How to build intelligent driving software-defined vehicle (SDV) architecture?
The autonomous driving intelligent platform can be roughly divided into four parts from the bottom up: hardware platform, system software (hardware abstraction layer + OS kernel + middleware), functional software (library components + middleware), and application algorithm software (autonomous driving, HMI, etc.).Autonomous driving R&D links mainly involve software engineering and hardware engineering:
- Basic software for intelligent driving: real-time vehicle control operating system (narrowly defined OS), intelligent driving middleware (ROS, CyberRT, DDS, AutoSAR), autonomous driving operating system (broadly defined OS), etc.;
- General algorithm design for intelligent driving: positioning, perception, planning, decision, etc., covering from small models to foundation models (BEV Transformer, Occupancy Network, autonomous driving end-to-end neural network, etc.);
- General algorithm training for intelligent driving: AI deep learning software platform, intelligent driving data training set, etc.;
- Terminal-cloud integration for intelligent driving: data closed loop, data collection and labeling, simulation test (scene library, simulation platform), cloud native platform, HD map, etc.;
- Intelligent driving system integration and engineering implementation: FCW, LDW, ALC, APA/AVP, etc.
- Intelligent driving assistance software: ADAS performance evaluation, ADAS data recording, etc.
- Intelligent driving hardware engineering: domain controllers (chips, hardware engineering), sensors (LiDAR, radar, ultrasonic radar, camera, GNSS, IMU, etc.), system engineering, chassis-by-wire, brake-by-wire, etc.;
- Intelligent driving hardware system design: computing platform hardware system architecture design, vehicle chip system design, vehicle sensor system design, etc.
There are usually two development paths for the kernel of intelligent driving operating systems:
One is to inherit the rich open-source ecosystems of Linux, based on the open-source and powerful Linux macro kernel, with a focus on enhancing its security and real-time performance and realizing the ASIL-B/D-compliant Safety Linux operating system. Linux operating system has rich ecosystems, but it is difficult to pass the required functional safety level certification;The other is to emphasize functional safety, target ASIL-D functional safety level, and implement microkernel RTOS according to POSIX standards, such as QNX OS; compared with Linux, microkernel RTOS lacks the similar open-source ecosystem support and is difficult to develop.
Safety Linux originates from Linux and has rich hardware and software ecosystems. In the era of software-defined vehicles, Linux will boast a rising share in the autonomous driving market and become a dominant underlying operating system for intelligent driving. In China automakers and suppliers will also head in the direction of Safety Linux in development of intelligent driving operating systems.
ZTE: The dual-core intelligent driving OS based on ZTE microkernel and Safety Linux takes into account the requirements of intelligent driving for functional safety and rich application ecosystems. It is composed of three parts: 1) ZTE Microkernel RTOS; 2) ZTE Hypervisor; 3) ZTE Safety Linux.
In terms of upper-layer software, ZTE has cooperated with middleware companies such as Neusoft Reach and iSOFT Infrastructure Software; as for bottom-layer chip, ZTE has established partnerships with mainstream Chinese chip companies like Horizon Robotics, Black Sesame Technologies, and SemiDrive.
In terms of mass production and implementation, early in 2021 ZTE had delivered a Safety Linux-based intelligent driving OS verification project to Changan Automobile. In 2022, ZTE and FAW started technical verification of intelligent driving OS based on microkernel + Safety Linux, and vehicle control OS. In 2023, ZTE added Dongfeng Safety Linux intelligent driving OS project.
Banma AliOS Drive: It is a dual-core driver formed by AliOS RTOS and AliOS Safety Linux, with both security and performance advantages. Its basic system's security domain is AliOS RTOS, a self-developed secure real-time microkernel that meets the highest level of vehicle functional safety requirements, ASIL-D. It is composed of the following parts: 1) AliOS RTOS; 2) AliOS Safety Linux; 3) AliOS Hypervisor; 4) AliOS Drive Middleware.
As the performance domain, AliOS Safety Linux is based on Linux for real-time security enhancement and can support high-performance computing needs of autonomous driving. In addition, Banma's self-developed AliOS Hypervisor provides a good fusion mechanism for dual cores, and also meets ASIL-D, the highest vehicle functional safety level.
Intelligent driving operating system kernel: the key to breakthroughs in localization lies in the coordinated development of homemade chips and kernel OS.
At present, the ownership of automobiles in China has exceeded 300 million units, but the localization rate of vehicle operating systems (including intelligent cockpit system) is about 5-10%, and vehicle control operating systems (including autonomous driving system) are still in their infancy;In addition to long development cycle, high technical difficulty, and heavy capital investment, the greater challenge is that 'deeply binding' dominant underlying operating systems (e.g., QNX and Android) to core technologies (e.g., chips) has created a winner-take-all ecosystem. For example, Android and ARM has formed the 'AA Alliance'. The two don’t simply combine together, but work on deep customization for each other, triggering an ever-growing chemical reaction.
ZTE: In October 2023, ZTE and Black Sesame Technologies worked together to implement the first Chinese microkernel OS product based on Black Sesame A1000 to support the full business process of AI perception and reasoning, building a 'Chinese chip' + ' Chinese software' solution in the field of intelligent driving;
Banma Zhixing: Banma Zhixing has forged partnerships with more than 10 mainstream chip vendors. Based on AliOS Drive intelligent driving operating system, Banma Zhixing builds a computing base on Horizon Journey 5, a chip which can support stronger AI algorithm innovation;
iSOFT Infrastructure Software: In response to the China Automotive Operating System Open Source Program of China Association of Automotive Manufacturers (CAAM), iSOFT Infrastructure Software has built open-source co-construction cooperation with 21 units including FAW, BAIC Research Institute, Geely, Li Auto, SemiDrive, and Horizon Robotics. iSOFT Infrastructure Software has open-sourced the “龘” (EasyAda) microkernel source code to the industry, which has been first adapted to SemiDrive’s smart gateway SoC G9X;
Kernelsoft: The chip adaptation of Linux-based Photon RTOS now has supported such chips as NVIDIA Orin and Black Sesame A1000, and is being adapted to the chips of UNISOC, Rockchip, SemiDrive, etc. Kernelsoft plans to cooperate with more vendors like Horizon Robotics and Phytium. The BSP of the above-mentioned vehicle chips will also be open-sourced subsequently.
As for automakers, emerging carmakers with strong R&D capabilities will be more inclined to build a fully independent intelligent driving “underlying kernel + chip” system:
- Tesla: Tesla has created its own RTOS (RT Linux, written in C language) based on the Linux system. On this basis, Tesla has built domain controllers, reconstructed automotive EEA, and applied self-developed FSD SoC;
- Li Auto: deeply customized on Linux kernel, Li OS will be first installed on Li Auto’s all-electric models. It will also pack Li Auto’s self-developed intelligent driving SoC in the future;
- NIO: SkyOS, a vehicle all-domain operating system based on Linux kernel, is the underlying operating system for NIO cars. It is installed on NT3.0 platform-based models (e.g., ET9) and is adapted to the chip platforms of NVIDIA, Qualcomm, Intel and others. In addition, it will also be equipped with Shenji NX9031, NIO's self-developed intelligent driving SoC.
Chinese operating system providers have launched open source plans.
Currently, China is quickening its pace of developing open-source vehicle OS:- In 2021 Huawei HarmonyOS was fully donated to the OpenAtom Foundationton to build the OpenHarmony open source project.
- In 2022, Banma Zhixing announced that AliOS Drive will effectively enable layered decoupling, cross-domain sharing and open cooperation.
In February 2023, Kernelsoft announced the overall planning and open source plan about Photon OS. Photon Linux, which is used in intelligent vehicle cockpit domain and autonomous driving domain, will be open sourced as the starting point for implementation of Kernelsoft’s open source plan. Other relevant companies, institutions or developers can develop automotive OS and applications based on this open source version.
How to build intelligent cockpit architecture for software-defined vehicles (SDV)?
Intelligent cockpit R&D links mainly involve software engineering and hardware engineering:- Cockpit basic software: vehicle operating system (QNX, Linux, Android, HarmonyOS, AliOS, etc.), virtual machine (Hypervisor), middleware (AutoSAR);
- Cockpit system software development: application development is mainly based on Android, cluster software development based on QNX, and TBOX software development based on Linux;
- Cockpit interface design: UI design software;
- Cockpit application software: user portrait, situational awareness, multimodal fusion interaction (AR HUD, voice, acoustics/audio, DMS/OMS, face recognition, gesture recognition and other software development). Foundation models have begun to be used in cockpit multimodal interaction;
- Cloud services: vehicle-cloud integrated platform, cloud native platform, information security, OTA development and operation strategy, etc.
Self-development: automakers pursue independent and controllable IT R&D and platform construction. Leading automakers have spontaneously chosen to self-develop. On the one hand, first-tier automakers boast great R&D and technical strength; on the other hand, they hope to ensure the stability and usability of their cloud-native platforms;
Open source: moreover automakers attach great importance to open source. Open source technology and community are the first stop for exploring cloud native. Open source is also the best way for automakers to pay attention to cutting-edge cloud native technology and foster technical talents;
Comprehensive digital transformation: in addition, cloud-native technologies such as container and microservice have also provided assistance to automakers to overtake on the bend in digital transformation. Building a cloud-native platform with full-stack capabilities has become the best way for advanced companies to realize digital transformation.
Cloud native originates from cloud computing, and is built and deployed in the cloud. It can truly access cloud infrastructures with powerful functions. Cloud native can be deployed in the cloud and inside the vehicle. Vehicle system software is becoming ever more complex, and the amount of code now has reached hundreds of millions of lines. Run-time software is therefore also introduced into the container inside the vehicle.
Geely: Geely's cloud-native technology was deeply co-developed with Volcengine and Neusoft Reach, a pioneer in broadly defined operating systems for software-defined vehicles and intelligent vehicles. At present, Geely has registered more than 30 patents for its self-developed digital twin intelligent cockpit system cloud application technology. Geely's cloud-native technology enables cloud-edge-terminal interconnection, decoupling of cockpit computing power and space hardware, and elimination of cockpit experiences’ dependence on the computing power of vehicle chips;
SAIC Motor Passenger Vehicle: CloudOS is mass-produced and used by SAIC Motor Passenger Vehicle. Based on cloud native technology, SAIC Motor Passenger Vehicle creates vehicle-cloud data cooperation architecture in which 'data synchronization means functions work”;
Aptiv: Aptiv and Wind River co-developed an 'end-to-end, cloud-native DevOps platform'. In supporting software-defined vehicles, Wind River Studio can be divided into two parts: runtime software inside the vehicle and a Studio toolset in the cloud.
How to build intelligent vehicle control architecture for software-defined vehicles (SDV)?
Intelligent vehicle control specifically involves multiple subdivisions such as body control, chassis control, power control, and energy management. EEA further evolves towards cross-domain integration and 'central computing + zone controllers' architecture.The centralization of electrical architecture further integrates power domain, chassis domain and body domain to provide the integration of core control functions at the vehicle interlayer. Its goal is to create a vehicle control operating system for autonomous driving to be connected to vehicles. OEMs or Tier1s have different integration ideas according to their product features.
Lotus vehicle motion control unit (VMCU): based on the functions of VCU, it is expanded in the direction of chassis functions and integrates all vehicle-level control functions in the chassis domain, including TVC, ESP, and TCS. The actuators include “three-electric” controllers, and brake, steer and suspension in the chassis surround them and are controlled and coordinated by them uniformly.
Lotus is jointly developing VMC vehicle dynamic control software with different partners. The OEM focuses on its core competence, that is, differentiated development at the vehicle level, and works on some differentiated software and parameters of vehicles, allowing suppliers to concentrate on developing platform components.
From functional domains to central computing architecture, the concept of zonal integration is indispensable, and the key link is the specific practice of zonal control. The new-generation body zone controller incorporates the idea of partial zonal control, divides the left and right controllers, and is responsible for signal collection and load drive in this zone. It has five core functions: zonal power supply, zonal information, zonal functions (provided by atomic services), zonal drive, and edge computing.
