2026-05-20 04:00 UTCOriginal source2 min readUpdated: 2026-06-30 13:03 UTC

Adversarial Stress Testing of SPARK Humanoid Safety Filters

This study evaluates the robustness of SPARK humanoid safety filters through replication and stress testing in MuJoCo. It compares six safety filter methods and builds a post-processing pipeline to compute goal-tracking, minimum-distance, and collision-step metrics. Results show trade-offs between goal tracking and collision reduction, and stress tests reveal sensitivity to obstacle crowding, noisy distance estimates, and delayed information. The authors recommend evaluating beyond nominal performance using failure-exposing metrics.

SourcearXiv RoboticsAuthor: Saurav Ghosh, Abdou Sow, Luke Zhang

[2605.19009] Adversarial Stress Testing of SPARK Humanoid Safety Filters

[Submitted on 18 May 2026]

Title:Adversarial Stress Testing of SPARK Humanoid Safety Filters

View a PDF of the paper titled Adversarial Stress Testing of SPARK Humanoid Safety Filters, by Saurav Ghosh and 2 other authors

View PDF HTML (experimental)

Abstract:Humanoid robots are difficult to deploy safely because they have high-dimensional bodies, many collision constraints, and must operate near people and obstacles. Safety filters help by modifying a nominal control action when it may violate collision-avoidance constraints. Still, nominal benchmark scores do not fully show how these filters behave in harder environments. In this work, we study the robustness of SPARK humanoid safety filters through replication and stress testing. We replicate the SPARK benchmark case G1SportMode_D1_WG_SO_v1 in MuJoCo and evaluate RSSA, RSSS, SSA, CBF, PFM, and SMA under controlled random seeds. We also built a post-processing pipeline that converts raw SPARK logs into goal-tracking, minimum-distance, and collision-step metrics. Our results show that some methods track the goal more closely, while others reduce collision steps more effectively. The stress tests further indicate that safety behavior can change under obstacle crowding, noisy distance estimates, and delayed obstacle information. These findings suggest that humanoid autonomy should be evaluated beyond nominal performance, using metrics that expose failure modes before deployment.

Comments: 5 pages, 7 figures, 1 table. Code available at this https URL

Subjects:

Robotics (cs.RO); Systems and Control (eess.SY)

Cite as: arXiv:2605.19009 [cs.RO]

(or arXiv:2605.19009v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2605.19009

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Saurav Ghosh [view email] [v1] Mon, 18 May 2026 18:32:45 UTC (5,022 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Adversarial Stress Testing of SPARK Humanoid Safety Filters, by Saurav Ghosh and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-05

Change to browse by:

cs cs.SY eess eess.SY

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)