[News-Oxcart Network]
Recently, Xiaoma Zhixing unveiled for the first time the shape design, sensor and computing platform scheme of its sixth-generation automatic driving software and hardware system for L4 vehicle specification mass production design, and said that the first model equipped with the system is Toyota S-AM (SIENNA Autono-MaaS), a hybrid model based on the 7-seat Xena, and will start road testing in China this year and put into Operation of Robotaxi in 2023.
It is reported that this batch of customized Toyota S-AM has a dual-redundant system for L4 level automatic driving functions.
In fact, as early as 2019, Xiaoma Zhixing and Toyota began to discuss the feasibility of autonomous driving of the Chinese version of S-AM, and the two sides fully considered the actual scenarios and technical requirements of the application of automatic driving technology, so that this batch of customized S-AM has a dual-redundant system and better control performance for L4 level automatic driving functions. In addition, as an MPV model, the Xena S-AM has a flexible and practical seating space to meet a variety of use scenarios such as family travel.
Peng Jun, co-founder and CEO of Xiaoma Zhixing, said: "Toyota S-AM models join the PonyPilot+ team, which is another major achievement of the in-depth strategic cooperation between Xiaoma Zhixing and Toyota, and the new generation of automatic driving software and hardware systems designed for the mass production of L4 vehicle rules will further improve technical reliability and promote the large-scale application of autonomous driving technology." ”
In terms of technology, the sixth generation system of Xiaoma Zhixing continues to follow the technical route of deep integration of multiple sensors, and for the first time, solid-state lidar is adopted on a large scale, with a total of 23 sensors, of which the resolution of self-developed signal light recognition cameras is 1.5 times higher than that of the previous generation.
In detail, this includes 11 cameras, 7 lidars, and 5 millimeter-wave radars.
First, four solid-state lidars on the roof of the car can achieve 360° environmental perception and object detection, and three blind lidars can help eliminate blind spots on the side and rear of the vehicle.
Secondly, 11 cameras are distributed on the roof and body of the car to achieve all-round perception. 2 medium and long-distance cameras to achieve forward object detection, 1 self-developed signal light recognition camera can accurately identify traffic lights, 4 wide-angle cameras located on the roof are used to achieve full coverage of the perimeter field of view, and 4 ultra-wide-angle cameras located in the body can support the application needs of low-speed scenes such as parking. In addition, there is a classic configuration of a forward millimeter wave radar and a four-angle radar, which can also detect the forward direction of the vehicle and the surroundings of the body.
In terms of computing platform, The automotive grade L4 autonomous driving calculation unit developed by Xiaoma Zhixing has introduced NVIDIA's DRIVE Orin system-on-chip. Compared with the previous generation of computing units, the new generation of computing power is expected to increase by at least 30%, reduce weight by at least 30%, and reduce costs by at least 30%. Based on the strategic cooperation and deep binding with Nvidia, Xiaoma Zhixing has also launched a variety of computing unit solutions with different chip configurations, which can be based on one or more Orin chips and NVIDIA Ampere to purchase GPUs to meet the different needs of autonomous passenger cars and commercial vehicles.
In terms of redundancy, the next generation of systems includes software, computing platforms, and vehicle platform redundancy systems that enable safe pull-over parking or in-safe laneline parking in emergency situations.