UAES USP 2.0 Developer Platform: in April 2023, UAES announced the USP 2.0 developer platform at its 2023 Developers Conference. USP2.0 enables the integration of nearly 20 independent ECUs via zonal architecture, with the communication rate increased from 2M to up to 1000M.
In the full process from development to testing and verification, UAES creates a pre-installed local development environment for developers and also provides a software development kit (SDK). On USP2.0, the services that can be called have gone deep into body control, energy management, motion control, thermal management and other fields.
Continental's 'Function as a Product (FaaP)' solution: suitable for all body and actuator functions and integrated into vehicle cross-domain products as a fast and cost-effective solution. For example, a variety of functions such as window lift, trunk control, seat adjustment, seat heating, and electric doors have the corresponding software package. Continental will expand them subsequently to bring more options.
The core of FaaP lies in decoupling of software and hardware. Continental's middleware can decouple the upper body and the lower body. It can be seen that the upper body highlights performance and computing power, involving ADAS algorithms and implementation of in-vehicle entertainment. The development of the upper body is more software and service oriented. The lower body is conventional body electronics and is hardware and product oriented.
The decoupling allows OEMs and Tier1s to develop with other suppliers and cooperate under the same framework, enabling higher development efficiency, and much higher portability of system modules.
Table of Contents
1 How to Build Intelligent Driving Software System?1.1 Overall Software and Hardware Architecture of Intelligent Cockpit
1.2 Basic Software: Real-time Vehicle Control Operating System (OS in Narrow Sense)
1.2.1 Intelligent Vehicle software architecture includes hypervisor, system cores, middleware, functional software, and application programs
1.2.2 Narrowly Defined OS (Kernel) for Intelligent Driving
1.2.3 CATARC’s Automotive OS Standard System
1.2.4 Intelligent Driving Real-time Vehicle Control OS Reference Architecture
1.2.5 Intelligent Driving Operating System Kernel Development Path (1): Inheriting Linux's rich open source ecosystem
1.2.6 Intelligent Driving Operating System Kernel Development Path (2): Implementation of Microkernel RTOS Based on POSIX Standard
1.2.7 Intelligent Driving Underlying OS: Status Quo of Chinese Market Development
1.2.8 Intelligent Driving Underlying OS: Software OS Providers Bind with Hardware Chip Vendors for Deep Cooperation
1.2.9 Intelligent Driving Underlying OS: Key to Localization Breakthrough lies in Collaboration of Chinese Chips and Microkernel OS
1.2.10 Intelligent Driving Underlying OS: Chinese Real-Time Vehicle Control OS Vendors Launch Open Source Programs
1.2.11 Localization of Real-time Operating System：“CETC iSOFT Infrastructure Software” EasyAda Microkernel (1)
1.2.12 Localization of Real-time Vehicle Control OS: “CETC iSOFT Infrastructure Software” EasyAda Microkernel (2)
1.2.13 Localization of Real-time Operating System：ZTE's Dual Core Intelligent Driving OS Based on ZTE Microkernel and Safety Linux
1.2.14 Localization of Real-time Vehicle Control OS: ZTE Dual-kernel Intelligent Driving OS based on ZTE microkernel and Safety Linux (2)
1.2.15 Localization of Real time Operating System: ZTE's "Three Step" Strategy for Intelligent Driving OS
1.2.16 Localization of Real-time Vehicle Control OS: ZTE Intelligent Driving OS Adaptation Solution
1.2.17 Localization of Real-time Vehicle Control OS: ZTE Safety Linux Adaptation on Black Sesame Technologies A1000
1.2.18 Localization of Real-time Vehicle Control OS: "ReachAuto +ZTE +SemiDrive" Collaborate on Fully Localized Vehicle Control Platform
1.2.19 Localization of Real time Operating System: RT Thread Open Source Real Time Operating System (RTOS)
1.2.20 Localization of Real time Operating System: Banma AliOS Drive Intelligent Driving System
1.2.21 Localization of Real-time Vehicle Control OS: Banma Zhixing AliOS Drive+Horizon J5+HoloMatic AI Algorithm
1.2.22 Localization of Real time Operating System: ZLingsmart“RAITE Microkernel” and“RAITE Hypervisor”
1.2.23 Localization of Real Time Operating System: Matrix of Kernelsoft Photon Operating System Products Based on Linux
1.2.24 Localization of Real-time Vehicle Control OS: "China Intelligent and Connected Vehicles (CICV)" Baseline 1.0 Automotive OS
1.2.25 Real Time Operating System: Aptiv VxWorks Microkernel
1.2.26 Real Time Operating System: Aptiv VxWorks Microkernel
1.2.27 Real-Time Vehicle Control OS: Aptiv Introduces Wind River Studio "Cloud Native" to Automotive Industry
1.2.29 Real Time Operating System: QNX OS for Safety
1.2.30 Real Time Operating System: Xpeng X-EEA 2.0/3.0 Intelligent Driving Adopts QNX OS at the Bottom Layer
1.2.31 Real Time Operating System: Tesla OS Bottom Layer Self-developed on Linux
1.2.32 Real Time Operating System: Li OS Bottom Layer Self-developed on Linux
1.2.33 Real Time Operating System: Changan SDA RTDriveOS Intelligent Driving Operating System (1)
1.2.33 Real Time Operating System: Changan SDA RTDriveOS Intelligent Driving Operating System (2)
1.2.34 Real Time Operating System: Toyota Open Vehicle Operating System - Arene
1.2.35 RTOS (in Narrow Sense) Suppliers and Product List (1)
1.2.36 RTOS (in Narrow Sense) Suppliers and Product List (2)
1.2.37 RTOS (in Narrow Sense) Suppliers and Product List (3)
1.2.38 RTOS (in Narrow Sense) Suppliers and Product List (4)
1.2.39 Summary: Real Time Operating System (in Narrow Sense)
1.3 Basic Software: Intelligent Driving Middleware (ROS, CyberRT, DDS, AutoSAR)
1.3.1 Key Technology for Mass Production and Implementation of Intelligent Driving: Middleware
