̽��ֱ�� of Cambridge - roads

Using machine learning to monitor driver ‘workload’ could help improve road safety

sc604 — Thu, 07 Dec 2023 07:48:29 +0000

̽��ֱ��researchers, from the ̽��ֱ�� of Cambridge, working in partnership with Jaguar Land Rover (JLR) used a combination of on-road experiments and machine learning as well as Bayesian filtering techniques to reliably and continuously measure driver ‘workload’. Driving in an unfamiliar area may translate to a high workload, while a daily commute may mean a lower workload.

̽��ֱ��resulting algorithm is highly adaptable and can respond in near real-time to changes in the driver’s behaviour and status, road conditions, road type, or driver characteristics.

This information could then be incorporated into in-vehicle systems such as infotainment and navigation, displays, advanced driver assistance systems (ADAS) and others. Any driver-vehicle interaction can be then customised to prioritise safety and enhance the user experience, delivering adaptive human-machine interactions. For example, drivers are only alerted at times of low workload, so that the driver can keep their full concentration on the road in more stressful driving scenarios. ̽��ֱ��results are reported in the journal IEEE Transactions on Intelligent Vehicles.

“More and more data is made available to drivers all the time. However, with increasing levels of driver demand, this can be a major risk factor for road safety,” said co-first author Dr Bashar Ahmad from Cambridge’s Department of Engineering. “There is a lot of information that a vehicle can make available to the driver, but it’s not safe or practical to do so unless you know the status of the driver.”

A driver’s status – or workload – can change frequently. Driving in a new area, in heavy traffic or poor road conditions, for example, is usually more demanding than a daily commute.

“If you’re in a demanding driving situation, that would be a bad time for a message to pop up on a screen or a heads-up display,” said Ahmad. “ ̽��ֱ��issue for car manufacturers is how to measure how occupied the driver is, and instigate interactions or issue messages or prompts only when the driver is happy to receive them.”

There are algorithms for measuring the levels of driver demand using eye gaze trackers and biometric data from heart rate monitors, but the Cambridge researchers wanted to develop an approach that could do the same thing using information that’s available in any car, specifically driving performance signals such as steering, acceleration and braking data. It should also be able to consume and fuse different unsynchronised data streams that have different update rates, including from biometric sensors if available.

To measure driver workload, the researchers first developed a modified version of the Peripheral Detection Task to collect, in an automated way, subjective workload information during driving. For the experiment, a phone showing a route on a navigation app was mounted to the car’s central air vent, next to a small LED ring light that would blink at regular intervals. Participants all followed the same route through a mix of rural, urban and main roads. They were asked to push a finger-worn button whenever the LED light lit up in red and the driver perceived they were in a low workload scenario.

Video analysis of the experiment, paired with the data from the buttons, allowed the researchers to identify high workload situations, such as busy junctions or a vehicle in front or behind the driver behaving unusually.

̽��ֱ��on-road data was then used to develop and validate a supervised machine learning framework to profile drivers based on the average workload they experience, and an adaptable Bayesian filtering approach for sequentially estimating, in real-time, the driver’s instantaneous workload, using several driving performance signals including steering and braking. ̽��ֱ��framework combines macro and micro measures of workload where the former is the driver’s average workload profile and the latter is the instantaneous one.

“For most machine learning applications like this, you would have to train it on a particular driver, but we’ve been able to adapt the models on the go using simple Bayesian filtering techniques,” said Ahmad. “It can easily adapt to different road types and conditions, or different drivers using the same car.”

̽��ֱ��research was conducted in collaboration with JLR who did the experimental design and the data collection. It was part of a project sponsored by JLR under the CAPE agreement with the ̽��ֱ�� of Cambridge.

