DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World
DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World
This paper introduces DuoBench, an extensible benchmarking framework designed to evaluate bimanual manipulation policies on the FR3 Duo platform.
The authors introduce DuoBench, a benchmark framework for bimanual manipulation on the FR3 Duo platform that includes eleven tasks across four coordination categories, implemented in simulation and partially replicated in the real world with reproducible task recipes.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- TeleoperatedOpen source S3
- paper: not_reported
- code: Available Artifact link Open source S5
- dataset: Available Artifact link Open source S5
- weights: not_reported
- code: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2606.11901v2 Announce Type: replace Abstract: Bimanual robot systems substantially expand manipulation capabilities, but coordinating two arms introduces additional control complexity and failure modes that are not well captured by existing benchmarks. We introduce DuoBench, an extensible benchmarking framework for bimanual manipulation policies on the FR3 Duo platform. DuoBench comprises eleven tasks spanning
Open source S2
four coordination categories, implemented in simulation and partially replicated in the real world through reproducible task recipes with 3D-printable assets. In addition, we propose a stage-based evaluation scheme that supports fine-grained semantic failure analysis beyond binary success. It includes stage-conditional pass rates with confidence intervals as well as human-teleoperated datasets for all benchmark tasks
Open source S3
. We benchmark several imitation-learning and vision-language-action policies in simulation and on real hardware. Our results show that current policies remain challenged by bimanual manipulation, particularly at the beginning of interaction, during parallel arm execution, and in sim-to-real transfer settings. We further find that simulation reveals the same failure modes as real-world experiments. DuoBench provides
Open source S4
a reproducible testbed for analyzing them and studying future methods for dual-arm policy learning. Code, datasets, and videos are available at https://duobench.github.io
Open source S5
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org