With more and more autonomous vehicles hitting the streets this year and starting to provide real services to the public, it marks a critical moment for this technology before mass production. In order to better welcome the upcoming 2020, the year of commercialization for autonomous driving, almost all entrants are seizing the time window to accelerate research and development and push products to market.

On September 17, a new technology company focusing on connected autonomous driving systems and components, Huanyu Zhixing, held the "Autonomous Driving Intelligent System Athena Launch Conference" in Shanghai, officially releasing the Athena high-reliability software system. It is understood that Athena mainly runs on Huanyu Zhixing's self-developed Titan autonomous driving domain controller, and the combination of the two marks the official completion of Huanyu Zhixing's integrated open platform for software and hardware.

As an emerging technology company in the field of autonomous driving, it is reported that Huanyu Zhixing began research and development related to autonomous driving as early as 2008. So far, it has established a series of leading autonomous driving technologies, including laser radar and camera fusion perception and positioning, decision planning, simulation platforms, and intelligent connected vehicle fleets, covering both hardware and software aspects.

In terms of hardware, Huanyu Zhixing's latest breakthrough is the launch of the TITAN III autonomous driving domain controller. This product is designed based on NVIDIA's TX2, runs the UBUNTU operating system, and supports various hardware interfaces such as USB, CAN, RS232, Ethernet, and AD/DA, allowing simultaneous connection of 12 cameras, 6 laser radars, and 5 millimeter-wave radars. Moreover, the TITAN III also has advantages such as compact size, chip-level algorithm integration, high reliability to automotive standards, and low power consumption.

The TITAN III integrates all components required for L4 autonomous driving functions onto a single board, including perception fusion computing, high-precision positioning, vehicle control, and cloud interaction communication. It does not require any external devices; simply connecting cameras, laser radars, and millimeter-wave radars can achieve various intelligent functions such as high-precision mapping, ACC, LDW, LKA, FCW, LC, VUI, PDS, AEB, and one-click overtaking.

Currently, a large number of facts prove that future vehicles will no longer be cold machines, but will be empowered by various software, continuously expanding their connotations and extensions, gaining more functions beyond traditional travel. By combining Athena with the TITAN autonomous driving domain controller, Huanyu Zhixing has achieved high-definition map collection, real-time 3D fusion perception and positioning, data storage and high-speed Ethernet communication, as well as different forms of autonomous driving functions for single vehicles, fleets, and vehicle-road collaboration, making it possible for car manufacturers to quickly validate autonomous driving technology and shorten mass production time.

To better demonstrate Huanyu Zhixing's software capabilities, relevant personnel from Huanyu Zhixing elaborated on their latest progress in AI, 3D perception, multi-sensor fusion positioning, and dynamic planning based on intelligent networking at the launch event. They also conducted a video demonstration of one-click ride-hailing and vehicle return, as well as a remote demonstration of 5G connected autonomous driving functions.

According to Dr. Cao Jing from Huanyu Zhixing, thanks to the development of artificial intelligence technology, there have been some new changes in the field of autonomous driving, such as the transformation from past 2D image-based visual perception to current 3D visual perception. In this regard, Huanyu Zhixing has made many groundbreaking advances, including the physical description of three-dimensional information and performing deep learning directly on point clouds. In terms of autonomous driving testing, using virtual simulation technology to replace more actual road tests has also become possible, especially in the generation of strategies and planning, where Huanyu Zhixing extensively uses cutting-edge simulation technologies, including software-in-the-loop, hardware-in-the-loop, and vehicle-in-the-loop, making the results more reliable and stable.

Academician Zhang Jianwei, co-founder of Huanyu Zhixing, brought to everyone the challenges faced by the next steps in artificial intelligence. He pointed out that current artificial intelligence is still weak AI, which is not prone to small mistakes but can easily make big mistakes. How to use human-like multimodal information to achieve strong AI is one of the important directions of current basic scientific research. Academician Zhang also pointed out that when using artificial intelligence for autonomous driving, future considerations should focus on the integration of more human-like multimodal information beyond vision and laser radar, while also drawing on current achievements in reinforcement learning, continuous learning, and transfer learning to enhance the learning capabilities of autonomous driving vehicles. He also mentioned the need to address the "three views" problem of autonomous driving, especially the moral view, as well as the multi-robot game theory for large-scale collective intelligence. The research on these key issues and the development of related technologies are also the direction of cooperation between Academician Zhang's team in Germany and the Huanyu Zhixing Research Institute.

According to Huanyu Zhixing CEO Li Ming, the integrated software and hardware solution of Huanyu Zhixing is nearing completion. The next phase will focus on how to further enhance the reliability of this open platform based on existing foundations and how to commercialize this solution. "In November, at NVIDIA's GTC China 2018 conference, we will release specific commercialization paths, including autonomous driving application scenarios for different vehicle types such as heavy trucks and passenger cars. At the same time, we also have some collaborative projects with car manufacturers underway, mainly focusing on the research and testing of L4 level autonomous vehicles," Li Ming stated.