Safety First: Using vehicle data to make us all better drivers

Vehicle data is invaluable in improving the safety & safe operation of vehicles for their occupants & other drivers. The next gen of vehicles will use real-time analysis to make driving even safer.

Monica McDonnell
Monica McDonnell
2022년 12월 15일 4 최소 읽기
Using vehicle data to make us all better drivers

In previous blogs I’ve highlighted the ways in which integrating vehicle data can transform every aspect of the vehicle ownership lifecycle. From personalising the dealer experience, to offering tailored in-car experiences, vehicle data helps identify what people actually do, rather than what they say or think they do. This data is also invaluable in improving the safety and the safe operation of vehicles for their occupants and other road users. Leading manufacturers are already incorporating features that periodically remind drivers to take breaks, warn them of potential hazards, and in some cases intervene to prevent incidents. But the next generation of vehicles will use real-time analysis of data from a range of sensors to radically improve the range and effectiveness of these safety features.

Capturing, integrating and analysing data from vehicle sensors can very quickly establish an individual’s driving style. Noting how you accelerate and brake, use of indicators and speed when cornering, average length of trip, even routes chosen can all help create a picture of the normal behaviour of a driver. Other factors such as the presence of mobile phones in the vehicle can also be considered. Sophisticated analysis can also discern between different regular drivers of the same vehicle.

Using this data to create a set of standard driving patterns for a specific vehicle and set of drivers then provides a benchmark against which real-time data from an ongoing journey can be measured. Deviations from the expected standard patterns can be used to infer behaviours and potential root causes that in turn could initiate automatic interventions.

For example, driving faster and accelerating more aggressively than normal or, alternatively lane wandering and slower reactions could trigger automated in-car alerts to advise the driver to slow-down, or stop and take a break. These targeted interventions, based on actual current driving style are likely to be more effective.  Current interval based ‘reminders’ that are not related to the way you are driving at that moment are easy to ignore.  Interventions which have anticipated unusual behaviour are more likely to gain attention and adjust behaviour. 

If the non-standard driving style continues or becomes dangerous, more definitive interventions could be triggered – for example speed limitations or even, ultimately, bringing the vehicle to a safe stop. New safety and security solutions could be created. For example, a non-standard driving style, combined with non-presence of usual registered mobile devices, and unusual routes could indicate a stolen vehicle. This could initiate messages to both the owner’s mobile device and the vehicle requesting confirmation of driver or alerting them to unauthorised use. 

If these uses of data seem far-fetched then you only need to look to financial services to see proof of this concept in action. PayPal, for example, uses the 27 million transactions it processes every day, to build a picture of each customer’s typical online payment behaviour. It uses this data to provide implicit verification of individuals to speed them through checkouts without compromising security. 

Similarly, a retail bank uses Teradata to track the online habits of its customers, and then compare that standard behaviour to their current online banking transactions. Any discrepancies between expected and actual behaviour raise a flag of potential fraud. This automatically initiates additional authentication procedures that the customer must complete before the transaction is allowed. Persistent egregious behaviour automatically terminates the online banking session.

The more data collected and integrated from diverse sources, the more accurate and effective these automated processes are. The same is true in the automotive space. Combining data from the wide range of sensors in vehicles, with customer information and external data sets ranging from GPS data to time of day and weather for example, improves the potential uses and quality of new safety measures. The more information can be analysed and the better behaviours inferred, the more powerful, useful and tailored these services can become. 

Not all drivers will want these interventions, some may want some just some of the time. Opt-ins will certainly be necessary for some of the scenarios described but collecting and integrating vehicle data will doubtlessly play a significant role in improving the safe operation of tomorrow’s vehicles. 

Combining granular, diverse data at scale and making it available for analysis in real time is the foundation of all the use cases I have described in my blogs. I see leading automotive manufacturers already starting to create the data fabrics that allow them to underpin personalised experiences. Whilst the starting point for personalised experiences is typically the web site, many are seeing the value through opportunities for new and enhanced services at every point in the vehicle and customer lifecycle. 

If you are interested in how integrating vehicle data can enhance your operations, please get in touch


약 Monica McDonnell

Monica McDonnell is a highly experienced consultant in the field of enterprise software, digital transformation and analytics. Her career has spanned Africa, the US and Europe with time spent on ERP and supply chain planning before focusing on delivering value from data. Monica advises on how to deliver business value by combining good data governance and advanced analytics technologies. Helping automotive companies understand how to release the full potential of Industry 4.0 technologies, and dramatically improve customer experience management as enabled by the connected vehicle is central to her role. Monica earned a BSc in Industrial Engineering from the University of Witwatersrand, and a MSc in Software Engineering from Oxford University. 

모든 게시물 보기Monica McDonnell

알고 있어

테라데이트의 블로그를 구독하여 주간 통찰력을 얻을 수 있습니다

I consent that Teradata Corporation, as provider of this website, may occasionally send me Teradata Marketing Communications emails with information regarding products, data analytics, and event and webinar invitations. I understand that I may unsubscribe at any time by following the unsubscribe link at the bottom of any email I receive.

Your privacy is important. Your personal information will be collected, stored, and processed in accordance with the Teradata Global Privacy Policy.