Behaviour AI, a new behavioural artificial intelligence (AI) system from Humanising Autonomy, claims to possess the ability to predict pedestrian’s actions and road users to prevent more than 90% of crashes.

Currently available as a dashcam after-fit solution, Humanising Autonomy hopes it will be offered as standard fit within the next two to three years, linked to advanced driver-assistance systems (ADAS). Talks with several manufacturers have already begun concerning this.

Behaviour AI predicts what other road users will do and alerts the driver, also providing fleets with data about any near miss (as well as any incident), assisting driver training.

Co-founder and chief product officer Leslie Nooteboom claims Behaviour AI can detect objects up to 80 metres ahead at 40mph, twice the distance of the industry standard, with 99% accuracy.

“It’s not just recognition; it predicts if they are going to cross the road or where they are moving to on the road…Our data shows that the system can predict two seconds before the driver realises what is happening and send them an alert.

“It is also continuously learning and not just from one driver, from the entire fleet because all the data sits within our management system. We believe it can prevent around 92% of accidents”.

The system is frequently updated to take account of new forms of mobility, such as e-scooters.

Nooteboom explains: “They (e-scooters) were a problem because they (riders) weren’t moving their limbs, but they were moving fast. So, we had to adapt the model to detect e-scooters.

“This is where we add intelligence to the system so it machine learns and applies that to the real world. It doesn’t just learn from the data we give it; it’s an interpretable AI approach. We can see how it’s making decisions, so we know how sure it is about making those decisions. Then we know what we need to do to make it even better, which we do with over-the-air updates.”

The system has been installed on Arriva buses in London for more than a year. Further trials, made possible through Humanising Autonomy’s partnership with FreightLab, have begun with a van-based fleet operator, Transport for London (TfL), and 10 industry partners including Royal Mail, DPD, UPS, and John Lewis Partnership.

Humanising Autonomy is already playing a part in improving the safety of passengers and staff at public transport interchanges through a partnership with Transport for Greater Manchester (TfGM).

The company’s behavioural video analytics software was deployed last year to help TfGM understand social distancing issues, assess how passenger behaviour is affected by the Covid-19 pandemic, and make temporary infrastructure changes.

Humanising Autonomy has its own data to support claims about accident reductions but in the next six months will have analysed copious amounts of real fleet data to provide ‘robust proof’ including using near-miss data for driver training.

Nooteboom says: “We take the video of the near miss and extract information on the risk level for driver education, even where there was no accident… We also provide the information for the insurance company so they can understand the lead up to the accident.