LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints
Abstract
LIBERO-Industry introduces a benchmark translating industrial manufacturing constraints into controllable robot learning tasks to evaluate generalist policies under realistic production conditions.
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.
Community
Are embodied AI models ready for the factory floor?
Flexible manufacturing requires robots to adapt to changing products and production conditions. Yet today’s general-purpose embodied models still struggle when action failures and execution errors accumulate.
We introduce LIBERO-Industry, a benchmark that turns four common production-line challenges into controllable test conditions: moving material flows, variation in product geometry, strict cycle times, and tight spatial tolerances. Across simulation and a physical conveyor-belt workcell, we evaluate models on industrial loading, unloading, and material-transfer tasks.
💡 What we found: In simulation, policy performance declined progressively as the constraints were introduced and combined. In real-world experiments, the LIBERO-Industry co-training condition achieved higher observed target-transfer completion than the original-LIBERO condition.
Ultimately, LIBERO-Industry aims to make industrial readiness a measurable research target for embodied AI.
Get this paper in your agent:
hf papers read 2610.16782 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper