Skip to content
Log in

Author

Xiaobo Li

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Aug 2026

Multi-task scheduling of self-driving laboratories under scientific constraints

Self-driving laboratories (SDLs) integrate automation, robotics, and artificial intelligence to autonomously execute scientific experiments. As SDLs evolve toward concurrent multi-task execution and support for heterogeneous experiments, experimental scheduling becomes a critical decision-making layer, determining the temporal order and execution timing of operations under strict scientific constraints, including operation precedence, station allocation, batch processing, experimental parameters, and critically, time synchronization between consecutive operations. For example, in inorganic synthesis, temporal deviations during nucleation can fundamentally alter material properties. While SDLs offer a promising route toward accelerated discovery, the absence of explicit scheduling for concurrent experiments leads to resource conflicts and uncontrolled interruptions. These deviations undermine the reproducibility and data quality essential for artificial intelligence modeling. Here, we present a multi-task scheduling algorithm that jointly accounts for scientific constraints. We integrated this algorithm into an SDL using a closed-loop communication architecture that enables tight coordination between scheduling and robotic experiment execution. The algorithm was validated through the concurrent multi-task synthesis of gold nanoparticles and metal–organic frameworks, distinct chemical reactions governed by nucleation and growth kinetics. By synchronizing robotic operations with experimental stations as well as chemical workflow, the algorithm preserves chemical fidelity and ensures consistent material quality across concurrent multi-task executions, unattainable with a conventional scheduling algorithm that does not adequately account for scientific constraints. This paradigm establishes a practical scheduling framework for concurrent multitasking in SDLs, ensuring the experimental consistency required to generate the high-fidelity datasets foundational to autonomous, AI-driven scientific discovery.

Junyi Zhou, Luyao Ge, Xiaobo Li et al. · 0 citations
Jun 2026

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

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.

Yuhan Wu, Zhao Jin, Tao Li et al. · 1 citation