“This research is vital in understanding the impact of our design from a user perspective, so that we can continually improve safety and curate exceptional driving experiences for our clients,” said JLR’s Senior Technical Specialist of Human Machine Interface Dr Lee Skrypchuk. “These findings will help define how we use intelligent scheduling within our vehicles to ensure drivers receive the right notifications at the most appropriate time, allowing for seamless and effortless journeys.”

̽��ֱ��research at Cambridge was carried out by a team of researchers from the Signal Processing and Communications Laboratory (SigProC), Department of Engineering, under the supervision of Professor Simon Godsill. It was led by Dr Bashar Ahmad and included Nermin Caber (PhD student at the time) and Dr Jiaming Liang, who all worked on the project while based at Cambridge’s Department of Engineering.

Reference:
Nermin Caber et al. ‘Driver Profiling and Bayesian Workload Estimation Using Naturalistic Peripheral Detection Study Data.’ IEEE Transactions on Intelligent Vehicles (2023). DOI: 10.1109/TIV.2023.3313419

Researchers have developed an adaptable algorithm that could improve road safety by predicting when drivers are able to safely interact with in-vehicle systems or receive messages, such as traffic alerts, incoming calls or driving directions.

There is a lot of information that a vehicle can make available to the driver, but it’s not safe or practical to do so unless you know the status of the driver

Bashar Ahmad

Coneyl Jay via Getty Images

Head up display of traffic information and weather as seen by the driver

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Cambridge researchers help develop smart, 3D printed concrete wall for National Highways project

sc604 — Thu, 13 Jul 2023 12:01:02 +0000

̽��ֱ��3D-printed structure – a type of retaining wall known as a headwall – has been installed on the A30 in Cornwall, where it is providing real-time information thanks to Cambridge-designed sensors embedded in its structure. ̽��ֱ��sensors provide up-to-date measurements including temperature, strain and pressure. This ‘digital twin’ of the wall could help spot and correct faults before they occur.

Headwall structures are normally made in limited shapes from precast concrete, requiring formwork and extensive steel reinforcement. But by using 3D printing, the team – including specialists from Costain, Jacobs and Versarien – could design and construct a curved hollow wall with no formwork and no steel reinforcement. ̽��ֱ��wall gets its strength not from steel, but from geometry instead.

̽��ֱ��wall – which took one hour to print – is roughly two metres high and three and a half metres across. It was printed in Gloucestershire at the headquarters of the advanced engineering company Versarien, using a robot arm-based concrete printer. Making the wall using 3D printing significantly saves on costs, materials and carbon emissions.

Over the past six years, Professor Abir Al-Tabbaa’s team in the Department of Engineering has been developing new sensor technologies and exploring the effectiveness of existing commercial sensors to get better-quality information out of infrastructure. Her team has also developed various ‘smart’ self-healing concretes. For this project, they supplied sensors to measure temperature during the printing process.

Temperature variations at different layers of the 3D-printed wall were continuously monitored to detect any potential hotspots, thermal gradients, or anomalies. ̽��ֱ��temperature data will be correlated with the corresponding thermal imaging profile to understand the thermal behaviour of the 3D-printed wall.

“Since you need an extremely fast-setting cement for 3D printing, it also generates an enormous amount of heat,” said Al-Tabbaa. “We embedded our sensors in the wall to measure temperature during construction, and now we’re getting data from them while the wall is on site.”

In addition to temperature, the sensors measure relative humidity, pressure, strain, electrical resistivity, and electrochemical potential. ̽��ֱ��measurements provide valuable insights into the reliability, robustness, accuracy, and longevity of the sensors.

A LiDAR system also was used to scan the wall as it was being printed to create a 3D point cloud and generate a digital twin of the wall.

“Making the wall digital means it can speak for itself,” said Al-Tabbaa. “And we can use our sensors to understand these 3D printed structures better and accelerate their acceptance in industry.”

̽��ֱ��Cambridge team developed a type of sensor, known as a PZT (Piezoceramic Lead-Zirconate-Titanate) sensor, which measures electromechanical impedance response and monitors changes in these measurements over time to detect any possible damage. These smart sensors can show how 3D-printed mortar hardens over time, while simultaneously monitoring the host structure’s health.

