Safer Roads

How To Improve Road Safety And Transport Infrastructure By Using Data?

While data can, and should, be used to enhance traffic safety, there are challenges beyond the technology. We need data in order to make decisions on the effectiveness and efficiency of safety programs, as well as other infrastructure improvements, that are data-driven.

Road safety challenges

Data integration and analysis are critical for understanding traffic safety issues and developing policies that will help to reduce the tens of thousands of deaths and injuries on roads every year.

We are using data to uncover safety challenges and come up with solutions that could save lives. We are looking to emerging technologies to address challenges in transportation, environment, and safety.

Going forward, governments at every level, as well as their private-sector counterparts, will have to revisit data standards, procurement policies, measurement technologies -- and privacy and cybersecurity -- in order to maximize the safety on our roads. The challenge, then, is designing policies that facilitate better data sharing between government, private, and citizen actors. Driving data, and its insights, are there, waiting to be applied to improving city infrastructure and street safety.

We seek to leverage advances in AI, machine learning, vision systems, LIDAR, telematics, and other data sources to provide key insights into road safety, accident characteristics, and the prioritization of investments, to all road users.

Hotspot forecasting, which relies on historic data, predicts where crashes are likely to occur, which allows transportation planners to build preventive solutions, preventing severe injuries and even deaths. Road infrastructure can be adjusted knowing it will immediately have a positive impact on drivers’ behavior, thus saving lives.

Building effective and robust infrastructure systems

Through infrastructure analysis, stakeholders can leverage historic and real-time data to shape effective, robust infrastructure systems.

This kind of smart data-driven transportation solutions is part of the ecosystem approach. If, for instance, the driving data shows that a specific corridor is seeing regular, substantial increases in traffic, resources could effectively be allocated to research the implementation of a new transit proposal. Analyzing aggregated, contextualized driving data could take it one step further, and give insights about collective behaviors, both typical and atypical.

Aggregated and contextualized driving data moves beyond single data points to reveal areas in which driving behaviors cluster, begin, or cease. The effect of those changes can then be tracked over time to see whether there is an improvement in near misses. As demonstrated, aggregating and contextualizing driving behavior data can yield actionable insights into the way that infrastructure is used and perceived.

Our better infrastructure data products catalogue the information and our insights aim at:

·       reducing the work load from road management department,

·       decreasing the amount of human interference and data errors,

·       reducing budgets associated with tagging, and

·       helping improve the road safety.