17 January 2020

Large industrial robots have thus far worked inisolation, in clearly defined areas without people nearby. A newly presented thesis at LiU, however, shows that such robots can very well work together with
people – and how safety can be ensured.

Varun Gopinath, researcher in robot safety at LiU.
Varun Gopinath, researcher in robot safety at LiU.

Part of the future

The Volvo Torslanda plant in Gothenburg. An operator lifts a plastic panel and attaches it to the lower surface of a vehicle chassis that is slowly moving forwards along the assembly line. Then she screws the panel on, working from below. The complete process is carried out above head height, only takes around a minute, and is repeated countless times during a working day.

The robot lab in the A Building, Linköping University. A large industrial robot in a demonstrator has replaced the operator for the first operation, and lifts the panel to place it under an imagined chassis. The operation requires that the robot has a considerable working range and stable motion, even though the panel is not particularly heavy.

In order to simulate working on an assembly line, the robot moves three metres during the complete assembly process.

The robot itself.

“Automation using robots will be important for industry in the future. Requirements related to ergonomics and the work environment are major factors in driving industry in this direction. Robots can be used as a third hand to help the operator and make her life easier”, says Varun Gopinath, robot researcher and in charge of the workstation at LiU.

All conceivable risks

In his doctoral thesis, On Safe Collaborative Assembly With Large Industrial Robots, he investigates how the collaboration between human and robot can be arranged without jeopardising safety. It is nothing new that small robots, known as collaborative robots, interact with people, but it has until now been seen as too dangerous to allow traditional industrial robots – which can weigh as much as a tonne and have a lifting power of 200 kg – to do the same.

Varun Gopinath, however, is convinced that people can work also in the vicinity of this type of machine, even if the robot have not been designed for collaboration.

Varun Gopinath in the lab.

“We have shown how the concept of safety can be handled, and given examples of how to solve it. But it’s the task of each individual factory to create its own solution, based on the situation. In a car factory, for example, there are many more people at work than in an aircraft factory, which has implications for safety. To put it simply, the system must be designed considering all conceivable risks”, he says.

Must consider visitors

The demonstrator in the robot lab has two zones, one in which humans and machines collaborate, and one in which the operator cannot be reached by the robot. Several sensors are arranged around the collaboration zone to detect when a person is in the vicinity, and to shut down the complete system in the event of an emergency. Fencing is arranged between the collaboration zone and the robot, showing clearly the area into which the operator must not enter.

“It’s important to define clearly the area in which collaboration is to take place. Outside of this area, it should not be necessary for the operator to consider the location or activity of the robot. The system must also consider visitors and others who are in the factory, and who may not know much about robots”, says Varun Gopinath.

The research has been carried out in close collaboration with Volvo and Scania, who were involved with developing an early version of the workstation. Varun Gopinath describes the method as collaborative research in which the demonstrators have played a large part, where both he and the companies have learnt together.

Now all that remains is to dismantle the workstation. The robot can be used in other research projects at LiU.

Translated by George Farrants

Read more

Latest news from LiU

Server room and data on black background.

Machine Psychology – a bridge to general AI

AI that is as intelligent as humans may become possible thanks to psychological learning models, combined with certain types of AI. This is the conclusion of Robert Johansson, who in his dissertation has developed the concept of Machine Psychology.

Research for a sustainable future awarded almost SEK 20 million grant

An unexpected collaboration between materials science and behavioural science. The development of better and more useful services to tackle climate change. Two projects at LiU are to receive support from the Marianne and Marcus Wallenberg Foundation.

Innovative idea for more effective cancer treatments rewarded

Lisa Menacher has been awarded the 2024 Christer Gilén Scholarship in statistics and machine learning for her master’s thesis. She utilised machine learning in an effort to make the selection of cancer treatments more effective.