By Tim Massey, Product Manager, Vicon
Manufacturing, warehousing and logistics are perhaps the three sectors where automation and robotics have the greatest potential to realise new efficiencies. In recent years, we have seen the rise of ever greater digitalisation of warehouses and factories, and the implementation of sophisticated warehouse management systems. Of course, the ultimate dream is to create the ‘autonomous warehouse’ – where processes are as streamlined and efficient as possible to serve an ever-growing demand for seamless logistics and virtually instantaneous deliveries.
And this isn’t empty talk. Brands like Amazon have talked extensively about the potential for drones to better serve the ever-growing market for small-scale shipments and shorter delivery deadlines, and operate highly automated warehouse facilities with a large amount of stock movements.
Robots are crucial to this vision. While already a common sight in warehouses, there is a need for a new generation of more collaborative robots – cobots – that are able to work more closely alongside real people. However, as robots and humans come into ever closer contact in warehouses, so the importance of the need for safe interactions escalates.
The question is, how can we guarantee the humans’ safety without stunting the efficiency gains that cobots offer?
The rise of the cobot
Traditionally, industrial and warehouse robots have operated in caged off-environments, away from humans. But with cobots, we are removing those cages and putting robots in spaces, directly alongside their human counterparts.
To date, cobots have typically been small and have used force sensors, machine vision and other sensing technologies to avoid striking humans. Moreover, the machines could be easily shut off in the event of accidental collisions. These are all sensible and obvious safety precautions that have served to help the expansion of the use of cobots.
With the success of these early cobots, so there is demand for them to take on more complex or heavyweight manufacturing, logistics and material handling tasks. This in turn means there is growing demand for higher-speed or heavier-duty — and therefore potentially more dangerous — cobots.
Drones are a useful example of this trend. The attraction of drones to warehouse managers is obvious – while the ‘airspace’ in a warehouse is currently empty, drones can turn this ‘wasted’ space into stacked productive areas where more packages and products can be picked and transported, while using a smaller footprint.
But as more drones are added to a warehouse space, and more drones become capable of lifting heavier and heavier loads, the risks also increase. Already, a collision between a human warehouse worker and a drone, or a parcel dropped on someone’s head by a faulty drone, could easily be fatal.
Taking on the engineering challenge
As you can see, the successful coexistence of drones and robots with people in warehouses is a significant engineering challenge. In response to this challenge, motion capture technology is playing a crucial part in helping cobots fit seamlessly into human environments.
Motion capture can improve robot control by tracking drones in dummy warehouse environments, analysing the interaction between humans and machines. Having this visual data can then be used to help the drones better recognise and avoid obstacles, particularly the quick and sometimes erratic movement of people. Machine learning can also be applied to help cobots recognise variations, such as people carrying boxes.
This data can be used as a reference system – enabling the development of safety protocols, monitoring sensor performance, and improving positional placement of cobots. Ultimately, the goal is to facilitate the decision-making process of cobots so in the future, they won’t require fixed infrastructures to navigate an environment.
An example of this research is the work done by Technische Universität (TU) Dortmund, one of the leading technical universities in Europe. In one of TU Dortmund’s stand-out demos, a person in a motion capture suit can walk through a swarm of 12 drones flying autonomously. This showcases the drones’ ability to react almost instantaneously, avoiding contact and keeping a minimum prescribed distance away.
TU Dortmund’s work with cutting-edge motion capture technology has far-reaching implications and benefits for the coexistence of robots and humans in the manufacturing and logistics industry. 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.
While this sort of research demonstrates the value that motion capture data can have, it also highlights the level of sophistication that will be required to make the ‘autonomous warehouse’ a reality.
While cobots are undoubtedly here to stay, there is much work to be done to make their operation as frictionless as possible. But once cobots are working in harmony with their human counterparts, the efficiency and outputs of warehouses can potentially skyrocket – delivering benefits for manufacturers, brands, and ultimately consumers themselves.
Tim Massey is a Product Manager at Vicon, an award-winning, leading provider of tailored motion capture systems for the life sciences, media and entertainment, location-based virtual reality and engineering industries. Tim has worked in manufacturing, supply chain and technology for 10 years, and holds an MBA from Harvard University and a Master’s degree in engineering from The University of Durham. Formally at Microsoft working on various operational technology projects, Tim joined Vicon as the Product Manager for Engineering & VR at the beginning of 2019.