Apollo 7.0 is released, and Baidu's multiple car robots enter the Metaverse

On December 29, Baidu Create 2021 (Baidu AI Developer Conference) autonomous driving sub-forum "Co-create Automotive Robots, Connect Technology and Scenarios" was held on the "Xirang" APP. This is the first conference held in the Metaverse in China, which can accommodate 100,000 people to interact on the same screen at the same time. At the forum, Baidu Apollo's autonomous driving open platform Apollo 7.0 was officially released, and the layout of the Apollo X plan in the diversified automotive robot ecosystem was demonstrated to the outside world. Baidu Apollo is using diversified automotive robot connection technologies and scenarios to empower ecological partners with technology to accelerate the development and commercialization of China's autonomous driving industry.

Image source: Baidu

As an important support for Baidu's multi-car robot landing, the upgraded Apollo 7.0 has achieved a milestone-like complete evolution from code to tools, from open source platform to tool platform. Based on the four major open source platforms of cloud services, open source software, hardware development, and vehicle certification, Apollo 7.0 provides a series of upgrades including Apollo Studio, a one-stop practice cloud platform, industry-leading simulation services, and efficient new models. Not only is the code fully open, but it also provides a full-stack tool chain for autonomous driving, which is easier to use, more advanced, and more efficient to help developers use platform capabilities.

Image source: Baidu

At the cloud service platform level, Apollo 7.0 officially upgraded the "data pipeline" service that was popular among developers in version 6.0 to Apollo Studio, covering the entire cloud tool chain from developers' computer to vehicle practice, providing developers with a one-stop practice platform experience. At the simulation platform level, Apollo 7.0 launched the industry's first PnC reinforcement learning model training and simulation evaluation platform, which has multiple advantages such as real data, powerful functions, comprehensive evaluation standards, and scalable architecture. It is expected to provide a unified verification standard for reinforcement learning research. At the open source software platform level, Apollo7.0 upgraded the perception and prediction algorithm modules, and introduced three deep learning-based models: MaskPillars, SMOKE, and Inter-TNT, which effectively reduced problems such as missed detection and jitter.

At present, Baidu Apollo autonomous driving open platform has completed 11 version iterations, has more than 80,000 developers in 135 countries and regions around the world, more than 210 partners, and a total of 700,000 lines of open source code. It has grown into the world's most active autonomous driving open platform.

Image source: Baidu

While empowering developers, Apollo 7.0 further expanded the ability of car robots to connect technologies and scenarios. By collaborating with industries and empowering industries, Baidu Apollo and multiple ecological partners jointly created "car robots" that run through passenger transport, freight, life services and other fields, and fully landed in passenger cars, buses, trunk logistics, warehousing and distribution, mining and port operations and other segmented scenarios. At the Metaverse "site" of the autonomous driving sub-forum, the "Apollo" bus robot, DeepWay trunk logistics car robot, Huaneng Yimin autonomous driving mining truck car robot, and Neolithic retail car robot in the Baidu Apollo ecosystem made their collective debut.

As China's first intelligent solution that achieves full coverage of vehicle, road and cloud in the mining field, Baidu Apollo's special mining robot has full autonomous driving capabilities and can achieve accurate location and operation status information through vehicle-road collaboration solutions. In the future, it will continue to evolve and support full-process operations across working faces; the trunk logistics robot Deepway is data-driven and self-learning, allowing the autonomous driving capabilities of high-speed heavy trucks to be rapidly iterated. Deepway is expected to invest 1,000 heavy trucks in 2023, making Deepway an AI veteran in the field of trunk logistics.

Image source: Baidu

In addition, Baidu Apollo also shared with developers the rich resources and latest progress of the Apollo EDU autonomous driving education talent program, and announced its plan to empower tens of millions of colleges and enterprises and train millions of autonomous driving engineering talents in the next three years, comprehensively covering application-oriented and research-oriented talents, so that autonomous driving can truly empower all walks of life and promote the continued prosperity and development of the autonomous driving industry.

Adhering to the core concept of "open capabilities, shared resources, accelerated innovation, and continuous win-win", Baidu Apollo continues to evolve with an open attitude. "Co-create automotive robots, connect technology and scenarios" has become an important consensus of the Baidu Apollo Autonomous Driving Ecological Alliance. In the future, Baidu Apollo will continue to accelerate the implementation of segmented automotive robot scenarios, work with partners on the road to commercialization of autonomous driving, and continuously promote the development of autonomous driving in China and even the world.