Baidu, Inc. has introduced Apollo 3.5, the newest and most powerful release of the open, reliable and secure software platform for the development of autonomous driving systems through on-vehicle and hardware platforms.

Apollo 3.5 is the first open source autonomous driving platform that can perform in complex urban and suburban driving scenarios. The new release unlocks the tools developers need to create reliable self-driving mobility solutions such as robo-taxis and autonomous delivery services.

udelv, a California-based autonomous delivery van company, is one example of companies leveraging Apollo 3.5 to develop its own autonomous driving solutions. At CES 2019, udelv announced up to 100 ADVs, which have been developed on the Apollo 3.5 software platform, and will be deployed this year in several US locations, including the San Francisco Bay Area.

The latest Apollo update includes new driving capabilities, such as the ability to manage unprotected turns, speed bumps, clear zones, side passes, narrow lanes, and autonomous parking.

One of the biggest innovations of Apollo 3.5 lies in its new high-performance runtime framework: the Apollo Cyber RT framework—the industry’s first open source autonomous driving framework compatible with the development of production-grade autonomous driving systems.

Apollo 3.5 is now compatible with the most advanced suite of sensors currently available on the market, such as Velodyne VLS-128 LiDAR. LeddarTech has also announced the integration of LeddarTech’s LiDAR products into Apollo.

Hardware development platform.

In addition, Apollo has had a close collaboration with Intel on the autonomous driving computing hardware. At CES 2019, Baidu demonstrated the successful implementation of Mobileye’s Responsibility Sensitivity Safety (RSS) in the simulation engine of Apollo, achieving the world’s first RSS implementation on an open source platform.

As of today, the Apollo has grown into one of the largest autonomous driving ecosystems in the world, bringing together more than 130 global partners and used by more than 12,000 developers and partners worldwide.

Apollo Enterprise. Baidu Apollo Enterprise, a suite of intelligent driving products and solutions for mass production vehicles, is scalable, safe, and highly customizable based on enterprise customer needs. Apollo Enterprise solutions support vehicle and information safety and can be upgraded via OTA (Over-the-Air Programing).

Apollo Enterprise solutions are fast to implement and customizable based on customer needs, while also providing comprehensive support for vehicle and information safety. Enterprise clients will also receive dedicated service from Baidu support teams.

The five main Apollo Enterprise products and solutions are:

1. Highway autonomous driving solutions;

2. Autonomous valet parking solutions;

3. Fully autonomous driving minibus solutions;

4. Intelligent map data service platform, with options for commercial, ADAS, and high-definition maps; and

5. DuerOS for Apollo, a set of AI-based IoV solutions, with voice assistant, augmented reality, and motion detection capabilities.

Baidu is collaborating with global and national auto brands to deploy these solutions in production vehicles, including Ford, Chery, BYD, Kyundai Kia, Great Wall, and WM Motor.

Open Source V2X and Robo-taxis. Baidu also announced at CES that it has open-sourced its V2X solutions.

Apollo V2X terminal software and reference hardware will create synergetic interactions between smart cars and intelligent roadways to improve safety and mitigate traffic congestion. Under this system autonomous vehicles will be able to better communicate with traffic lights.

In 2019, 100 robo-taxis will operate on 130 miles of city roads equipped with Baidu’s V2X technology in Changsha, the capital city of Hunan province in the south-central part of China.

The fleet will be China’s first group of autonomous driving taxis managed by Baidu’s V2X system, a comprehensive solution that integrates smart vehicles and intelligent road infrastructure for safer deployment of autonomous cars.