Human-Aware Robot Behaviour in Self-Driving Labs
🤖 AI Summary
This work addresses the limited understanding of human intent in current mobile robotic chemists operating in shared human-robot laboratories, which rely solely on basic obstacle detection and consequently suffer from inefficient collaboration and redundant waiting. To overcome this, the study proposes an embodied, AI-driven perception framework that introduces, for the first time, a hierarchical human intention prediction model. By integrating LiDAR-based sensing with behavioral context, the model distinguishes between preparatory gestures and actual equipment usage intentions, enabling a shift from passive avoidance to proactive coordination. This approach significantly enhances task scheduling efficiency in shared experimental environments, reduces idle waiting times, and optimizes the collaborative performance of automated scientific workflows.
Application Category
📝 Abstract
Self-driving laboratories (SDLs) are rapidly transforming research in chemistry and materials science to accelerate new discoveries. Mobile robot chemists (MRCs) play a pivotal role by autonomously navigating the lab to transport samples, effectively connecting synthesis, analysis, and characterisation equipment. The instruments within an SDL are typically designed or retrofitted to be accessed by both human and robotic chemists, ensuring operational flexibility and integration between manual and automated workflows. In many scenarios, human and robotic chemists may need to use the same equipment simultaneously. Currently, MRCs rely on simple LiDAR-based obstruction detection, which forces the robot to passively wait if a human is present. This lack of situational awareness leads to unnecessary delays and inefficient coordination in time-critical automated workflows in human-robot shared labs. To address this, we present an initial study of an embodied, AI-driven perception method that facilitates proactive human-robot interaction in shared-access scenarios. Our method features a hierarchical human intention prediction model that allows the robot to distinguish between preparatory actions (waiting) and transient interactions (accessing the instrument). Our results demonstrate that the proposed approach enhances efficiency by enabling proactive human-robot interaction, streamlining coordination, and potentially increasing the efficiency of autonomous scientific labs.
Problem
Research questions and friction points this paper is trying to address.
human-robot interaction
self-driving laboratories
situational awareness
mobile robot chemists
shared workspace
Innovation
Methods, ideas, or system contributions that make the work stand out.
human-aware robotics
intention prediction
self-driving laboratories
proactive human-robot interaction
embodied AI
🔎 Similar Papers
No similar papers found.