Eight PZT sensors were embedded within the wall layers at different positions during the 3D printing process to capture the presence of loading and strain, both during the construction process and service life after field installation.

̽��ֱ��team, which included experts in smart materials, automation and robotics and data science, also developed a bespoke wireless data acquisition system. This enabled the collection of the multifrequency electromechanical response data of the embedded sensors remotely from Cambridge.

“This project will serve as a living laboratory, generating valuable data over its lifespan,” said Al-Tabbaa. “ ̽��ֱ��sensor data and ‘digital twin’ will help infrastructure professionals better understand how 3D printing can be used and tailored to print larger and more complex cement-based materials for the strategic road network.”

Members of the team included Dr Sripriya Rengaraju, Dr Christos Vlachakis, Dr Yen-Fang Su, Dr Damian Palin, Dr Hussam Taha, Dr Richard Anvo and Dr Lilia Potseluyko from Cambridge; as well as Costain’s Head of Materials Bhavika Ramrakhyani, a part-time PhD student in the Department of Engineering, and Ben Harries, Architectural Innovation Lead at Versarien, who is also starting a part-time PhD in the Department of Engineering in October.

̽��ֱ��Cambridge team’s work is part of the Resilient Materials for Life Programme and the Digital Roads of the Future Initiative. ̽��ֱ��research is supported in part by the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI), and the European Union.

Cambridge researchers, working in partnership with industry, have helped develop the first 3D-printed piece of concrete infrastructure to be used on a National Highways project.

Making the wall digital means it can speak for itself, and we can use our sensors to understand these 3D-printed structures better and accelerate their acceptance in industry

Abir Al-Tabbaa

Cool Concrete – the smart, 3D printed concrete wall used for National Highways project.

National Highways

3D printed retaining wall

Yes

Road planning 'trade off' could boost food production while helping protect tropical forests

fpjl2 — Thu, 15 Dec 2016 19:04:57 +0000

Conservation scientists have used layers of data on biodiversity, climate, transport and crop yields to construct a colour-coded mapping system that shows where new road-building projects should go to be most beneficial for food production, at the same time as being least destructive to the environment.

̽��ֱ��hope is that this "trade-off" strategy might guide governments, investors and developers to focus on road expansions that make the most difference for current agricultural areas, rather than projects that threaten to open up significant natural habitats for conversion to farmland.

As a proof of concept, scientists applied their technique to a specific sub-region: the Greater Mekong in Southeast Asia - one of the most biologically important parts of the planet, and a place that has lost almost a third of its tropical forest since the 1970s.

They found a number of current road proposals in Vietnam, Laos, Myanmar and Cambodia have potential for massive habitat conversion with little benefit for populations and food security. They also found areas where new roads could increase food production and connectivity with limited environmental cost.

Researchers from the ̽��ֱ�� of Cambridge, UK, the Kunming Institute of Botany and the World Agroforestry Centre in China say their study, published today in PLOS Biology, is an attempt to explore a more "conciliatory approach" in the hope of starting greater dialogue between developers and conservation experts.

They call on organisations such as the newly established Asian Infrastructure Investment Bank as well as Asian Development Bank to use such analyses when considering investment in future road expansion projects in the Mekong region - an area undergoing rapid development.

"It is estimated that by 2050 we will build 25 million km of new road lanes, the majority of which will be in the developing world," says Andrew Balmford, Professor of Conservation Science at Cambridge.

"Conservationists can to appear to oppose nearly all new infrastructure, while developers and their financial backers are often fairly mute on the environmental impact of their proposals. This can lead to a breakdown in communication."

" ̽��ֱ��Mekong region is home to some of the world's most valuable tropical forests. It's also a region in which a lot of roads are going to be built, and blanket opposition by the conservation community is unlikely to stop this," says Prof Jianchu Xu from the Kunming Institute of Botany in China.