1.3.2 Intelligent Driving Vehicle Middleware: Communication Middleware (1)
1.3.3 Intelligent Driving Vehicle Middleware: Communication Middleware (2)
1.3.4 Development Prospects of SOME/IP & DDS
1.3.5 Intelligent Driving Communication Middleware Solutions (1): Greenstone "Swift" Communication Middleware SWIFT DDS (1)
1.3.6 Intelligent Driving Communication Middleware Solutions (1): Greenstone "Swift" Communication Middleware SWIFT DDS (2)
1.3.7 Intelligent Driving Communication Middleware Solution (2): RTI Connext Drive 3.0
1.3.8 Mainstream Communication Middleware Suppliers and Their Product Lists (1)
1.3.9 Mainstream Communication Middleware Suppliers and Their Product Lists (2)
1.3.10 Intelligent Driving Middleware: Autosar, ROS2, CyberRT
1.3.11 Intelligent Driving Middleware Solution Options for OEMs and Tier1 Suppliers (1)
1.3.12 Intelligent Driving Middleware Solution Options for OEMs and Tier1 Suppliers (2)
1.3.13 Intelligent Driving Automotive Middleware (1): AP AUTOSAR
1.3.14 Intelligent Driving Middleware: AUTOSAR CP+AP Hybrid Software Architecture (1)
1.3.15 Intelligent Driving Middleware: AUTOSAR CP+AP Hybrid Software Architecture (2)
1.3.16 Intelligent Driving Middleware: ROS
1.3.17 Differences between ROS 2 and AUTOSAR AP
1.3.18 Autonomous Driving Middleware Solution (1): Baidu CyberRT
1.3.19 Autonomous Driving Middleware Solution (2): Bosch EDMS AD Middleware (1)
1.3.20 Autonomous Driving Middleware Solution (2): Bosch EDMS AD Middleware (2)
1.3.21 Autonomous Driving Middleware Solution (3): HoloMatic HoloSAR
1.3.22 Autonomous Driving Middleware Solution (3): HoloSAR Autonomous Driving Middleware of HoloMatic Technology (2)
1.3.23 Autonomous Driving Middleware Solution (4): Technomous Domain Control Middleware - RazorWareX1.0
1.3.24 Autonomous Driving Middleware Solution (5): Photon Middleware Adaptive Software Platform
1.3.25 Autonomous Driving Middleware Solution (6): iSOFT ORIENTAIS AP Intelligent Driving Basic Software Platform
1.3.26 Is It Necessary for OEMs to Self-develop Middleware? (1): Suppliers’ Perspective
1.3.27 It Necessary for OEMs to Self-develop Middleware? (2): OEMs’ Perspective
1.3.28 Is It Necessary for OEMs to Self-develop Middleware? (3): Summary
1.3.29 Global Autonomous Driving Middleware AUTOSAR Suppliers and Product Lists（1）
1.3.30 Global Autonomous Driving Middleware AUTOSAR Suppliers and Product Lists（2）
1.3.31 Global Autonomous Driving Middleware AUTOSAR Suppliers and Product Lists（3）
1.3.32 Chinese Autonomous Driving Middleware AUTOSAR Suppliers and Product Lists（1）
1.3.33 Chinese Autonomous Driving Middleware AUTOSAR Suppliers and Product Lists（2）
1.3.34 Chinese Autonomous Driving Middleware AUTOSAR Suppliers and Product Lists（3）
1.3.35 Autonomous Driving Middleware ROS 2 Players and Product Lists
1.3.36 Independent R&D Suppliers of Autonomous Driving Middleware and Product Lists（1）
1.3.37 Independent R&D Suppliers of Autonomous Driving Middleware and Product Lists（2）
1.3.38 Independent R&D Suppliers of Autonomous Driving Middleware and Product Lists（3）
1.3.39 Independent R&D Suppliers of Autonomous Driving Middleware and Product Lists（4）
1.4 Basic Software: How to Systematically Build a Generalized OS for Autonomous Driving?
1.4.1 Generalized OS Definition for Autonomous Driving
1.4.2 Evolution of Vehicle EEA Drives Changes in Underlying OS of Vehicles
1.4.3 Development Trend of Generalized OS for Autonomous Driving: Evolution towards Unified and Integrated Smart Car Operating System
1.4.4 Market Size of China Autonomous Driving Operating System in Broad Sense(Middleware OS)
1.4.5 Intelligent Driving Generalized OS Software Platform: Neusoft ReachNeuSAR 4.0 (1)
1.4.6 Intelligent Driving Generalized OS Software Platform: Neusoft Reach NeuSAR 4.0 (2)
1.4.7 Intelligent Driving Generalized OS Software Platform: ISOFT Infrastructure Software’s AUTOSAR CP+AP Integrated Solution
1.4.8 Intelligent Driving Generalized OS Software Platform: ZTE Communications Layered Decoupling Three-Dimensional Ecology
1.4.9 Generalized Intelligent Driving OS Software Platform: Vehicle OS of Jingwei Hirain Technologies
1.5 Construction of Universal Algorithms for Intelligent Driving: from Small Models to Large Models
1.5.1 Intelligent Driving 3.0 Era, from Small Models to Large Models
1.5.2 How to Build an End-to-end Neural Network Foundation Model of Autonomous Driving?
1.5.3 Core Autonomous Driving Algorithm Modules
1.5.4 Iteration Process of Autonomous Driving Algorithm module (2016-2023)
1.5.5 Autonomous Driving Algorithm Module: Bev+Transformer Intelligent Driving Algorithm
1.5.6 Autonomous Driving Algorithm Module: BEV Is Further Upgraded to Occupancy Network
1.5.7 Autonomous Driving Algorithm Module: "End-to-end" Intelligent Driving Algorithm, 2023 Best Paper Autonomous Driving General Algorithm Framework UniAD
1.5.8 Autonomous Driving Algorithm Module: "End-to-end" UniAD Large Model (1)
1.5.9 Autonomous Driving Algorithm Module: "End-to-end" UniAD Large Model (2)
1.5.10 Automated Driving Algorithm Module: The Official Version of Tesla V12 will Introduce an “End-to-End” Algorithm
1.5.11 Summary of OEM Self-Developed Intelligent Driving Algorithm (1)
1.5.12 Summary of OEM Self-Developed Intelligent Driving Algorithm (2)
1.5.13 Summary of Tier 1 Supplier Intelligent Driving Algorithm
1.5.14 Tesla's Autopilot solution Is Called the "IOS" in Autonomous Driving World
1.5.15 Third-Party Giants Expected to Build "Android" in the Automated Driving Field with Tool Chains
1.5.16 Baidu Is Committed to Enhancing the Perception Model of Autonomous Driving and Mining Long Tail Data by Using Large Model ERNIE
1.5.17 SenseTime Uses Foundation Models to Empower Autonomous Driving Perception Closed Loop and Decision-making Closed Loop, Etc.
1.5.18 Horizon Robotics Believes that Future Autonomous Driving will Eventually Move toward End-to-End Algorithms
1.5.19 Tesla Transformer Neural Network Enables Multi-Camera Data Fusion
1.5.20 Tesla FSD Deep Learning Code Ratio Increases
1.5.21 HAOMO.AI MANA System Adopts Transformer Neural Network
1.5.22 Deployment of XPeng G9 Transformer Network
1.5.23 “Xnet”-the New Generation Perception Architecture Released by Xpeng G9
1.5.24 Xpeng Self-develops Automatic Annotation System
1.5.25 End-to-end Autonomous Driving Algorithms May Replace Traditional Open Source Frameworks for Autonomous Driving Software
1.5.26 Open Source Software Platform Autonomous Driving OS Suppliers and Product List (1)
1.5.27 Open Source Software Platform Autonomous Driving OS Suppliers and Product List (2)
1.6 Intelligent Driving General Algorithm Architecture: AI Deep Learning Software Platform
1.6.1 AI Deep Learning Software Suppliers and Product Lists (1)
1.6.2 AI Deep Learning Software Suppliers and Product Lists（2）
1.6.3 Major Foundation Model Vendors at Home and Abroad
1.6.4 Emergence of Large Models Brings Great Challenges to Model Training
1.6.5 Featured Distributed Training Technology of Baidu PaddlePaddle in the Field of Foundation Model Training
1.6.6 Baidu and Geely Released the Industry’s First Knowledge-enhanced Automotive Foundation Model - Geely-Baidu·ERNIE
1.6.7 Huawei Open Dource Delf-developed AI Framework MindSpore Transformer Large Model Training Library
1.6.8 Colossal-AI Large Model Training System of Luchen Tech
1.6.9 NVIDIA CV-CUDA Open Source Library, General High-performance Image Processing Acceleration Library
1.7 Intelligent Driving General Algorithm Construction : Intelligent Driving Data Training Set
1.7.1 Why to Build Dataset? (1)
1.7.2 Why to Build Dataset? (2）
1.7.3 Why to Build Dataset? (3）
1.7.4 How does the autonomous driving training data acquisition vehicle collect data ?
1.7.5 Dataset Development Direction (1): Evolve from Single Vehicle Intelligence to Vehicle-City Fusion
1.7.6 Dataset Development Direction (2): Data Set Tasks Extend from Perception to Prediction and Planning
1.7.7 Dataset Development Direction (3): large model era, the new generation data set development direction of autonomous driving
1.7.8 Next-generation data set product : the world 's first language + self-driving full-stack open source data set-DriveLM（1）
1.7.9 Next-generation data set product : the world 's first language + self-driving full-stack open source data set-DriveLM（2）
1.7.10 Autonomous Driving Dataset Product Comparison (1）
1.7.10 Autonomous Driving Dataset Product Comparison (1）
1.7.11 Autonomous Driving Dataset Product Comparison (2）
1.7.12 Autonomous Driving Dataset Product Comparison (3）
1.7.12 Autonomous Driving Dataset Product Comparison (3）
1.7.13 Autonomous Driving Dataset Product Comparison (4）
1.7.14 Autonomous Driving Dataset Product Comparison (5）
1.7.15 Autonomous Driving Dataset Product Comparison (6）
1.7.16 Data Training Dataset Suppliers and Product List (1)
1.7.17 Data Training Dataset Suppliers and Product List（2）
1.7.18 Data Training Dataset Suppliers and Product List（3）
1.7.19 Data Training Dataset Suppliers and Product List（4）
1.7.20 Data Training Dataset Suppliers and Product List（5）
1.8 Construction of Intelligent Driving General Algorithm : Autonomous Driving System Integration and Engineering Strategy
1.8.1 Autonomous Driving Algorithm Classification
1.8.2 Autonomous Driving Perception Algorithm - Visual Perception
1.8.3 LiDAR Perception (1)
1.8.3 LiDAR Perception (2)
1.8.4 Radar Perception
1.8.5 Autonomous Driving Perception Algorithm-Multi-sensor Fusion Perception
1.8.6 Advantages and Disadvantages Comparison of Pre/ Middle/ Post Fusion
1.8.7 Autonomous Driving Perception Route-BEV Perception System
1.8.8 Autonomous Driving Perception Technology（1): BEV Transformer Large Model (1）
1.8.9 Autonomous Driving Perception Technology（1): BEV Transformer Large Model（2）
1.8.10 Autonomous Driving Perception Technology（2): Occupancy Network
1.8.11 Domestic Intelligent Driving Perception System Market Trends: BEV + Transformer Accelerate Boarding to Assist "Heavy Perception, Light Map"
1.8.12 OEM’s Perception Algorithm: Full Fusion Algorithm of RISING AUTO
1.8.13 OEM’s Perception Algorithm: Xpeng XNet Deep Visual Neural Network（BEV + Transformer）
1.8.14 OEM’s Perception Algorithm: Xpeng XNet Deep Visual Neural Network（BEV + Transformer）
1.8.15 OEMs’ Application of Autonomous Driving Perception Model
1.8.16 Tier1s’ Application of Autonomous Driving Perception Model
1.9 Intelligent Driving Terminal-cloud Integration: Data Closed-loop
1.9.1 The Development Process of High-level Autonomous Driving Evolves from the V-model-based to the Data-driven
1.9.2 Importance of Closed-loop Data for L3/L4 Autonomous Driving
1.9.3 Data Closed-loop is Key to Mass Implmentation of City NOA
1.9.4 Process of Baidu Full-link Data Closed Loop Technology
1.9.5 Baidu Full-link Data Closed Loop Solution: Autonomous Driving Toolchain
1.9.6 Momenta Flywheel Model
1.9.7 iMotion’s Data Closed Loop and Cloud Platform Network
1.9.8 Data Closed Loop Solution of Black Sesame Technologies
1.9.9 Data Closed Loop Platform of PhiGent Robotics
1.9.10 List of Autonomous Driving Data Closed-loop Providers and Products (1)
1.9.11 List of Autonomous Driving Data Closed-loop Providers and Products (2)
1.9.12 List of Autonomous Driving Data Closed-loop Providers and Products (3)
1.10 Intelligent Driving Terminal-Cloud Integration: Data Collection & Annotation
1.10.1 Development Trends of Autonomous Driving Data Collection and Labeling Market
1.10.2 Data Collection and Annotation Industry Chain: Upstream and Downstream Structure and Role
1.10.3 Data Collection & Annotation Platform: Architecture Design
1.10.4 Data Collection & Annotation Platform: Difficulties of Data Collection
1.10.5 Data Collection & Annotation Platform: Data Collection Process and Method
1.10.6 Data Collection & Annotation Platform: Data Collection & Annotation Process
1.10.7 Data Collection & Annotation Platform: Backend Simulation of Data Collection
1.10.8 Five Stages of Intelligent Driving Data Annotation Development
1.10.9 L0/L1 Stage of Intelligent Driving Data Annotation: Data Crowdsourcing
1.10.10 L0/L1 Stage of Intelligent Driving Data Annotation: Data Crowdsourcing
1.10.11 L2/L3 Stage of Intelligent Driving Data Annotation: ChatGPT and Other Large Models Introduced to Intelligent and Semi-Automated Annotation
1.10.12 L2/L3 Stage of Intelligent Driving Data Annotation: Automakers Become Mainstay in Intelligent and Semi-Automated Annotation
1.10.13 New Trend of Intelligent Driving Data Annotation: BEV & 4D Annotation
1.10.14 New Trend of Intelligent Driving Data Annotation: Data Simulation Synthesis for Corner Case Pain Points
1.10.15 New Trend of Intelligent Driving Data Annotation: End-Cloud Integrated Intelligent Driving Solution with End-to-End Large Model
