AI EMPLOYEE
Industries
INDUSTRIES
Restaurants Cleaning Services Home Service Companies Dental & Orthodontics Fitness & Wellness Hospitality HVAC/Plumbing
Pricing
Partners
PARTNERS
Become a partner Partners Listing
Resources
DEVELOPERS
Agent Creator NEWO BUILDER API & DOCUMENTATION ACADEMY VIDEO TUTORIALS COMMUNITY HELP How to choose AI automation
COMPANY
ABOUT Competitive Advantage CONTACT BLOG INSIGHTS
Call 24/7: +1 (888) 639-6939 free consultations
Book a Demo
Home / Blog / TUM’s New Robot Test Method: How Sensitive Are Our Industrial Helpers?
2 days ago

TUM’s New Robot Test Method: How Sensitive Are Our Industrial Helpers?

img

A Fresh Approach to Robot Sensitivity Testing

In July 2025, researchers at the Technical University of Munich (TUM) introduced a pioneering methodology to measure the sensitivity of industrial robots. This new approach is designed to evaluate how accurately robots can react to contact and mechanical resistance, a critical feature for modern collaborative robots, or “cobots.” Unlike earlier safety tests, which often only measured physical force limits, TUM’s method focuses on tactile responsiveness — essentially, a robot’s ability to feel.

This advancement matters because today’s Non-Human Workers are increasingly working side by side with humans. Whether in automotive plants or logistics centers, these machines must be able to detect when something — or someone — is in their path. TUM’s method provides a standardized way to simulate and test such encounters using realistic conditions.

Why Sensitivity Matters in Industry

The need for more sensitive robots is growing as automation moves from isolated cages into open human workspaces. TUM’s team uses a sensor system mounted on a dummy arm to measure the robot’s reaction time, force distribution, and movement precision when it touches or pushes against an object. This allows engineers to fine-tune the robot’s behavior before real-world deployment.

Such testing is especially relevant for industries deploying Voice AI Agents and AI Employees to operate or collaborate with robotic systems. Safety and adaptability are top priorities, and TUM’s testing method adds an essential tool for ensuring these smart machines can perform safely around people.

Toward Safer and Smarter Robots

The long-term goal of TUM’s research is to establish uniform safety standards and make robot-human collaboration as smooth and safe as possible. Their new testing protocol could soon be adopted internationally, setting a new benchmark for robotic safety assessment. As cobots take on more varied tasks — from assisting in surgeries to packing groceries — their ability to sense and react to touch will be vital.

This initiative not only paves the way for more capable and reliable robots but also supports the development of intelligent digital employees that can learn from physical interaction, adapt, and improve continuously.

Key Highlights:

  • Who: Researchers from Technical University of Munich (TUM)
  • What: Developed a new methodology to test industrial robot sensitivity
  • Why: To ensure safer and more responsive robot-human interaction
  • How: Using sensor-equipped dummy arms to simulate and measure touch
  • Impact: Sets a new standard for robot sensitivity, critical for cobots and AI Employees working near humans

Reference:

https://www.springerprofessional.de/robotics/industrial-robots/tum-develops-test-methodology-for-robot-sensitivity/51249826

Recent Posts See all
TUM’s New Robot Test Method: How Sensitive Are Our Industrial Helpers?
Teaching Robots by Hand: New Interface Simplifies Training for Non-Human Workers
From Sidewalks to Warehouses: Why Cartken Reprogrammed Its Robots
Industries
  • Restaurants
  • Fitness & Wellness
  • Home Services
  • Cleaning Services
  • Dental & Orthodontics
Company
  • Digital Employee
  • About Us
Resources
  • Pricing
  • Documentation
  • Academy
  • Community
  • Partner Program
Contact Us
  • Linkedin
  • Instagram
  • Facebook
  • Email
  • © 2025 Newo.ai
  • Terms
  • Privacy Policy
  • Data Processing Addendum
  • Trust Center