Chris Middleton reports on how sensor-packed driverless cars are exploring London’s congested streets.

Autonomous vehicles travelling on London streets are required to make 150 independent vehicle detections every second and can detect traffic lights in 1/2,000th of a second – faster than the human eye.

Those are the claims made by UK driverless technology company, Oxbotica, which has been trialling five fully autonomous vehicles in London – the sixth most congested city on Earth – since December 2018, as part of the DRIVEN consortium.

The consortium now plans a demonstration of autonomous cars’ progress to date in London later this month, after 3D mapping more than 250,000 miles of roads in and around the capital.

In October 2018, British car hire and courier firm Addison Lee partnered with the startup, with the aim of launching an autonomous taxi service in London by 2021.

Oxbotica was founded in 2014, using technology developed a year earlier for the RobotCar Project at Oxford University. In 2016, it became the first company to trial a driverless car on British roads, in partnership with the Transport Systems Catapult.

Oxbotica’s Universal Autonomy software is vehicle and platform-agnostic, and is built around two core components: Selenium, an operating system that combines data from sensors fitted to each self-driving vehicle, and Caesium, a data and vehicle management tool that allows anonymised learnings to be shared between vehicles anywhere in the world. In this way, Oxbotica vehicles learn from others and become smarter and safer over time.

Paul Newman, Oxbotica founder, said: “As humans, we get better at driving the more experience we have, but we don’t share our learnings with each other. This is the covenant for autonomous vehicles. They learn as a community in a way that we don’t. If we, humans, have a mishap, or see something extraordinary, we aren’t guaranteed to make our neighbour or colleague a better driver.

“Even if we could learn from each other like computers can, we can’t share at scale, across vast numbers and we can’t do it all the time. That’s what our AI software will do for every host vehicle wherever it is in the world.

“Providing life-long shared learning, and with it in-depth, and continually improved knowledge of the local area – allowing our cars to not just read the roads, but also to predict common hazards with ever greater sophistication.”

  • At least 40 companies are developing autonomous vehicle and/or driver assistance technologies worldwide, including Uber, Tesla, Ford, Lyft, Honda, GM, Toyota, Jaguar LandRover, Apple, Baidu, Didi Chuxing,, Hyundai, Audi, BMW, Amazon, Aptiv, and Waymo, the driverless car division of Google’s parent, Alphabet.

The aim is to make personal transport into a safer, more environmentally friendly, on-demand service and reduce the burden of urban car ownership, while also making services available to the young, old, sick, and disabled.

  • Studies have revealed that roughly 95 percent of the estimated 1.2 million deaths on the world’s roads each year are caused by human error, not technical failure. However, a brace of fatal US accidents in vehicles running under software control last year has damaged public confidence in the technology.

Source: Press release