Designing the factory of the future with humans and robots

How can humans and robots work together safely and efficiently in tomorrow’s factories? Through VF-KDO, the University of Skövde and Volvo Group have used virtual simulation and multi-objective optimisation to explore the possibilities.

“Long before we started VF-KDO, we had already observed that industrial companies are highly interested in extracting knowledge, from their data to support better decision-making.”

For Amos Ng, Professor of Automation Engineering at the University of Skövde and project leader of VF-KDO, the research profile has been about going beyond data from existing production systems.

“However, many overlook that more valuable insight can often only be obtained by running optimization on virtual factory models at different levels rather than relying solely on data from real factories.”

This approach has been particularly valuable when investigating complex production systems where several objectives need to be considered at the same time.

Finding the right balance

“In my research, I used to work with different objectives to optimize, and the same kind of information happened or the same kind of problems currently happen in industry,” says Carlos Alberto Barrera Diaz, Business Strategy Manager at Volvo Group’s Skövde Plant.

“So, most of the problems that we have are not single objectives, so they rather look at different things to improve.”

Carlos Alberto Barrera Diaz, Business Strategy Manager at Volvo Group’s Skövde Plant.

In a real industrial environment, improving one aspect can affect another. Sustainability, for example, involves several considerations at once.

“If we take, as an example, sustainability, we want to optimize energy, reduce costs, improve material handling and improve throughput,” says Barrera Diaz.

The challenge is therefore not necessarily to find one perfect solution, but to understand the trade-offs between different alternatives.

“So, my research was applied to find the best trade-off among all these different objectives, and that's actually what happens in reality in industrial cases. You need to make compromises and find what is best for each specific moment.”

When humans and robots work together

Within VF-KDO, this way of thinking has been applied to human-robot collaboration. The University of Skövde and Volvo have worked on robotic systems where humans and robots can work together.

Anna Syberfeldt, Professor of Production Engineering at the University of Skövde.

“Together with Volvo, we have developed the next generation of industrial robotic systems with a special focus on human-robot collaboration, which means that we have developed cobots, robots that can successfully work together with humans,” says Anna Syberfeldt, Professor of Production Engineering at the University of Skövde.

The virtual approach makes it possible to investigate a solution before testing it in a real production environment.

“We have used a virtual approach for this, where we have tested everything virtually before we have tested it in reality.”

Testing the factory of the future virtually

For Volvo, the flexibility of such systems is becoming increasingly important as production requirements change.

Atieh Hanna, Researcher in the Trucks Technology & Industrial division at Volvo Group.

“Fully automated assembly systems tend to lack the flexibility required for Volvo's future production needs, where product variation and the amount of material handled are increasing,” says Atieh Hanna, Researcher in the Trucks Technology & Industrial division at Volvo Group.

“Collaborative setups between humans and robots present an opportunity to address these challenges by leveraging the strengths of both robotic accuracy and consistency together with human adaptability and problem-solving.”

At Volvo’s Future Factory Lab at CampX, the researchers are now bringing several factors into the same simulation.

“Together with the University of Skövde, we are investigating how multidisciplinary simulation combined with multi-objective optimization can support this applied to a use case at our Future Factory Lab in CampX.”

The approach considers robot speed, safety, productivity, ergonomics and energy efficiency simultaneously. The aim is not simply to optimise a technical system, but to support decisions that can be understood and justified.

“The methods emerging from VF-KDO aim to support more transparent and knowledge-based decision-making,” says Hanna.

And in a factory where humans and robots work side by side, that transparency matters.

“They can give us possibilities to better explain and justify design choices for collaborative workstations to operators and safety stakeholders.”