"Studies like ours help pinpoint the projects we should oppose most loudly, while transparently showing the reasons why and providing alternatives where environmental costs are lower and development benefits are greater.

"Conservationists need to be active voices in infrastructure development, and I think these approaches have the potential to change the tone of the conversation."

̽��ֱ��Greater Mekong encompasses Vietnam, Laos, Cambodia, Thailand, Myanmar and the Yunnan Province of China. It is home to around 20,000 plant species, 2000 types of land vertebrates and 850 species of freshwater fish. Much of this biodiversity is found nowhere else on the planet.

̽��ֱ��saola, for example, is a mammal resembling a small antelope that was only discovered in 1992, and is so rare it is known as the "Asian unicorn". ̽��ֱ��region's vast forests also act as critical carbon 'sinks', absorbing greenhouse gases.

̽��ֱ��Greater Mekong is also home to over 320 million people, and habitat loss has been accelerating. Between 1973 and 2009, an estimated 31% of the region's natural forest disappeared. Alongside this there is widespread poverty; food insecurity and malnutrition remain major challenges.

̽��ֱ��researchers created the new framework for road planning in the Mekong by analysing various data sources: including crop yield gaps across the region, travel times between population hubs, range maps for birds and mammals, and biomass carbon stocks in soil and vegetation.

By combining this data into composite layers, the team were able to map them over the region and reduce the results to a simple green-to-purple colour scale comparing food production benefits to environmental costs.

In areas such as Myanmar's Ayeyarwady Delta, new roads could substantially boost food production through improved transport links for getting produce to market, lowering waste and increasing access to new technologies. This would come at a relatively limited environmental cost, as much of the area has been converted to agriculture, yet crop yields remain low.

However, researchers warn that planned projects in other areas with extensive forests, such as in northern Laos and western Yunnan in China, could devastate vital ecosystems with little gain for food production.

"If new roads are deployed strategically, and deliberately target already-cleared areas with poor transport connectivity, this could attract agricultural growth that might otherwise spread elsewhere," says Prof Xu.

For Balmford, this is perhaps the crux of the argument, and something he has long been vocal about: "By increasing the crop yield of current agricultural networks, there is hope that food needs can be met while containing the expansion of farming and so sparing natural habitats from destruction. ̽��ֱ��location of infrastructure, and roads in particular, will play a major role in this."

However, the researchers caution that the channeling of roads into less damaging, more rewarding areas will have to go hand-in-hand with strengthening protection for globally significant habitats such as the remaining forests of the Mekong.

Scientists hope a new approach to planning road infrastructure that could increase crop yield in the Greater Mekong region while limiting environmental destruction will open dialogues between developers and the conservation community.

Conservationists can to appear to oppose nearly all new infrastructure, while developers and their financial backers are often fairly mute on the environmental impact of their proposals. This can lead to a breakdown in communication

Andrew Balmford

Jianchu Xu & Biaoyun Huai

A highway cuts across the Yunnan Province of Southwest China, part of the Greater Mekong.

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. For image use please see separate credits above.

Yes

Natural disasters, infrastructure and the “new normal”

tdk25 — Tue, 15 Jan 2013 15:51:27 +0000

Some of the worst natural disasters of the last decade have radically changed the ways in which we strive to protect communities from similar, future tragedies, a leading engineer will explain this week.

Citing a roll-call that includes the Tohoku earthquake and tsunami, the Canterbury earthquake and Hurricanes Katrina and Sandy, Professor Tom O’Rourke of Cornell ̽��ֱ�� will argue that these and other similarly devastating incidents have established a “new normal” for the way in which we prepare ourselves for extreme events.

