AI in Robot Vision
With a global market size of almost 34 billion euros and annual growth of 42 % until 2027 (Grand Research), it is no longer possible to imagine industry without AI. Machine Vision in particular benefits from new possibilities and greatly improved image recognition. That is why we rely on this advanced technology.
Different levels help to always develop the right application:
What benefits does AI offer?
- New functions and possibilities in Machine Vision
- Automated quality inspection at every point of the shop floor, going beyond a mere edge and geometry check
- Reliable decisions even with difficult parts
- Higher process speed
- Improved cost effectiveness (AI systems pay for themselves after approx. 2 years at the latest)
- Higher customer satisfaction through increasing product quality
AI use – practical examples
Check friction discs on the conveyor belt
An automotive supplier wanted to carry out the quality inspection of the produced friction discs in-line on a conveyor belt.
An integrated system of vision sensor and AI-supported software now reliably takes over this task. The error detection rate is an outstanding 99.97 %.
Internal and external inspection of joint pins
An automotive supplier was also looking for an automated internal and external inspection of its joint pins. A difficult challenge.
But not impossible: together with an integrator for further object handling, a fully comprehensive system was created that reliably inspects the inside and outside of the shiny metallic parts in two rapid steps using Deep Learning.
Automating petrol injections independently with AI
Another supplier needed a vision solution to independently automate petrol injections step by step.
Consequently, the company not only received an AI automation solution for quality inspection, but also an introduction to teaching new defect types. Thus, the employees can independently and easily expand and adapt the system at any time. In total, the supplier now saves about 1,000 EUR/day.
Handling of transparent syringes
A manufacturer of laboratory equipment was looking for bin picking solution of its transparent syringes. This task could not be solved with object-based handling – the transparency of the parts prevented a successful grasping of the parts.
Together with the integrator of the overall solution, we implemented a vision and software solution for bin picking based on neural networks. This means that even this previously unsolvable task can now be transferred to regular, automated operation.
More about Artificial Intelligence from our blog
Hardly any other topic is as important in research at the moment as artificial intelligence. What sounded like science fiction ten years ago has long since become reality. Robots perform tasks autonomously and adapt to their tasks more and more thanks to various...
Automated quality assurance with MVTec HALCON’s Anomaly Detection – using the food industry as an example
In his capacity as the Technical Product Manager at MVTec Software GmbH, Mario Bohnacker has been responsible for the technical enhancement of the standard machine vision software HALCON. His duties include identifying technologies that are relevant for future...
When we learn a new skill, the neural network of our brain strengthens existing synaptic connections and forms new ones between neurons. The more synapses are generated during the learning process and strengthened by repeated recalling, the better the learning...
More info about AI
Please get in contact with us for additional information. We will get back to you as soon as possible.