1.10.16 AI Data Annotation Company Ranks in China
1.10.17 Xpeng Self-develops Automatic Annotation System
1.10.18 Appen MatrixGo Platform Data Loopback
1.10.19 Appen MatrixGo Invests in Mindtech to Expand Corner Case Applications Based on Synthetic Data
1.10.20 Example of 4D Data Annotation for Appen MatrixGo Platform
1.10.21 Haomo.ai DriveGPT Dramatically Reduces Annotation Costs
1.10.22 Huawei Octopus Data Automatic Annotation Service
1.10.23 Haitian Ruisheng Autonomous Driving Data Collection & Annotation Business (1)
1.10.24 Haitian Ruisheng Autonomous Driving Data Collection & Annotation Business (2)
1.10.25 EXCEEDDATA Vehicle-side Data Acquisition Architecture
1.10.26 EXCEEDDATA Vehicle-Cloud Link Empowering Data Acquisition and Storage
1.10.27 EXCEEDDATA Corner Cases Solution Mechanisms
1.10.28 CATARC "Automotive Big Data Algorithm Service Platform"
1.10.29 Autonomous Driving Data Collection & Annotation Tool Software Suppliers and Product List (1)
1.10.30 Autonomous Driving Data Collection & Annotation Tool Software Suppliers and Product List (2)
1.10.31 Autonomous Driving Data Collection & Annotation Tool Software Suppliers and Product List (3)
1.10.32 Autonomous Driving Data Collection & Annotation Tool Software Suppliers and Product List (4)
1.10.33 Autonomous Driving Data Collection & Annotation Tool Software Suppliers and Product List (5)
1.11 Intelligent Driving Terminal-Cloud Integration: Simulation Testing: Scenario Library
1.11.1 Data Sources for Autonomous Driving Scenario Library
1.11.2 Automatic Generation of Autonomous Driving Scene Library
1.11.3 Autonomous Driving Scene Library Format Standard
1.11.4 Building Process of Autonomous Driving Scenario Library
1.11.5 Construction of Autonomous Driving Test and Evaluation System (1)
1.11.6 Construction of Autonomous Driving Test and Evaluation System (2)
1.11.7 Suppliers and Standardization Organizations for Autonomous Driving Scenario Library (1)
1.11.8 Suppliers and Standardization Organizations for Autonomous Driving Scenario Library (2)
1.12 Intelligent Driving Terminal-Cloud Integration: Simulation Testing: Simulation Platform
1.12.1 Why Autonomous Driving Simulation Tests?
1.12.2 Intelligent Connected Vehicle Simulation Testing Tools and Platform Market Size
1.12.3 Autonomous Driving Simulation Toolchain
1.12.4 Autonomous Driving Simulation Testing Trend (1)
1.12.5 Autonomous Driving Simulation Testing Trend (2)
1.12.6 Autonomous Driving Simulation Testing Trend (3)
1.12.7 Autonomous Driving Simulation Testing Trend (4)
1.12.8 Autonomous Driving Simulation Testing Trend (5)
1.12.9 Global Mainstream Autonomous Driving Simulation Software Companies
1.12.10 Suppliers and Products of Autonomous Driving Simulation Software: Traffic Flow Simulation
1.12.11 Suppliers and Products of Autonomous Driving Simulation Software: Vehicle Simulation (1)
1.12.12 Suppliers and Products of Autonomous Driving Simulation Software: Vehicle Simulation (2)
1.12.13 Suppliers and Products of Autonomous Driving Simulation Software: Vehicle Simulation (3)
1.13 Intelligent Driving Terminal-Cloud Integration: Cloud Native and Storage Platform
1.13.1 Autonomous Driving Storage Platform
1.13.2 ETAS Ladder Platform (1)
1.13.3 ETAS Ladder Platform (2)
1.13.4 Alibaba Cloud ACK@Edge Facilitates DeepRoute.ai’s Vehicle-Cloud Integrated Cooperation
1.13.5 Alibaba Cloud ACK Cloud-Native AI Suite Powers Haomo.ai AI’s Platform
1.14 Intelligent Driving Terminal-Cloud Integration: HD Map
1.14.1 Urban NOA Becomes A New Battlefield in Passenger Car Autonomous Driving
1.14.2 Passenger Car Map Solution 1 with Urban NOA: HD Map
1.14.3 Passenger Car Map Solution 2 with Urban NOA: Light HD Map (1)
1.14.4 Passenger Car Map Solution 2 with Urban NOA: Light HD Map (2)
1.14.5 Passenger Car Map Solution 2 with Urban NOA: Cloud Map
1.14.6 Multi-source Fusion Autonomous Driving Maps can effectively Solve the Problem of Urban NOA
1.14.7 Tier 1 Advanced Assisted Driving Map Solution: Baidu Mapping Technology (1)
1.14.8 Tier 1 Advanced Assisted Driving Map Solution: Baidu Mapping Technology (2)
1.14.9 Tier 1 Advanced Assisted Driving Map Solution: DeepRoute-Driver 3.0 （1）
1.14.10 Tier 1 Advanced Assisted Driving Map Solution: DeepRoute-Driver 3.0 (2）
1.14.11 Tier 1 Advanced Assisted Driving Map Solution: MAXIEYE Hyperspace
