Labimus: A Simulation and Benchmark for Humanoid Dexterous Manipulation in Chemical Laboratory

2026-06-29

AI Summary

Existing evaluation benchmarks struggle to assess the operational quality and experimental validity of humanoid robots in high-precision chemical tasks. This work introduces the first dexterous manipulation simulation benchmark tailored for organic chemistry laboratories, reproducing over 30 real-world experimental assets and standardized protocols to enable end-to-end closed-loop simulation—from physical manipulation to quantitative measurement. The study proposes a novel evaluation protocol that jointly considers task completion, experimental accuracy, and long-horizon execution, defining six atomic manipulation primitives and a seven-step solid-weighing workflow. It integrates real-to-sim modeling, articulated lab instruments, particle-level powder simulation, and closed-loop reading techniques. Evaluations across diverse layouts and perturbations reveal that while current methods can complete tasks, they consistently fail to meet quantitative precision requirements, exposing a critical gap between task success and experimental compliance and thereby addressing a key void in humanoid robot assessment for scientific laboratories.

Abstract

Laboratory automation has made remarkable progress through robotic platforms and AI-driven scientific reasoning. However, many laboratory operations (e.g., solid--solid transfer) remain inherently dynamic and require real-time adaptation to different materials and experimental conditions. Such precision-critical manipulations are difficult to standardize, motivating the use of humanoid robots with dexterous hands. Despite this opportunity, no existing benchmark evaluates humanoid manipulation in precision-critical laboratory environments. We present Labimus, to our knowledge, the first benchmark for humanoid dexterous manipulation in organic chemistry laboratories. Labimus reconstructs over 30 functionally faithful assets from real organic chemistry workstations through real-to-sim modeling, collectively covering the core operations of routine organic chemistry experiments. The benchmark integrates articulated laboratory instruments, particle-based powder physics, and closed-loop instrument readouts, enabling a complete manipulation-to-measurement pipeline. It further defines six atomic operations and a seven-step solid-weighing workflow derived from real laboratory standard operating procedures. We introduce a precision-aware evaluation protocol designed to jointly measure task completion, experimental precision, and long-horizon execution. We benchmark three representative policies under procedural layouts and environmental perturbations. Results reveal a precision gap: policies that successfully complete laboratory tasks can still fail to satisfy the quantitative tolerances required by experimental protocols. Our benchmark exposes a fundamental disconnect between task completion and experimental validity, providing a new testbed for developing reliable humanoid robots for scientific laboratories.

Problem

• humanoid manipulation
• laboratory automation
• dexterous manipulation
• precision-critical tasks
• benchmark

Innovation

• humanoid dexterous manipulation
• laboratory automation
• real-to-sim modeling
• precision-aware evaluation
• particle-based physics simulation