FHS-OCT23-PG34+35_Layout 1 13/10/2023 11:59 Page 34


health & safety


spaces, often with operators who are relatively inexperienced – makes them a leading cause of injuries at work. People being struck by a moving vehicle remains one of the top three causes of work-related fatalities in the Uk (hse, 2023) and reports on the health & safety executive website evidence the life-changing injuries caused by collisions with forklift trucks. But what if technology already exists that


a means this type of collision is entirely avoidable?


SEnSOr and taG SyStEmS My personal mission to prevent plant hitting people dates back to the early 2000s, when a friend was fatally crushed by an excavator on a construction site. i decided to investigate how we could harness new technology to prevent this ever happening again and, with a colleague, invented the Uk’s first rfid (radio-frequency identification) safety system. this uses electromagnetic fields to identify and track tags – if someone wearing a tag gets too close to a piece of machinery, the tag vibrates and an alarm goes off to warn the plant operator. this sensor and tag system was a step forward


in safety and is widely used in the manufacturing sector. however, it is far from infallible. it relies on everyone wearing tags – difficult to achieve when there are regular visitors, including delivery drivers, to a factory. Moreover, the rfid signal bounces off metal as well as off the tags, creating lots of false alerts in an environment crowded with racking and machinery.


aI fOr COllISIOn avOIdanCE seeking a more reliable solution, we drew inspiration from the automotive industry’s successful use of ai for collision avoidance. could we adapt this technology to reduce the risk of workplace collisions? after ten years’ research, development and


testing, we came up with a camera-based collision avoidance system that uses ai to detect the human form, filtering out all other objects and acting as a third eye to alert the operator when people enter the danger zone of moving plant. three key elements make up the technology:


the ai core unit, hd cameras, and the operator interface. the system, known as safety shield, is installed onto the plant and adjustable detection zones are set, as appropriate for the working environment. visual and audible alerts go off in the cab if a person enters the vehicle’s amber (outer) zone or red (inner) zone, at which point a collision is imminent.


frOm COnStruCtIOn tO thE faCtOry designed primarily for use in the construction sector, the safety shield ai collision avoidance system has already been fitted to over 5,000 items of plant on sites across the Uk – with zero


t first sight unintimidating, forklift trucks are widely recognised as one of the most dangerous vehicles when it comes to workplace collisions. their use around pedestrians – in confined


ai collision avoidance: a new vehicle for forklift safety


collisions. we’re now finding that it can be similarly effective on forklift trucks in factories. although at first sight the challenges of a


factory’s indoor environment seem very different to those of a construction site, the principles underlying collision avoidance are identical. forklift truck operators have clear visibility


around the cab, but not always in front of them when they are carrying a load. accidents often occur when people walk out from behind racking, or when a pallet on the front of a forklift impairs visibility. By installing the ai system on a forklift, with one camera on the rear and one on the front, an instant alert can be sent to the operator if someone walks into their vehicle’s amber or red zone. the addition of autonomous braking – auto


stop if a person enters the red zone and the operator hasn’t responded – effectively eliminates the risk of colliding with someone. crucially in the factory environment, this automatic braking is carefully controlled to ensure that if the forklift is carrying a load it remains firmly in place on the carriage. the ai technology is linked to a cloud-based


monitoring system. whenever an alert is triggered from a forklift on the shop floor, information is sent to a data centre. this keeps a record of alerts, video footage of incidents, driver behaviour and the vehicle’s location. analysing the data enables the identification of safety trends and the prediction of incidents, informing any changes needed to pedestrian walkways, the positioning of barriers, the placement of racking, staff training, and so on.


EffICIEnCy and prOduCtIvIty results from the construction sector show that within a week of installing the ai collision avoidance system and delivering a toolbox talk to


By Jonathan Guest, CEO, Safety Shield Group


staff, there has been a reduction of at least 50 per cent in red zone incursions on site. this effect builds over time, as companies respond to issues highlighted through data to change behaviour and reduce the risk of collision still further. clearly, the most important outcome of all


this is increased safety – fewer individuals and families facing the devastation of a workplace accident. however, organisations are also seeing marked benefits in relation to productivity. fewer safety incidents means reduced downtime for investigations and claims. data that improves site layout has an impact on efficiency as well as safety. improvements in day-to-day behaviour create a more focused, confident workforce. ai may seem a daunting prospect, but as


applications like this show, when used effectively in the workplace it can be remarkably straightforward in its immediate, life-changing impact. exciting times lie ahead for organisations ready to embrace its potential.


Safety Shield Global www.safetyshieldglobal.com


34 octoBer 2023 | factory&handlinGsolUtions


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