Vision in Motion: Real-World Validation of Vision-Based Robotics by LMS & RobotAI
Technology Being Tested
Vision-Based Robot Grasping Solution – A flexible, AI-powered software system enabling robotic arms to identify, locate, and manipulate specific parts on a moving conveyor in real time. The solution was aimed at optimizing robotic car assembly without manual intervention.
Use case in a Nutshell
LMS (Laboratory for Manufacturing Systems & Automation, University of Patras), technology owner, and RobotAI, early adopter, partnered through the DIMOFAC Early Adopters Programme to validate a vision-based robotic assembly system. LMS provided the testbed and integration platform, while RobotAI delivered its real-time object detection and grasping software. The seamless collaboration allowed both partners to validate and demonstrate a technology with strong potential for industrial automation.
About the collaboration partners
The Laboratory for Manufacturing Systems & Automation Department of Mechanical Engineering and Aeronautics (LMS) at the University of Patras has implemented close-to-market services to external companies within the framework of the DIMOFAC project.
RobotAI is a company that specializes in developing software for integrators or robot automation providers. It was one of the beneficiaries of the programme hosted by LMS Pilot 10 ‘Flexible Processing and Assembly Robotic Framework’.
Description of the Collaboration
Problem Addressed
Enhancing robotic car assembly by enabling robots to detect and locate parts on a conveyor belt without manual assistance.
Solution
RobotAI’s AI-driven vision system was integrated with LMS’s robotic setup, allowing for real-time part identification and manipulation.
Execution
The implementation was swift and collaborative. LMS facilitated connectivity with vision cameras and robot systems. Minimal integration challenges were reported due to the flexibility of RobotAI’s software.
Host Role (LMS)
Offered the robotic platform, conducted meticulous integration, and provided continuous feedback.
Beneficiary Role (RobotAI)
Supplied the object recognition software, tuned the system for the industrial environment, and validated performance.
Results of the Colaborration
Successful Deployment
RobotAI’s solution operated effectively in a live manufacturing-like environment, confirming its industrial readiness.
Operational Efficiency
The combined solution enabled accurate and fast part detection, supporting seamless robotic assembly.
Innovation Boost
LMS was able to advance their machine learning-based robot grasping solution, while RobotAI achieve validation in real-world conditions.
Minimal Challenges
LMS spent time fine-tuning the vision calibration and ensuring reliable communication between system components. However, overall integration was reported as smooth.
Business Impact
Although immediate commercial gains were not quantifiable, the collaboration opened new use cases and fostered deeper R&D capabilities for RobotAI.
Testimonials
The collaboration with DIMOFAC provided us with valuable opportunities to test and integrate advanced technologies into our operations
Our collaboration with the beneficiaries was seamless, from discussions with directors to hands-on testing with operators. Their engagement provided invaluable feedback.
Project info:
The use case DIMOFAC project which received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 870092, aiming to help factories implement a smart factory architecture that will allow them to be more reactive to a personalised demand and changing market dynamics.
Do you want to create a use case for your technology or test this technology in your processes?