arXiv：cs.AI· Ming Shin Cindy Sung, Duan Leijiahao, Haoxiang Wang, Boning Tan, Liangna Fu, Chao Tan, Yafu Li, Yulong Chen, Chaoqun Wan, Zhen Huang, Shuxian Liang, Xian-Sheng Hua·· 16 小时前
LIBERO-Industry：面向工业流程约束的机器人操作基准
LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints
AI 导读
研究者提出 LIBERO-Industry，一个基于 LIBERO 构建的机器人操作基准，将产品变体、移动物料流、有限执行窗口和严格几何公差等工业约束转化为可控任务条件。
正文
Authors:Ming Shin Cindy Sung, Duan Leijiahao, Haoxiang Wang, Boning Tan, Liangna Fu, Chao Tan, Yafu Li, Yulong Chen, Chaoqun Wan, Zhen Huang, Shuxian Liang, Xian-Sheng Hua
Abstract:Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing products and production conditions. Such settings impose industrial process constraints, including product variants, moving material flows, finite execution windows, and tight geometric tolerances. However, existing evaluation frameworks do not systematically capture these constraints when assessing generalist robot policies. To address this gap, we introduce LIBERO-Industry, a novel benchmark built on the widely used robot learning benchmark LIBERO, that translates the aforementioned industrial constraints into controllable task conditions and measurable success criteria. Specifically, LIBERO-Industry comprises three classic task scenarios: Static-to-Dynamic (S2D) loading, Dynamic-to-Static (D2S) unloading, and Dynamic-to-Dynamic (D2D) transfer. The suites contain 216 tasks in total that systematically vary object geometry, conveyor speed, interaction-window duration, and geometric acceptance region size. Extensive experiments across five generalist robot policies (including vision-language-action models and world-action models) show that performance progressively degrades as industrial constraints are introduced and combined. Under a shared fine-tuning and evaluation protocol, the LIBERO-Industry co-training condition achieved higher observed target-transfer completion than the original-LIBERO condition.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16782 [cs.AI] |
| (or arXiv:2610.16782v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16782 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ming Shin Cindy Sung [view email]
[v1]
Mon, 12 Oct 2026 13:38:46 UTC (9,973 KB)
来源：arXiv：cs.AI · arxiv.org