Smart robotics is key to automation

Thema:
Artifical intelligence

The products we manufacture as a society are becoming more advanced and more diverse. In addition, the associated production processes are becoming more and more complex.At the same time they have to be more and more flexible. This is time-consuming and human brainpower oftencomes up short here. However, we can cope with the complexity and flexibility if we opt to use robotisation and automation in an increasingly intelligent way. This will bring a future-proof industry a big step closer.

At TNO, for example, we are working on AI techniques forautomatic path planning. This allows the make industry to program robots in such a way that they can determine their own route and adjust it when the environment changes. This is especially possible in combination with machine learning. In this way wecreate a flawless production process, which saves time and money.

Automation is efficient and creative

A good example of this is the automation of metalworking. We use robots to do this. These are now manually programmed for each new product, which is time-consuming.

Based on the product knowledge and the work preparation, we are able to automatically generate the required robot paths. This can significantly increase daily production and save the operator a lot of manual program input.

On the design side, model based design optimisation techniques are decisive in order to make optimal decisions within the design space. Likeintelligent design assistance that enables us to make huge strides in the development of 3D printing ortopology optimisation techniques in which free form designs are created that a human designer couldn't imagine.

Automating the programming process

A lot of time and effort is needed to manually program robots. TNO wants to get this as close to zero as possible. To do this, we use:

  • All the available information of the product itself
  • The machining steps as defined in the operating instructions
  • A 3D environment model of the robot plus machine tools.

In this environment, intelligent path planners program the optimal automation process. Each separate part of that process is merged into a complete robot program. This is programmed almost automatically. This saves time and therefore leads to more productivity.

Get inspired

20 resultaten, getoond 1 t/m 5

Responsible decision-making between people and machines

Informatietype:
Article

Bias in facial recognition and accidents with self-driving cars. AI must be developed further. The fastest way to do this is in close cooperation with people.

Knowledge representation and reasoning

Informatietype:
Article

Correct and unambiguous information is needed when making a decision. That is why we use AI technology called "knowledge representation & reasoning".

Natural language processing

Informatietype:
Article

What is natural language processing (NLP) and how do we use it intelligently? Find out how we use this AI technique to gather information from textual data.

Fair machine learning

Informatietype:
Article

Fair machine learning is relevant to all kinds of discrimination and bias arising from the use of biased data. Read more!

Deep vision

Informatietype:
Article

Through Deep Vision, we’re developing AI algorithms to make automatic image analysis possible. Learn more!