Skip to main content

Baidu autonomous car reaches milestone in Beijing

An autonomous car developed by Chinese language Internet search provider Baidu has successfully completed rigorous, fully autonomous tests on one route with mixed roads under a variety of environmental conditions, says the company. The Baidu autonomous car is the first in China to have demonstrated full autonomy under mixed road conditions, marking a milestone in China's autonomous driving effort. The road tests were carried out under complex road conditions, and the Baidu vehicle, a modified BMW 3 Serie
December 11, 2015 Read time: 2 mins
An autonomous car developed by Chinese language Internet search provider Baidu has successfully completed rigorous, fully autonomous tests on one route with mixed roads under a variety of environmental conditions, says the company.

The Baidu autonomous car is the first in China to have demonstrated full autonomy under mixed road conditions, marking a milestone in China's autonomous driving effort. The road tests were carried out under complex road conditions, and the Baidu vehicle, a modified BMW 3 Series, completed the tests by executing a comprehensive set of driving actions and accurately responding to the driving environment.

Baidu claims the car demonstrated full autonomy on the entirety of the 30 kilometre test route and successfully executed driving actions including making right turns, left turns and U-turns, decelerating when detecting vehicles ahead, changing lanes, passing other cars and merging into traffic from on-ramps and exiting from off-ramps. The car speed peaked at 100 km per hour during the test runs.

Baidu AutoBrain, the core of Baidu's autonomous driving technology, includes highly automated driving (HAD) maps, positioning, detection, smart decision-making and control.

Baidu's self-developed HAD maps record 3D road data to within a few centimetres of accuracy of vehicle positioning. With Baidu's leading object recognition and environment perception technology, the car can detect, recognise, and follow other vehicles with high accuracy; recognise road lanes; and accurately gauge distance and velocity.

"Fully autonomous driving under mixed road conditions is universally challenging, with complexity further heightened by Beijing's road conditions and unpredictable driver behaviour," said Wang Jing, SVP of Baidu and general manager of Baidu's newly established Autonomous Driving Business Unit.

Related Content

  • December 13, 2013
    Daimler’s double take sees machine vision move in-vehicle
    Jason Barnes looks at Daimler’s Intelligent Drive programme to consider how machine vision has advanced the state of the art of vision-based in-vehicle systems. Traditionally, radar was the in-vehicle Driver Assistance System (DAS) technology of choice, particularly for applications such as adaptive cruise control and pre-crash warning generation. Although vision-based technology has made greater inroads more recently, it is not a case of ‘one sensor wins’. Radar and vision are complementary and redundancy
  • June 6, 2016
    Autonomous driving – what can we really expect?
    Dave Marples of Technolution BV looks beyond the hype to the practical implementation of autonomous vehicles. Having looked at the development of this sector for some time, I am concerned about the current state of autonomous driving development as engineering (and marketing) have run way ahead of the wider systemic, and legislative, requirements to support an autonomous future.
  • November 26, 2013
    Lidar technology wins big in China’s autonomous vehicle challenge
    China’s fifth annual Future Challenge earlier this month pitted eleven unmanned intelligent vehicles against each other on a course designed to test their capabilities in suburban and urban road tests, over a 23-kilometre course. All of the first eight cars to finish were equipped with Velodyne’s 3D Lidar vision technology which provides active sensing for crash avoidance, driving automation and mobile road survey and mapping. Velodyne HDL-64E and HDL-32E sensors deliver 360-degree views of the car’s env
  • November 12, 2015
    Driver aids make inroads on improving safety
    In-vehicle anti-collision systems continue to evolve and could eliminate some incidents altogether. John Kendall rounds up the current developments. A few weeks ago, I watched a driver reverse a car from a parking bay at right angles to the road, straight into a car driving along the road. The accident happened at walking pace, no-one was hurt and both cars had body panels that regain their shape after a low speed shunt.