Responding is Kim Vigilia, vice president, strategy, Humanising Autonomy, London.

Artificial intelligence has emerged as a powerful tool for scaling productivity and spotting anomalies in large data sets. How does this translate and apply to the dynamic environment found within the health and safety sector? Here’s how AI can positively impact health and safety practices and help address some of the biggest hazards to workers within manufacturing, construction, industrial and logistics.

Actionable detection of slips, trips and falls

According to the Royal Society for the Prevention of Accidents, slips, trips and falls are the most commonly reported injury in the workplace. On average, they cause 40% of all reported major injuries and cost employers more than $604 million annually – with many more unreported.

Computer-vision software using advanced behavior AI – an AI system that directly interacts with humans to understand human behavior for further decision-making – gives cameras the power of sight with added context, an important tool that can be used to help prevent and predict slips, trips and falls.

By using behavior AI and tapping into existing video feeds such as closed-circuit TV or infrastructure cameras, employers can see when and where workers have fallen; decipher the difference between a slip, trip or a deliberate bend forward; and understand the context of the situation – for instance, in cases of crowding, uneven material on the ground or if someone was distracted. This enables organizations to make the right changes to their environments to prevent future incidents – all at a low cost.

Flag insufficient PPE gear

Organizations can use AI to flag employees wearing insufficient or incorrect personal protective equipment and help prevent them from entering a hazardous environment without the proper protection. Computer-vision software can detect and match items, while more advanced AI can pick up on more detailed information, such as ill-fitting PPE.

This technology could also help address the difficulties women face with poorly designed PPE, by measuring statistics and capturing data on the number of times employees enter a construction site with improperly fitted PPE. This will give employers data-based insights on which to enact change without requiring workers to report or submit complaints.

Prevent struck-by injuries

According to OSHA, “Approximately 75% of struck-by fatalities involve heavy equipment such as trucks or cranes, with 1 in 4 ‘struck by vehicle’ deaths involving construction workers, more than any other occupation.” AI can help prevent struck-by injuries in two ways:

• Organizations using semi- or fully automated machinery can install dashcams with built-in behavior AI models, which can predict a person’s intent to cross in front of a vehicle so the vehicle’s driver can be alerted to a potential crash.
• AI can help map optimal route options for humans in the workplace, through a historical analysis of current worksites and the directional pathways of every moving object in the space. Further, the more flexible behavior AI pre-maps zones of interest and tracks humans’ physical behavior.

Enable and automate better incident reporting

According to the Survey of Occupational Injuries and Illnesses, 69% of incidents go unreported, making it difficult for employers to make larger health and safety decisions to better protect their employees. When using behavior AI, incident reporting is made easier, as there would be video footage to go along with the report, or it could be automatically flagged for the employer.

Conclusion

AI can be used on its own as a technology or in tandem with edge computing, sensors, cameras or on the cloud. Its flexibility means it can support a larger system or be the main algorithm in a process.

Like with any technology adoption, health and safety leaders should clarify the key objectives they need to achieve, including specific and tangible metrics. They should also have clarity on how easy – or difficult – it is to integrate within their current systems or if an entire new infrastructure is required.

Finally, leaders must understand how usable, transparent, or explainable and ethical the AI model is designed to be. If the algorithm ends up perpetuating unfair bias, or incorrectly triggers inappropriate automations, then it will be costly to backtrack and fix. It’s better to have this clarity and understanding of how the AI system is meant to work at the beginning to ensure complete success in the long run.

Editor's note: This article represents the independent views of the author and should not be considered a National Safety Council endorsement.