1.14.12 Tier 1 Advanced Assisted Driving Map Solution: MAXIEYE automated mapping memory
1.14.13 Tier 1 Advanced Assisted Driving Map Solution: JueFX + Horizon Robotics
1.14.14 Tier 1 Advanced Assisted Driving Map Solution: Huawei
1.14.5 Advanced Assisted Driving Loading Solution for OEMs (1)
1.14.6 Advanced Assisted Driving Loading Solution for OEMs (2)
1.14.7 Advanced Assisted Driving Map Solution: Mainstream Map Providers Build Map in Advance
1.14.8 Advanced Assisted Driving Map Solution: Some Players Build Map Online with Algorithms (1)
1.14.9 Advanced Assisted Driving Map Solution: Some Players Build Map Online with Algorithms (2)
1.15 Intelligent Driving Assistance Software: ADAS Performance Evaluation
1.15.1 Vehicle ADAS Power Consumption Evaluation Software Requirements
1.15.2 Vehicle ADAS Performance Evaluation Tool: ViCANdo Extended Tool Set (ICVT)
1.15.3 Polelink Information Intelligent Driving Test Solution
1.15.4 List of ADAS Performance Assessment Software Vendors and Products
1.16 Intelligent Driving Assistance Software: ADAS Data Recording
1.16.1 ADAS Data Recording Requirements (Validation Test Link)
1.16.2 ADAS Data Logging Requirements (Post-delivery)
1.16.3 Definition of L3 Autonomous Driving System
1.16.4 What Are The Requirements of L3 System for Data Logging?
1.16.5 NI Completes ADAS Verification by Cooperating with Others
1.16.6 Vector's Solution for ADAS Data Logging System
1.16.7 List of Data Logging Tool Software Providers and Products (1)
1.16.8 List of Data Logging Tool Software Providers and Products (2)
1.16.9 List of Data Logging Tool Software Providers and Products (3)
2 How to Build Intelligent Cockpit Software System?
2.1 Overall Software and Hardware Architecture of Intelligent Cockpit
2.2 Basic Software: Automotive Non- RTOS (in Narrow Sense)
2.2.1 Intelligent Cockpit Operating System: System Framework
2.2.2 Intelligent Cockpit Operating System : Underlying Core OS
2.2.3 Summary of Intelligent Cockpit Underlying OS for Auto Companies
2.2.4 Market Share of Cockpit Operating Systems for New Vehicles
2.2.5 Non- RTOS (in Narrow Sense) Suppliers and Product List (1)
2.2.6 Non- RTOS (in Narrow Sense) Suppliers and Product List (2)
2.3 Basic Software: Intelligent Cockpit Operating System (in Broad Sense)
2.3.1 Intelligent Cockpit Operating System (in Broad Sense): Secondary Development Based on Underlying OS
2.3.2 Intelligent Cockpit Operating System (in Broad Sense): Evolve from Cockpit OS to Vehicle OS
2.3.3 Market Prospect of Intelligent Cockpit Operating System (in Broad Sense)
2.3.4 Tier1 Solution (1): Thundersoft Cockpit Middleware OS Software Architecture
2.3.5 Tier1 Solution (2): Banma Zhixing AliOS Intelligent Cockpit Operating System
2.3.6 Tier1 Solution (3): Huawei Harmony Cockpit Software Platform - HOS-A
2.3.7 Tier1 Solution (4): Megatronix Cockpit Solution
2.3.8 Tier1 Solution (5): ECARX Cross-platform General Operating System Software Framework - EAS Core
2.3.9 Tier1 Solution (6): E Planet Technology Venus Intelligent Vehicle Software Platform
2.3.10 List of Intelligent Cockpit General Operating System Providers and Products (1)
2.3.11 List of Intelligent Cockpit General Operating System Providers and Products (2)
2.3.12 List of Intelligent Cockpit General Operating System Providers and Products (3)
2.3.13 List of Intelligent Cockpit General Operating System Providers and Products (4)
2.3.14 List of Intelligent Cockpit General Operating System Providers and Products (5)
2.3.15 OEM Solution (1): Xpeng Motor X-EEA 3.0 Architecture
2.3.16 OEM Solution (2): SAIC Z-ONE SOA Software Platform
2.3.17 OEM Solution (3): Geely Galaxy NOS
2.3.18 OEM Solution (4): ZEEKR OS Intelligent Cockpit
2.3.19 OEM Solution (5): Great Wall Self-developed Cockpit Operating System - GC-OS
2.4 Basic Software: Hypervisor
2.4.1 Current Fused Domains Isolation Solutions for Intelligent Cockpits
2.4.2 Hypervisor Mainly Used in Vehicles
2.4.3 Application of Smart Cockpit Hypervisors in China
2.4.4 Hypervisor Alternative Solution for Intelligent Cockpits: Hard Isolation Solution
2.4.5 Advantages and Disadvantages of Intelligent Cockpit Hardware Isolation Solution
2.4.6 Prospects of Global Automotive Hypervisor Market
2.4.7 Global Hypervisor Suppliers and Their Product Lists (1)
2.4.8 Global Hypervisor Suppliers and Their Product Lists (2)
2.4.9 Global Hypervisor Suppliers and Their Product Lists (3)
