China's Baidu Completes its ‘Apollo Park', the World's Largest Autonomous Driving & Intelligent Vehicle Testing Site

Home > News > Content

【Summary】The world’s largest intelligent vehicle infrastructure cooperative System (IVICS) has been completed in China, internet giant Baidu announced on Tuesday. The comprehensive test site is called “Apollo Park” and will support the development of autonomous vehicles as part of Baidu's open Apollo platform.

Eric Walz    Jul 03, 2020 12:15 PM PT
China's Baidu Completes its ‘Apollo Park', the World's Largest Autonomous Driving & Intelligent Vehicle Testing Site

For the past three years, China's internet search giant Baidu is actively developing self-driving cars as part of its open Apollo platform. Since launching Apollo in 2017, more than 100 companies and automakers have joined the platform, which is designed to speed up the development of autonomous driving technology through collaboration between the various partners. 

Now the world's largest intelligent vehicle infrastructure cooperative System (IVICS) to support these efforts has been completed in China, Baidu announced on Tuesday. 

The comprehensive test site is called "Apollo Park" and will support the development of autonomous vehicles, as well as vehicle-to-vehicle (V2V) and vehicle-to-everything (V2X) technology, which allows vehicles to communicate with each other as well as to urban infrastructure, such as traffic lights. 

Apollo Park can support all of the functions associated with self-driving vehicles and connected cars, including cloud computing for analyzing big data, operational command, maintenance and calibration, research and development and vehicle storage.

Baidu started the construction phase of Apollo Park in late 2018. The test site is located in the Beijing Economic-Technological Development Area (Yizhuang Development Zone) in the southeast part of China's capital. Apollo Park covers an area of 13,500-square-meter (145,000 square feet) and deploys over 200 autonomous vehicles.

The test site also features a vehicle calibration center, a maintenance center, security command center, an asset storage center, a training center for safety drivers that supervise the self-driving vehicles, as well as closed-loop roads for testing of self-driving vehicles.

Apollo Park 2.png

Autonomous vehicles inside a parking facility at Baidu's Apollo Park in China.

Baidu's Open Apollo Development Platform

Baidu launched its Apollo project in April 2017. The open Apollo autonomous driving platform is widely regarded as the "Android of the Automotive Industry" and has grown to become the largest open-source autonomous driving platform in the world, according to Baidu. Among the global automakers contributing to the Apollo platform are BMW, Ford Motor Co, Toyota, Volkswagen and Honda.

Apollo is a comprehensive, secure, all-in-one autonomous driving ecosystem which supports all of the major functions of a self-driving car. Contributions from Baidu's industry partners are helping to spur the development of autonomous driving and related technology, as intended.

This collaborative effort is designed to push the entire industry forward. Using the open Apollo platform and the necessary hardware to support it, a developer has access to all the source code needed to build and test a fully-functional self-driving vehicle. 

Apollo also includes a computer simulation engine, which allows developers to test their autonomous driving algorithms before deploying their vehicles on public roads. The simulation engine, which has embedded HD maps with centimeter level accuracy, is backed by vast amounts of actual driving data collected by Baidu, including traffic lights, road signs, speed limits, and lane markers so developers can fine tune their autonomous driving algorithms.

In March 2018, Baidu announced the release of "Apollo Scape", billed as the world's largest open-source dataset for autonomous driving technology. The dataset is part of Apollo. The dataset eliminates the time it takes for manual data collection. These datasets are used to train machine learning algorithms for autonomous driving.

According to a 2016 Rand Corporation report, accumulating the same amount of real road test data from human drivers would require a fleet of 100 vehicles driving nonstop for 500 years.

In addition to developing autonomous vehicles, Baidu is also working on a commercial robotaxi service. The robotaxis are being produced at China's first Level-4 passenger vehicle production line jointly built by Baidu and Chinese automaker FAW. 

The self-driving vehicles are currently being tested by Baidu on public roads in China.

Prev                  Next
Writer's other posts
    Related Content