Presented By O’Reilly and Intel AI
Put AI to work
Sep 4-5, 2018: Training
Sep 5-7, 2018: Tutorials & Conference
San Francisco, CA

Enabling affordable but reliable autonomous driving

Shaoshan Liu (PerceptIn)
1:45pm-2:25pm Thursday, September 6, 2018
Implementing AI
Location: Imperial B
Secondary topics:  Edge computing and Hardware, Transportation and Logistics
Average rating: ***..
(3.00, 1 rating)

Who is this presentation for?

  • Anyone interested in the autonomous driving technology stack

Prerequisite knowledge

  • A basic understanding of AI

What you'll learn

  • Learn how PerceptIn built an autonomous vehicle for less than $10,000 and ensured reliability with modular design
  • Explore the technologies used in the design


The universal adoption of autonomous driving will greatly reduce pollution and traffic problems, improve safety, and make the economy more efficient. Nonetheless, autonomous driving solutions suffer from affordability and reliability issues and are therefore not ready for universal adoption.

Shaoshan Liu explains how PerceptIn built a reliable autonomous vehicle for low-speed scenarios with a total cost under $10,000. PerceptIn chose to start with low-speed environments to ensure safety, thus allowing immediate deployment. As technology advances, this solution can be gradually upgraded for high-speed scenarios, with vehicle performance eventually equaling that of a human driver in every driving scenario.

For more information about the project, check out this YouTube video and this article.

Photo of Shaoshan Liu

Shaoshan Liu


Shaoshan Liu is the cofounder and chairman of PerceptIn, a company working on developing a next-generation robotics platform. Previously, he worked on autonomous driving and deep learning infrastructure at Baidu USA. Shaoshan holds a PhD in computer engineering from the University of California, Irvine.