2.4.10 Global Hypervisor Suppliers and Their Product Lists (4)
2.4.11 Global Hypervisor Suppliers and Their Product Lists (5)
2.4.12 Global Hypervisor Suppliers and Their Product Lists (6)
2.4.13 Chinese Hypervisor Suppliers and Their Product Lists
2.5 Application Algorithm: Application of GPT Model in Intelligent Cockpit
2.5.1 OEMs Actively Promote Chat GPT and Other Large AI Model Platforms to Get on Smart Cockpit
2.5.2 Application Field of Large AI Model in Automotive
2.5.3 GPT Model Layout of Tier 1 Suppliers (1): Generative AI Model
2.5.4 GPT Model Layout of Tier 1 Suppliers (2): Generative AI Model
2.5.5 GPT Model Layout of Tier 1 Suppliers (3): Generative AI Model
2.5.6 Large AI Model Layout Modes of OEMs
2.5.7 Application of Large AI Model in Vehicles (1)
2.5.8 Application of Large AI Model in Vehicles (2)
2.5.9 Application of Large AI Model in Vehicles (3)
2.5.10 Application of Large AI Model in Vehicles (4)
2.5.11 Application of Large AI Model in Vehicles (5)
2.5.12 Application of Large AI Model in Vehicles (6)
2.6 Application Algorithm: UI Design Software
2.6.1 Overview of Vehicle Interface Design
2.6.2 Classification of HMI Design
2.6.3 Market Prospects of Cockpit HMI UI/UX Design
2.6.4 Automakers Apply 3D Engines to Intelligent Cockpit
2.6.5 Layout and Business Model of Automotive 3D Engine Application in Intelligent Cockpit
2.6.6 Application of 3D Engine in Vehicles (1)
2.6.7 Application of 3D Engine in Vehicles (1)
2.6.8 Application of 3D Engine in Vehicles (1)
2.6.9 Application of 3D Engine in Vehicles (2)
2.6.10 Application of 3D Engine in Vehicles (3)
2.6.11 Application of 3D Engine in Vehicles (4)
2.6.12 Application of 3D Engine in Vehicles (5)
2.6.13 Application of 3D Engine in Vehicles (6)
2.6.14 Application of 3D Engine in Vehicles (7)
2.6.15 Application of 3D Engine in Vehicles (8)
2.6.16 Application of 3D Engine in Vehicles (9)
2.6.17 HMI Design Software Suppliers (1)
2.6.18 HMI Design Software Suppliers (2)
2.6.19 HMI Design Software Suppliers (3)
2.6.20 HMI Design Software Suppliers (4)
2.6.21 HMI Design Software Suppliers (5)
2.7 Application Algorithm: Voice Software
2.7.1 Overview of Human Computer Interaction
2.7.2 Overview of In-vehicle Voice Interaction Technology
2.7.3 Global and Chinese In-vehicle Voice Players
2.7.4 Market Prospects of In-vehicle Voice
2.7.5 Advanced Evolution of HMI Driven by New technologies such as AI Large Model
2.7.6 Multimodal Interactive Software Supply Trend: Shift from Single Module to Integrated Supply
2.7.7 Voice Interaction Development Trends (1): Evolve from Single Interaction Supplier to Multimodal Interaction System Supplier
2.7.8 Voice Interaction Development Trends (1): Evolve from Single Interaction Supplier to Multimodal Interaction System Supplier
2.7.9 Voice Interaction Development Trends (2): Establish A Solid Foothold in Segments and Enhance Competitive Edges
2.7.10 Voice Interaction Development Trends (3): Extend Product Chain and Integrated Layout in Supply Chain
2.7.11 Voice Interaction Development Trends (4): Pre-integration Collaboration
2.7.12 Vehicle Voice Software Suppliers and Products List (1)
2.7.13 Vehicle Voice Software Suppliers and Products List (2)
2.7.14 Vehicle Voice Software Suppliers and Products List (3)
2.7.15 Vehicle Voice Software Suppliers and Products List (4)
2.7.16 Vehicle Voice Software Suppliers and Products List (5)
2.8 Application Algorithm: Acoustics Software
2.8.1 Summary of Business Models of Acoustic Software Vendors
2.8.2 Some Automakers Self-develop Tuning Systems for A Say in Acoustics Technology
2.8.3 Exploration of Acoustic Software Business Model
2.8.4 New Requirement of Automotive Acoustics
2.8.5 Typical Case (1)
2.8.6 Typical Case (2)
2.8.7 Typical Case (3)
2.8.8 Typical Case (4)
2.8.9 Typical Case (5)
2.8.10 Ac
Companies Mentioned
- CETC iSOFT Infrastructure Software
- ZTE
- RT Thread
- Banma Zhixing
- ZLingsmart
- Kernelsoft Photon
- Aptiv
- QNX
- Xpeng
- Tesla
- LI Auto
- Chang'an
- Toyota
- Geely
- ZEEKR
- Great Wall
- SAIC Z-ONE
- Greenstone
- Baidu
- Bosch
- HoloMatric
- Technomous
- Photo
- Neusoft Reach
- Momenta
- iMotion
- Black Sesame Technologies
- PhiGent Robotics
- ETAS
- DeepRoute
- MAXIEYE
- JueFX
- Huawei
- Thundersoft
- Megatronix
- ECARX
- E Planet
- UAES
- NXP
- Dassault Systèmes
- Luxoft
- LinearX
- Kernelsoft
- HiRain
Methodology
LOADING...
