Compass' unique data insights have been used by researchers and universities around the world.
Browse published research papers which study and use our data.
2026
Mihaita A. S., Cheung C., Grigorev A., Mao T., Lillo-Trynes D.
Road safety monitoring has historically been reactive, relying on crash-record analysis after fatalities and injuries have already occurred. Proactive identification of high-risk locations and dangerous driving behaviour before incidents occur is a critical but underexplored challenge. This paper addresses this gap using connected vehicle telemetry data from Greater Sydney, Australia, to detect and forecast near-miss risky driving events at the Local Government Area (LGA) level.
2026
Wijayaratna K., Aouad G.
Shared spaces have been proposed and implemented as a means of supporting safe and sustainable road networks by reducing the prominence of vehicles and defining places for people. However, empirical evidence on their performance remains limited, particularly in the Australian context. This paper presents a before-and-after empirical evaluation of three shared space applications in New South Wales, Australia. The implementations were delivered through the “Streets as Shared Spaces” program by local government authorities with support from the New South Wales Government.
2026
Fowler S., Tsiplakis M., McKay T.
Road safety management and crash programmes are dependent on collision data to target remedial action. However, this means a collision and potential fatality have to occur in order for data to be collected about road safety risk at a location, making it a reactive approach. Near-miss data from Connected Vehicles (CVs) provides a proactive approach, identifying harsh braking and swerving events where a collision could have occurred. Kent County Council (KCC) incorporated near-miss data into their own Crash Remedial Programme (CRM).
2026
Sun J., Feng D., Chen B., Hu Y.
Understanding vehicle parking behaviour in metropolitan environments is essential for the effective deployment of electric vehicle charging infrastructure. This study introduces a data-driven framework that integrates spatial clustering with probabilistic topic modelling to characterise urban stop patterns in a dense, diverse urban context.
2026
Grayson H., Tsiplakis M.
This project, a collaboration between Transport for London (TfL) and Compass IoT, demonstrates that there is a significant correlation between near-misses (recorded by connected vehicles) and collisions. The project’s objectives included identifying clusters where near-misses coincided with collision events, evaluating the overlap between Compass and TfL data, and testing the predictive power of historical near-miss patterns for future collision hotspots.
2025
Nassir N., Sarvi M., Lavieri P.
This project explored the potential of utilising and integrating vehicle location and telematics data from connected vehicles (and bicycles) GPS and gyroscope data, alongside traditional sensors, for modern traffic management systems.
2025
Chen L., Manley E.
Vehicular speeding remains a major challenge in urban and transportation planning. Its prevalence in cities arises from a complex mix of social and spatial factors, and a suite of countermeasures are now built into road infrastructure to mitigate its impact. Yet our understanding of how urban context influences speeding is less clear, and we have little sense of the spatial scale at which urban form shapes speeding behaviour.
2025
Li L., Yin D., Xue H., Lillo-Trynes D., Salim F.
With the growing electric vehicles (EVs) charging demand, urban planners face the challenges of providing charging infrastructure at optimal locations. For example, range anxiety during long-distance travel and the inadequate distribution of residential charging stations are the major issues many cities face. To achieve reasonable estimation and deployment of the charging demand, we develop a data-driven system based on existing EV trips in New South Wales (NSW) state, Australia, incorporating multiple factors that enhance the geographical feasibility of recommended charging stations.
2025
Grigorev A., Lillo-Trynes D., Mihaita A. S.
Conventional road safety management is inherently reactive, relying on analysis of sparse and lagged historical crash data to identify hazardous locations, or crash blackspots. The proliferation of vehicle telematics presents an opportunity for a paradigm shift towards proactive safety, using high-frequency, high-resolution near-miss data as a leading indicator of crash risk.
2025
Ziakopoulos A., Karahlis N., Yannis G.
The aim of the present paper is to showcase both the contents and the findings of a large dataset of naturalistic connected vehicle data and to examine its potential for road safety analysis. Specifically, a large dataset of LCVs is presented, collected from the Greater London Area in the UK and their acceleration values are analysed, together with map visualizations which can support policymakers and stakeholders.
2024
Williams B.
Periurban local roads present complex road safety challenges, differing from typical rural roads due to higher number of driveways, intersections, and residences. Our council implemented evidence-based speed limit reductions on an 18.7km network of periurban roads involving a coordinated communications strategy. After the reductions were implemented 85th percentile speeds decreased.
