In front of me is an optical color sorter, one of dozens of giant machines on the floor of the Lavergne plastic recycling plant in Montreal. At the time of my visit, I don’t know what it is for, let alone how to operate it or clean it. But thanks to a HoloLens 2 augmented reality headset placed in front of my eyes, images appear virtually over the device and tell me what to do to maintain it.
Two virtual arrows point, for example, to the screws to be turned to open the machine casing. In the next step, more arrows pop up to show me where to shoot compressed air. I’m learning how to clean the optical sorter, but I could also have been trained to know how operate it or perform preventive maintenance.
“Our goal is for an employee who has never done a task to be able to put on the headset and do it quickly, without making mistakes,” explains Nicolas Bearzatto, co-founder and general manager of DeepSight, the Montreal company that designed the platform. software used by the augmented reality headset to display instructions.
Another tool for training
The DeepSight software platform, launched in February, comes at a good time, when the training needs of the manufacturing sector are glaring. According to a recent survey by Quebec Manufacturers and Exporters, 98.5% of companies in the sector are short of manpower. And the training of new personnel is often carried out in collaboration with experienced employees, who do not have a minute to lose in their shift and are therefore doubly requisitioned.
To address this problem, DeepSight has developed a suite of software to design instructions without programming, much like making a PowerPoint presentation, then display them on a Microsoft HoloLens 2 headset. At Lavergne, the employee responsible for creating the instructions takes a day to put them together, then tests them with staff the next day and adjusts them based on feedback.
Augmented reality has two great advantages over the paper instructions that are usually offered in factories: it allows you to perform tasks with your hands free and to see precisely where to perform operations.
And it seems to work. The creation of the instructions is not finished at Lavergne, but the Quebec aerospace company Avior, where the DeepSight technology was deployed before its official launch, claims that training time for employees has been reduced by two or three thanks to augmented reality.
Recruits aren’t the only ones benefiting from augmented reality instruction, however. “Sometimes someone with experience can be temporarily transferred to another department, and night workers do not always have a supervisor with them when they have questions”, illustrates Patrick Laviolette, who was a trainer at Lavergne. at the time of passing Newsearlier this winter.
“We are developing a console that will be added to the system to collect data that will help determine, for example, how long tasks are completed and which are the most problematic, which will allow factories to improve their instructions” , notes Nicolas Bearzatto.
Other uses to come
For Yoan Lavergne, director of marketing at Lavergne (a company founded and still run by his father Jean-Luc), training is just the beginning for augmented reality.
“I would like us to buy glasses for each of our large customers, so that we can assist them remotely,” he notes. Currently, Lavergne must often send employees to Asia to help customers use certain machines and the recycled plastic produced by the company. An augmented reality headset allowing you to see what employees on the other side of the world are doing and to guide them could avoid certain trips. “The potential is incredible,” notes Yoan Lavergne. At around $5,000 a helmet, however, the project is on hold until the technology improves and its price drops.
Other expected technological advances may also be useful in the manufacturing sector, such as image recognition. In front of the optical color sorter, the helmet indicates for example where to screw, and asks to click on a virtual button in the air with the hands to signal that the stage is finished. The software will one day be able to ensure itself that the operation has indeed been carried out, which will simplify its use and minimize the risk of error.
“It is possible to train an artificial intelligence model of the kind in a controlled environment to achieve such a result, but currently, the technology does not really allow to do it so that it is accessible in any company. », Specifies Nicolas Bearzatto, adding that DeepSight intends to offer such functionalities in the future.
We would like to give thanks to the writer of this short article for this outstanding web content
Augmented reality arrives in factories
Visit our social media profiles and other related pageshttps://www.ai-magazine.com/related-pages/