DISTRIBUTION
capable of lifting heavier and heavier loads - the safety risks also significantly increase. An accidental collision with a human worker or a parcel being dropped onto someone’s head due to a faulty drone could be extremely dangerous, and in some cases, fatal.
Overcoming the engineering challenge While the successful coexistence of drones and robots with humans in warehouses can provide many benefits, it’s also unfortunately a significant engineering challenge. But to overcome this, motion capture technology is playing an increasingly important role in helping cobots to seamlessly integrate within human environments in a safe and secure way. Motion capture - the process of recording
the movement of objects or people - is now being used to improve robot control by tracking drones to analyse the interaction between humans and machines. Having visibility into this data can then be used to better recognise and avoid any potential obstacles, particularly in an environment where people may be moving around the shop floor quickly and erratically. Through the use of motion capture, which
can simultaneously process high volumes of real-time data and deliver fast response
times, drones being used within a warehouse setting can be trained to react almost immediately - helping to avoid contact while maintaining a safe distance from humans at all times. Recent research into human activity
recognition and ergonomics in manufacturing carried by Technische Universität (TU) Dortmund, a leading technical university in Europe, is a great example of how motion capture is being used to improve drone tracking within warehouses. The university used motion capture
technology within its InnovationLab to deliver the visual and data evidence that was vital to guide the team’s understanding of human activity and drone tracking. Through the technology, TU Dortmund was able to improve robot control by tracking drones to analyse the interaction between humans and machines and help the drones to recognise and avoid human obstacles. In one demo carried out by TU Dortmund, a
person dressed in a motion capture suit was able to safely and successfully walk through a flock of 12 drones flying autonomously - showcasing the drones’ ability to react almost immediately and remain at a safe distance to avoid colliding with any obstacles. In addition to motion capture technology,
the university is also using machine learning (ML) to help drones recognise variations, for example, workers carrying boxes. This allows for the development of safety protocols and increases flexibility so drones won’t require a fixed infrastructure to successfully navigate an environment in future. TU Dortmund’s recent work with motion
capture technology has far-reaching implications and benefits for the coexistence of robots and humans in the manufacturing and logistics sector. And, in true open-source spirit, it plans to curate and share the data to make sure other researchers can access and use its findings. Although this research clearly highlights the
value that motion capture data can bring, it also proves the high level of sophistication that’s needed to make the fully autonomous warehouse a reality. While technological advances in cobots are
only set to increase, there’s still work that needs to be done to ensure they can operate safely and seamlessly as possible. As soon as cobots have the ability to work in harmony with humans, warehouse productivity and efficiency levels will increase at an exponential rate - benefiting not only the manufacturers, but brands, and ultimately consumers themselves.
Vicon
www.vicon.com
NOVEMBER 2021 | ELECTRONICS TODAY 9
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46
