Introduction
In today’s fast-evolving manufacturing landscape, adopting advanced technologies like artificial intelligence and robotics is essential. For Link Robotics, a robotics startup specializing in AI-based localization and navigation, validating their sensor fusion system was a key step in ensuring their solution could handle real-world industrial challenges.
Thanks to their collaboration with AI-MATTERS and the LMS experts, Link Robotics was able to rigorously test their mapping, navigation, and obstacle avoidance capabilities under realistic scenarios. This partnership helped them confirm performance, identify improvements, and move closer to large-scale deployment. This is their story.
The Challenge
The main challenge for Link Robotics was to validate that their sensor fusion algorithms could maintain centimetre-level localization accuracy and produce stable maps even in dynamic, unstructured environments. Additionally, they needed support in quantifying performance in terms of mapping stability, navigation robustness, and obstacle avoidance efficiency-metrics critical for convincing potential industrial clients of the system’s readiness.
“We wanted to be sure that our robot could handle narrow passages, dynamic obstacles, and other real-life complexities without losing accuracy or safety,” explains Berk Turanli, Co-Founder of Link Robotics.
The Solution
AI-MATTERS and LMS provided Link Robotics with access to testing environments and expertise to evaluate the system under challenging, repeatable conditions. This included obstacle-rich layouts, dynamic movement in the surroundings, and scenarios designed to stress-test the mapping and navigation stack.
“Working with AI-MATTERS gave us the chance to push our system to its limits in a controlled but realistic environment. Their team helped us design tests that truly reflected industrial challenges,” says Berk Turanli.
The Results
The collaboration between AI-MATTERS and Link Robotics delivered tangible outcomes. Some of the key results include:
- Stable, Drift-Free mapping of shopfloor with IoU (Intersection over Union) ≈ 70%
- Navigation success rate ≈ 90%.
- Reliable Obstacle Avoidance in narrow and cluttered passages with aCollision avoidance rate ≈ 90%.
- Centimetre-Level Accuracy Maintained in environments with static and moving obstacles.
- Improved Responsiveness after migration to ROS2 middleware.
“The results gave us the confidence that our system can meet industrial demands without major hardware changes,” adds Berk Turanli.
Looking Ahead
Working with AI-MATTERS has been a pivotal step for Link Robotics moving toward commercial deployment. Moving forward, they plan to expand testing to larger and more complex sites, enhance mapping algorithms to include semantic labeling for more intelligent navigation decisions and integrate multi-robot coordination to assess fleet navigation and mapping in shared workspaces.
“AI-MATTERS has been a real partner in validating our technology and accelerating our readiness for the market,” concludes Berk Turanli.
Conclusion
Link Robotics’ story demonstrates the transformative potential of AI in European manufacturing. By addressing challenges head-on and leveraging the resources of AI-MATTERS, they’ve paved the way for a future of smarter, more efficient operations.
Would you like to know how our project managers can help your organisation?
Contact us for a non-binding conversation: https://ai-matters.eu/contact/