He will be speaking at the inaugural lecture of the Cambridge Centre for Smart Infrastructure and Construction (CSIC). This marks the formal commencement of a multitude of new research projects on infrastructure, many of which are designed to enable society to protect critical infrastructure from the unexpected. ̽��ֱ��lecture will take place in the Department of Engineering, ̽��ֱ�� of Cambridge, on 17 January, at 6pm.

Researchers at the Centre are already developing and improving wireless technologies, fibre optics and other types of sensors, with a view to establishing them as the norm for the construction industry and those in asset management responsible for monitoring bridges, tunnels, roads, railways, and other types of infrastructure.

As Professor O’Rourke will discuss, however, that norm is already being dramatically reshaped by the game-changing incidents of recent years. His talk – “ ̽��ֱ��New Normal for Natural Disasters” – will argue that these have forced a shift in the way in which the risks of natural disasters occurring are evaluated. In turn, that necessitates a different approach to the question of protecting critical infrastructure itself.

His talk will examine the threat posed by potential future earthquakes to the water supply of Southern California, or that of hurricanes to New York City. It will also propose a strategy for improving infrastructure resilience at a time when the financial resources sometimes available to governments wishing to do so are limited.

̽��ֱ��Centre’s inaugural lecture will be followed by a seminar, the following day, led by another specialist in the field, Professor Bill Spencer of the ̽��ֱ�� of Illinois, who will focus on the potential of new technology to continuously monitor the integrity of infrastructure in real-time. This will not only improve public safety, Spencer will argue, but also simultaneously reduce maintenance and inspection costs. His presentation will draw on the real-life example of a network of smart sensors which have been used on the Jindo Bridge, a structure in South Korea with a 344 metre main span.

Radio 4 listeners can also listen to Professor Robert Mair, Principal Investigator at the Centre for Smart Infrastructure and Construction, on this week’s Life Scientific, where he discusses tunnel construction in busy cities and the novel application of sensors to the construction industry, among other subjects. ̽��ֱ��show was broadcast today (Tuesday, 15 January) at 9am, is repeated at 9.30pm, and is available on BBC iPlayer.

After a year of preparation following the Centre’s establishment in 2011, numerous research projects are now underway, focusing on its main mission, which is to develop and commercialise technologies which will change the way in which infrastructure is managed. In particular, researchers are examining new and innovative ways in which to use technologies in sensors and data management to monitor the day-to-day performance of bridges, tunnels, roads and more.

Doing so remotely is, as Friday’s seminar implies, particularly valuable where the infrastructure is hard for people to reach and monitor themselves. Finding ways in which sensors can harvest their own energy so that they can continue to operate without needing to be maintained is therefore particularly important. One breakthrough in this area is the recently reported development of a device which can convert the vibration of passing traffic into electricity, enabling a sensor to generate its own power, so that batteries are not required.

In addition, the Centre is concerned with the practical purpose of commercialising these technologies, and developing them to a stage where their use in industry is common practice. ̽��ֱ��research programmes have been developed in unison with construction companies and partners from the IT, electronics and materials sectors with the aim of developing tools that will be of practical use to industry once the research stage is complete. In the long term, it is hoped that this will lead to cradle-to-grave monitoring of infrastructure around the world, both in new and existing structures, vastly improving public safety when disaster next strikes.

̽��ֱ��Japanese and Canterbury earthquakes, Hurricanes Katrina and Sandy and a host of other modern natural disasters have changed the game for those striving to protect our infrastructure from extreme events. ̽��ֱ��inaugural lecture at a Cambridge Centre dedicated to this cause will hear how.

̽��ֱ��talk will examine the threat posed by potential future earthquakes to the water supply of Southern California, or that of hurricanes to New York City.

NASA.

Hurricane Katrina makes landfall in the US. Speaking this week in Cambridge, engineer Tom O’Rourke will describe such disasters as game-changers for those wishing to protect people from similar, future events.

This work is licensed under a Creative Commons Licence. If you use this content on your site please link back to this page.

Yes