Skip to content
AI News HubLIVE
Original source2 min read

GPUSimBench: Towards Scalable and Reliable GPU-Accelerated Simulators in Embodied AI

Summary

GPUSimBench introduces a benchmark for evaluating GPU-accelerated robotic simulators on physical fidelity, parallel scalability, and computational determinism, revealing non-determinism in mainstream simulators like Isaac Lab and Genesis and identifying four stochasticity regimes.

SourcearXiv RoboticsAuthor: Huzhenyu Zhang, Shenghai Yuan, Wenrui Yan, Li Ma, Hengjie Li, Jingcheng Pang, Dmitry Yudin
GPUSimBench: Towards Scalable and Reliable GPU-Accelerated Simulators in Embodied AI
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 6 Jul 2026]

Title:GPUSimBench: Towards Scalable and Reliable GPU-Accelerated Simulators in Embodied AI

View a PDF of the paper titled GPUSimBench: Towards Scalable and Reliable GPU-Accelerated Simulators in Embodied AI, by Huzhenyu Zhang and 5 other authors

View PDF HTML (experimental)

Abstract:Data-driven embodied AI is rapidly transitioning into a paradigm that scales training through massively parallel simulation, where GPU-accelerated simulators serve as the foundational data infrastructure. However, as computational throughput scales, the underlying trade-offs between parallel efficiency, physical fidelity, and execution determinism remain largely unexamined, hindering the development of reliable robot learning. In this paper, we expose the hidden limits of mainstream GPU-based robotic simulators (e.g., Isaac Lab, Genesis) by introducing GPUSimBench, which focuses on scalability, physical consistency, and computational determinism. First, GPUSimBench establishes a physical grounding evaluation with a controlled inclined-plane task, quantifying the distributional alignment between simulated dynamics and their real-world counterparts. Second, we benchmark parallel scalability by measuring throughput and memory footprints across scaling environment counts. Crucially, beyond standard performance metrics, we unveil and quantify the inherent non-determinism introduced by GPU-batched execution, characterized by significant run-to-run and inter-environment variability even under identical initial conditions. Finally, we identify four empirical regimes of stochasticity within current simulator stacks, highlighting that unbounded scaling can compromise reproducibility without explicit constraints.

Comments: Accepted by IROS 2026

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2607.13059 [cs.RO]

(or arXiv:2607.13059v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2607.13059

arXiv-issued DOI via DataCite

Submission history

From: Huzhenyu Zhang [view email] [v1] Mon, 6 Jul 2026 15:46:30 UTC (1,556 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GPUSimBench: Towards Scalable and Reliable GPU-Accelerated Simulators in Embodied AI, by Huzhenyu Zhang and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

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

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • GPUSimBench evaluates physical consistency via a controlled inclined-plane task, quantifying sim-to-real distributional alignment.
  • The benchmark quantifies inherent non-determinism from GPU-batched execution, with significant run-to-run and inter-environment variability.
  • Four empirical regimes of stochasticity are identified, highlighting that unbounded scaling can compromise reproducibility without explicit constraints.

Highlights and analysis are generated automatically and may contain errors. Check the original source.