spaces underneath the seats, which is one area where many items of waste get stuck.


Some of those spaces measure just 28cm in height, with the entry points being as narrow as 31cm. That makes it difficult for cleaners to get to the rubbish and soaks up a lot of their time, which has a knock-on effect for the wider train timetables.


Some of our early work also focused on the shape of the robots themselves. What was going to be the most efficient design, so that the machines could work alongside humans in the railway carriages?


We looked at one design that used a vacuum-powered arm, similar to the type utilised in manufacturing plants, while another was based on the dustpan and brush used in domestic cleaning, and a third was based on a conveyor belt. Although the conveyor belt design proved to be the most practical because it could operate without additional tools, we opted for a brush-based collection mechanism because a brushed system was considered to be more effective to collect waste in the confined under-seat area.


Bringing machine learning into play


Our next step was to teach our robots how to spot litter. We showed the machines more than 58,300 studio images of waste in a wide variety of conditions so that they could start to recognise rubbish, along with photographs taken of real- life waste inside carriages.


That’s involved a lot of behind-the-scenes work to get the components correct inside the robots’ ‘brain’. Over the past year, we’ve spent a lot of time further developing the complex system of micro-computers that allows the robot to identify waste. It’s been time well spent: our robots can now detect rubbish on their own and move towards it.


Part of that success has come through what we call ‘machine learning’. That means the robots’ software can look at past data – like all those pictures of dirty coffee cups that we showed to it – and then make a more accurate prediction about whether the item in front of it is a piece of rubbish or not, all without having been specifically programmed to do so.


This allows robots to be flexible, like humans. As they encounter new situations – such as a new packaging


www.tomorrowscleaning.com


design or a different kind of waste lying on the floor – they'll be able to make assumptions based on their previous learning to help accommodate such new challenges.


Moving into a new home for the robots


It’s not been without bumps in the road though. Our project has been hit by supply chain issues and the global shortage in silicon chips, which is affecting everything from car production to domestic appliances.


However, we’ve been able to use another clever piece of kit to help overcome some of those problems. We’ve used some of the three-dimensional (3D) printers at Heriot-Watt University to make some of the components we need, reducing the wait times associated with global freight, as well as helping us adapt to the temporarily reduced global supply chain.


So far, we’ve been developing our robots in our existing laboratories at Heriot-Watt University but, come autumn of this year, we’ll have a new home. The National Robotarium is a partnership between Heriot-Watt University and the University of Edinburgh. It combines Heriot-Watt’s engineering heritage and strengths in robotics for hazardous environments, manufacturing, healthcare, and human-robot interaction with the University of Edinburgh’s expertise in space, construction, and humanoid robotics. Our dedicated new building is now almost finished, and it’ll give us special facilities in which we can develop and test our robots.


Before coronavirus struck, more than 1.7bn journeys were being made on the UK’s railways each year, with the total starting to climb again from 388m through the depths of the pandemic to 990m during the past year. That illustrates just how much the British public relies on its train services and the hard work of the cleaners who keep the carriages on the move.


Creating these robots will give members of staff an extra tool to help maintain the cleanliness of their carriages, as well as protecting them from some of the dirtiest and most hazardous tasks, plus saving their knees and their backs from long-term damage. The days of finding a stray empty coffee cup underneath your train seat may well be numbered.


TECHNOLOGY | 47


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  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68