Electronics and Semiconductors

Baidu to build largest driverless ride-hailing service

30 November 2022
Baidu will expand its robotaxi service it is currently running in 10 cities in China including Beijing, Chongqing and Wuhan. Source: Baidu

Chinese tech giant Baidu Inc. plans to build what it claims will be the world’s largest autonomous ride-hailing service area in 2023.

The goal is to expand the operation area for fully driverless robotaxis and reach potentially more customers. Additionally, Baidu revealed a new artificial intelligence model built specifically for autonomous driving including:

  • Perception
  • High-definition autonomous driving maps
  • Closed-loop autonomous driving data system
  • End-to-end adaptation of AI chips for autonomous vehicles

Previously, Baidu obtained permits to operate fully autonomous robotaxis without a safety driver inside the cities of Chongqing and Wuhan, China. This comes after it was given licenses to operate fully driverless robotaxis in the Chinese capital Beijing.

Baidu said it will continue to expand its operation area in 2023 to make the largest service in these cities and others. Currently Baidu’s autonomous ride-hailing platform, Apollo Go, covers more than 10 cities in China and has completed more than 474,000 rides. In 2022, rides have increased some 311% year-over-year and have increased 65% in just the last quarter.

Baidu said each robotaxi it operates can provide 15 rides a day on average, nearly the same daily ride average of a standard ride-hailing car service.

New maps

The autonomous maps provide comprehensive capabilities such as automatic production, real-time fusion and knowledge enhancement. This includes:

  • A 96% automation rate for map production
  • Real-time map updates
  • Massive data plus human driver knowledge for better reliability.

A closed loop

Baidu’s closed loop technology identifies and utilizes data. The system called Apollo Loop is a system that leverages both on-board small AI models and a cloud-based big AI model for data mining and automated labeling.

The data achieves automated training, and the data is then optimized and distributed to effectively use the data and enhance overall intelligence of autonomous vehicles.

To contact the author of this article, email PBrown@globalspec.com


Powered by CR4, the Engineering Community

Discussion – 0 comments

By posting a comment you confirm that you have read and accept our Posting Rules and Terms of Use.
Engineering Newsletter Signup
Get the Engineering360
Stay up to date on:
Features the top stories, latest news, charts, insights and more on the end-to-end electronics value chain.
Advertisement
Weekly Newsletter
Get news, research, and analysis
on the Electronics industry in your
inbox every week - for FREE
Sign up for our FREE eNewsletter
Advertisement