2026
Mihaita A. S., Cheung C., Grigorev A., Mao T., Lillo-Trynes D.
Road safety monitoring has historically been reactive, relying on crash-record analysis after fatalities and injuries have already occurred. Proactive identification of high-risk locations and dangerous driving behaviour before incidents occur is a critical but underexplored challenge. This paper addresses this gap using connected vehicle telemetry data from Greater Sydney, Australia, to detect and forecast near-miss risky driving events at the Local Government Area (LGA) level.
2026
Fowler S., Tsiplakis M., McKay T.
Road safety management and crash programmes are dependent on collision data to target remedial action. However, this means a collision and potential fatality have to occur in order for data to be collected about road safety risk at a location, making it a reactive approach. Near-miss data from Connected Vehicles (CVs) provides a proactive approach, identifying harsh braking and swerving events where a collision could have occurred. Kent County Council (KCC) incorporated near-miss data into their own Crash Remedial Programme (CRM).
2026
Grayson H., Tsiplakis M.
This project, a collaboration between Transport for London (TfL) and Compass IoT, demonstrates that there is a significant correlation between near-misses (recorded by connected vehicles) and collisions. The project’s objectives included identifying clusters where near-misses coincided with collision events, evaluating the overlap between Compass and TfL data, and testing the predictive power of historical near-miss patterns for future collision hotspots.
2024
Williams B.
Periurban local roads present complex road safety challenges, differing from typical rural roads due to higher number of driveways, intersections, and residences. Our council implemented evidence-based speed limit reductions on an 18.7km network of periurban roads involving a coordinated communications strategy. After the reductions were implemented 85th percentile speeds decreased.
2025
Grigorev A., Lillo-Trynes D., Mihaita A. S.
Conventional road safety management is inherently reactive, relying on analysis of sparse and lagged historical crash data to identify hazardous locations, or crash blackspots. The proliferation of vehicle telematics presents an opportunity for a paradigm shift towards proactive safety, using high-frequency, high-resolution near-miss data as a leading indicator of crash risk.
2025
Ziakopoulos A., Karahlis N., Yannis G.
The aim of the present paper is to showcase both the contents and the findings of a large dataset of naturalistic connected vehicle data and to examine its potential for road safety analysis. Specifically, a large dataset of LCVs is presented, collected from the Greater London Area in the UK and their acceleration values are analysed, together with map visualizations which can support policymakers and stakeholders.
2026
Sun J., Feng D., Chen B., Hu Y.
Understanding vehicle parking behaviour in metropolitan environments is essential for the effective deployment of electric vehicle charging infrastructure. This study introduces a data-driven framework that integrates spatial clustering with probabilistic topic modelling to characterise urban stop patterns in a dense, diverse urban context.
2025
Chen L., Manley E.
Vehicular speeding remains a major challenge in urban and transportation planning. Its prevalence in cities arises from a complex mix of social and spatial factors, and a suite of countermeasures are now built into road infrastructure to mitigate its impact. Yet our understanding of how urban context influences speeding is less clear, and we have little sense of the spatial scale at which urban form shapes speeding behaviour.
2025
Li L., Yin D., Xue H., Lillo-Trynes D., Salim F.
With the growing electric vehicles (EVs) charging demand, urban planners face the challenges of providing charging infrastructure at optimal locations. For example, range anxiety during long-distance travel and the inadequate distribution of residential charging stations are the major issues many cities face. To achieve reasonable estimation and deployment of the charging demand, we develop a data-driven system based on existing EV trips in New South Wales (NSW) state, Australia, incorporating multiple factors that enhance the geographical feasibility of recommended charging stations.
2026
Wijayaratna K., Aouad G.
Shared spaces have been proposed and implemented as a means of supporting safe and sustainable road networks by reducing the prominence of vehicles and defining places for people. However, empirical evidence on their performance remains limited, particularly in the Australian context. This paper presents a before-and-after empirical evaluation of three shared space applications in New South Wales, Australia. The implementations were delivered through the “Streets as Shared Spaces” program by local government authorities with support from the New South Wales Government.
2025
Nassir N., Sarvi M., Lavieri P.
This project explored the potential of utilising and integrating vehicle location and telematics data from connected vehicles (and bicycles) GPS and gyroscope data, alongside traditional sensors, for modern traffic management systems.
