remains a challenge. This difficulty arises from the requirement to pinpoint vulnerabilities across a long-tailed distribution within a high-dimensional, temporally sequential space. As a first step towards quantitative verification, we propose a computational method that leverages sequential adversarial attacks to identify weaknesses in learned locomotion controllers. Our research demonstrates that, even state-of-the-art robust controllers can fail significantly under well-designed, low-magnitude adversarial sequence. Through experiments in simulation and on the real robot, we validate our approach's effectiveness, and we illustrate how the results it generates can be used to robustify the original policy and offer valuable insights into the safety of these black-box policies. Project page: https://fanshi14.github.io/me/rss24.html

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. High-speed control and navigation for quadrupedal robots on complex and discrete terrain

    cs.RO 2025-06 conditional novelty 7.0 of 10

    A hierarchical planner-plus-tracker system enables a quadruped to run on walls, clear a 1.3 m gap, and navigate discrete terrain at up to 4 m/s using a competitive generative curriculum.

  2. SoK: Cybersecurity Assessment of Humanoid Ecosystem

    cs.CR 2025-08 conditional novelty 5.0 of 10

    A seven-layer humanoid security model with a 39x35 risk-weighted scoring method, demonstrated on Pepper, G1 EDU, and Digit.

  3. Skill-Nav: Enhanced Navigation with Versatile Quadrupedal Locomotion via Waypoint Interface

    cs.RO 2025-06 conditional novelty 5.0 of 10

    A waypoint-based interface between planners and a trained quadrupedal locomotion policy enables navigation over diverse obstacles in simulation and on a real robot.

  4. Robust RL Control for Bipedal Locomotion with Closed Kinematic Chains

    cs.RO 2025-07 conditional novelty 4.0 of 10

    A reinforcement-learning gait controller that explicitly models closed kinematic chains outperforms one trained on a simplified serial model, both in simulation and on the physical TopA robot.

  5. Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots

    cs.RO 2025-05 conditional novelty 4.0 of 10

    A hybrid position-torque policy with a learned disturbance observer lets a Unitree Go2 quadruped carry heavy payloads and reject impacts beyond a DreamWaQ baseline.

Pith tools