After achieving technical self-confidence, Xiaoma Zhixing began to pursue aesthetics, efficiency, and emotional communication, so that the automatic driving front of the mass production car was more mature, and lidar was no longer a fat creature.
Wen 丨 wisdom driving network Wang Shuoqi
The year is approaching, and Pony Zhixing is not idle.
On January 20, Xiaoma Zhixing unveiled for the first time the appearance design, sensor and computing platform solution of the sixth generation of autonomous driving software and hardware system design for L4 vehicle specification mass production. The first model equipped with the system is the Toyota S-AM, a hybrid electric platform based on the seven-seat Syna, which will start road testing in China this year and start the daily operation of autonomous mobility services in the first half of 2023.
It is worth noting that the automatic driving system is aimed at vehicle-level mass production from the aspects of modeling design, parts research and development and selection, software and hardware coupling, safety redundancy and system assembly production.
The choice of Senna is also aimed at the market of high-end commercial vehicles, with a larger and wider body in the city road to complete the automatic driving, which is also based on the pony's confidence in technology.
Up to now, Pony Zhixing has accumulated more than 10 million kilometers of autonomous driving public road test mileage worldwide, and Toyota S-AM models have joined the PonyPilot+ team, which is another major achievement of the in-depth strategic cooperation between Xiaoma Zhixing and Toyota.
Stronger and more aesthetically pleasing sensors
Compared with the previous generation, the new program has been fully upgraded in the direction of mass production in the number of sensors and the selection of models, and for the first time, solid-state lidar has been used on a large scale, with a total number of 23 sensors, of which the resolution of the self-developed signal light recognition camera has been increased by 1.5 times.
The sensor scheme consists of 4 solid-state lidars on the roof; 3 blindfolding lidars distributed on the left and right sides and backwards; 4 millimeter wave angle radars at the four corners of the roof; 1 forward long-range millimeter wave radar; and 11 cameras, 7 on the roof and 4 around the body.
The appearance of the autonomous vehicle equipped with the new system is closer to the modeling design concept of mass production, making the perception module more integrated and beautiful.
The new generation of sensor kit adopts a unique front and rear two-stage split design, the front section integrates a solid-state lidar, and the rear end integrates three solid-state lidar, which is greatly reduced compared to the previous generation design, presenting a more lightweight visual experience.
In order to have a more technological sense, Xiaoma Zhixing designed the concept lights of the front horizontal ring and the rear vertical three sections on the roof perception module, with an integrated transparent cover to create a sense of technological futurism for Robotaxi.
These lights not only add a visual reference to the operating status of various systems, but also help Robotaxi users quickly identify pre-ordered autonomous vehicles.
With NVIDIA chip, self-developed vehicle specification level calculation unit
Pony Zhixing's self-developed vehicle-level calculation unit solution is equipped with NVIDIA DRIVE Orin (SoC) system-on-chip.
Currently conducting road tests, the software system has been able to operate in real time on Orin with low latency. Mass production of the new computing unit will begin at the end of 2022.
At present, the DRIVE Orin system-on-chip has 254 TOPS computing power, and the pony's computing unit can be customized according to the needs, based on one or more NVIDIA Orin system-level chips and vehicle-grade NVIDIA Ampere architecture GPUs, which can meet the technical requirements of the research and development of autonomous driving passenger cars and autonomous commercial vehicles at the same time, and accelerate the large-scale mass production of autonomous driving technology by Xiaoma Zhixing.
This practice is also the current mainstream manufacturers' practice, using multiple chips to improve computing power.
From the ability of automatic driving to the accumulation of algorithms and data, Xiaoma Zhixing has gradually mastered key technologies, and laws and regulations are gradually opening up, and governments at all levels are also vigorously supporting.
For example, in December last year, Xiaoma Zhixing became the first company to conduct self-driving truck road testing on China's public highways, and at the same time, Xiaoma Zhixing was also the only company with an autonomous truck road test license in Beijing and Guangzhou; in November, Xiaoma Zhixing, as one of the first enterprises, was approved to carry out the pilot commercialization of autonomous driving Robotaxi in Beijing; in addition, Xiaoma Zhixing is also the first batch of companies to conduct autonomous driving road tests in the four first-tier cities in China.
In the next step, the automatic driving companies, including Xiaoma Zhixing, are more commercial and product landing, which is also the focus of the conference of Xiaoma Zhixing, making the integration of automatic driving technology and the car more harmonious on the product side, making the front-loading mass production products more mature, and deeply participating in the automatic driving calculation unit on the technical side, gradually achieving the purpose of mastering the core technology.
【Pay attention to the video number of intelligent driving, pay attention to the frontier of intelligent driving】