The prospects of autonomous vehicles has opened up debate about how changes to vehicle transport can change property. Combined with car-sharing and alternative modes of transport, driverless vehicles promise less car parking, and less intrusive highways, meaning more space for more interesting property development.

In London, Addison Lee plans self-driving taxis by 2021. It will start by creating detailed maps that record the position of kerbs, road signs and traffic lights, in preparation for autonomous cars.

Now a specialist in machine learning is pourching cold water on the idea.

Sally Epstein, machine learning expert at Cambridge Consultants, has warned that full autonomy remains a long way off.

“The goal of autonomous vehicles in the U.K. by 2021 is hugely ambitious, but consumers should know that we’re nowhere near to having genuinely driverless cars on public roads," she said.

The challenges include the constant stream of roadworks and the ever-changing throng of street furniture which cannot be mapped easily.

"Mapping data will become out of date as soon as it is collected. Street furniture is constantly changing, with roadworks, accidents and more, while human movement in the same environment will remain stubbornly difficult to predict," Epstein said.

"But mapping data alone is not sufficient for the challenge. Maps must be intelligently integrated with other sensor data, in order to keep drivers and other road users safe."

Epstein also warns that it is not enough to argue that autonomous vehicles are safer than driven vehicles.

"When fully autonomous vehicles do finally arrive, explaining how their decisions are made, particularly following accidents, will be much more important than any statistical proof that they experience fewer accidents than with humans at the wheel," Epstein said.