Humanoid Robots for Cleaning and Sterilization of Medical Equipment (HERCULES)

This project develops AI-driven humanoid robot automation for hospital sterilization departments (CSSDs). Combining robotic foundation models with environment-aware whole-body control, we enable autonomous handling of surgical instruments and sterile containers, validated with pilots in hospitals.

Key data

Description

European hospitals face a documented shortage of 1.2 million healthcare workers, with Central Sterile Supply Departments (CSSDs) particularly affected. CSSD staff perform physically demanding, repetitive tasks: handling heavy containers, sorting thousands of surgical instruments daily in contamination-prone environments. Current automation (conveyors, AGVs) cannot perform the dexterous manipulation these workflows require.

This project develops an AI-enabled humanoid robot system for CSSD automation, deploying the Unitree G1 platform within Belimed's medical equipment ecosystem. We introduce three innovations:

environment-adaptive whole-body control that dynamically adjusts robot configuration based on workspace perception, enabling safe operation in cluttered spaces;
a modular agentic architecture using the Model Context Protocol to orchestrate vision-language-action models, reinforcement learning policies, and navigation; and
robot-equipment co-design, collaborating with Belimed to adapt equipment for more reliable autonomous operation.

Two use cases drive validation: automated container handling in unclean areas and surgical instrument tray assembly in clean areas.