Calendar An icon of a desk calendar. Cancel An icon of a circle with a diagonal line across. Caret An icon of a block arrow pointing to the right. Email An icon of a paper envelope. Facebook An icon of the Facebook "f" mark. Google An icon of the Google "G" mark. Linked In An icon of the Linked In "in" mark. Logout An icon representing logout. Profile An icon that resembles human head and shoulders. Telephone An icon of a traditional telephone receiver. Tick An icon of a tick mark. Is Public An icon of a human eye and eyelashes. Is Not Public An icon of a human eye and eyelashes with a diagonal line through it. Pause Icon A two-lined pause icon for stopping interactions. Quote Mark A opening quote mark. Quote Mark A closing quote mark. Arrow An icon of an arrow. Folder An icon of a paper folder. Breaking An icon of an exclamation mark on a circular background. Camera An icon of a digital camera. Caret An icon of a caret arrow. Clock An icon of a clock face. Close An icon of the an X shape. Close Icon An icon used to represent where to interact to collapse or dismiss a component Comment An icon of a speech bubble. Comments An icon of a speech bubble, denoting user comments. Comments An icon of a speech bubble, denoting user comments. Ellipsis An icon of 3 horizontal dots. Envelope An icon of a paper envelope. Facebook An icon of a facebook f logo. Camera An icon of a digital camera. Home An icon of a house. Instagram An icon of the Instagram logo. LinkedIn An icon of the LinkedIn logo. Magnifying Glass An icon of a magnifying glass. Search Icon A magnifying glass icon that is used to represent the function of searching. Menu An icon of 3 horizontal lines. Hamburger Menu Icon An icon used to represent a collapsed menu. Next An icon of an arrow pointing to the right. Notice An explanation mark centred inside a circle. Previous An icon of an arrow pointing to the left. Rating An icon of a star. Tag An icon of a tag. Twitter An icon of the Twitter logo. Video Camera An icon of a video camera shape. Speech Bubble Icon A icon displaying a speech bubble WhatsApp An icon of the WhatsApp logo. Information An icon of an information logo. Plus A mathematical 'plus' symbol. Duration An icon indicating Time. Success Tick An icon of a green tick. Success Tick Timeout An icon of a greyed out success tick. Loading Spinner An icon of a loading spinner. Facebook Messenger An icon of the facebook messenger app logo. Facebook An icon of a facebook f logo. Facebook Messenger An icon of the Twitter app logo. LinkedIn An icon of the LinkedIn logo. WhatsApp Messenger An icon of the Whatsapp messenger app logo. Email An icon of an mail envelope. Copy link A decentered black square over a white square.

Robot ‘training’ on famous Highland estate will make driverless vehicles more reliable

Gathering data for driverless vehicles on the Ardverikie Estate.
Gathering data for driverless vehicles on the Ardverikie Estate.

Rough tracks on a famous Highland estate are being used to teach robots about the challenges of off-road driving.

The project will help make driverless vehicles of the future more reliable, wherever they go – from busy city streets to rain-lashed Scottish glens.

In a dramatic location, soon to feature in the latest James Bond movie, researchers from the Oxford Institute of Robotics (ORI) have been putting a Range Rover packed with sensors and cameras through its paces.

With expert local four-by-four drivers, they have been amassing data on routes around Ardverikie Estate, south of Newtonmore, which has also starred in TV hits Outlander, The Crown and Monarch of the Glen.

The Oxford Robotics Institute team, with their drivers.

Part of Oxford University, ORI has been among research institutions leading the rapid development of technology for driverless, or ‘autonomous’ vehicles in recent years.

But, so far, most of the data needed to ‘train’ the robots that will drive them has been gathered in urban areas.

Oliver Bartlett, of ORI, said: “Nearly all the main driving data sets are in towns and cities and you can train your car to drive those.

“But, if you take them outside that environment, you’ve got no idea how they are going to perform.

We wanted to collect one data set that has the entire spectrum, so you can train it and also prove it works on motorways and in the Highlands, in cities and all these different places.”

Data gathering was carried out in daylight and darkness and in a typically Highland variety of weather. The Oxford team is planning a return visit to collect more.

‘Pesky’ Highland weather useful

Matthew Gadd, one of the researchers on the Sense-Assess-eXplain (SAX) project, said the conditions at Ardverikie offered a “unique opportunity” to carry out ‘robust sensing’ to train robots.

He continued: “The weather can be really pesky in how robots perceive the world.

“We went there three or four times and it was almost a different place entirely and that’s really useful information for us in terms of making our robots really robust in challenging weather.

When you are out and about in a car in the Highlands, it looks very different to the south of England and what the environment looks like is also useful for us.”

Driving on mud, gravel and other surfaces also helped to generate data to enable robot drivers to adapt their behaviour, just as their human counterpart would have to.

Mr Gadd said that, amid the mountainous landscape of the estate, which has more than 60 miles of tracks, the “feature rich” horizon was helpful to the research and “super important for the algorithms to log onto.”

He added: “A lot of the time we assume that the robot moves on a flat world, like a two-dimensional plane.

“All those assumptions just break down when you’re going up a scree, or down a muddy slope.”

Machines will drive like local experts

The ORI team worked with specialist off-road driving company Highland All Terrain, which is based at Kinloch Laggan, near Newtonmore.

Mr Bartlett added: “It was one of Highland All Terrain’s drivers who was doing all the driving for us.

“So, when we learn from the data, we’ll get expert annotation and teach the robot to drive like him – not like us.”

The SAX project is part of the Assuring Autonomy International Programme (AAIP), which is funded by the Lloyd’s Register Foundation.  It is led by Professor Paul Newman and Dr Lars Kunze, of ORI.

A subsidiary of Oxford University’s Department of Engineering Science, ORI comprises collaborating and integrated groups of researchers, engineers and students dedicated to researching robotics, artificial intelligence, systems engineering, and other related fields.

A crash scene for the new James Bond movie being filmed on Ardverikie Estate.

Two years ago, dramatic footage of a car flipping over on a forest track emerged as scenes for the next James Bond film, No Time to Die, were shot on 38,000 acre Ardverikie Estate.

The release of the movie, starring Daniel Craig in his final outing as secret agent 007, was delayed by the Covid-19 pandemic, but it is now due to open in UK cinemas at the end of September.

The estate’s scenery has also featured in the TV historical saga Outlander.  The show’s world-wide popularity has drawn fans from around the globe to visit its Scottish locations

Ardverikie House, on the shores of Loch Laggan, had a starring role in the most recent series of Netflix hit The Crown.

Ardverikie House.

The 19th century Baronial manor was used to portray the Royal Family’s Aberdeenshire county retreat, Balmoral, with Oscar winner Olivia Colman playing the Queen and Gillian Anderson former Prime Minister Margaret Thatcher, in scenes filmed there.

It first found TV fame as the “big house” house of fictitious Glenbogle estate in the hugely popular BBC Sunday night series, Monarch of the Glen.

The show ran for seven seasons, from 2000, and starred Richard Briers, Susan Hampshire, former Dr Who Tom Baker, Alastair Mackenzie and Dawn Steele.

Adverikie has starred in a number of other films and television programmes.