DUBLIN, March 14, 2024 /PRNewswire/ — The “Software-Defined Vehicle Research Report, 2023-2024 – Industry Panorama and Strategy” report has been added to ResearchAndMarkets.com offer.
How to build a software-defined vehicle architecture (SDV) for intelligent driving?
The intelligent platform for autonomous driving can be roughly divided into four parts from bottom to top: 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 research and development links mainly involve software engineering and hardware engineering:
- Core 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 core models (BEV transformer, Occupancy Network, end-to-end neural network for autonomous driving, etc.);
- General Intelligent Driving Algorithm Training: AI Deep Learning Software Platform, Intelligent Driving Training Dataset, etc.;
- Intelligent driving terminal and cloud integration: data closed loop, data collection and labeling, simulation test (scene library, simulation platform), cloud source platform, HD map, etc.;
- Intelligent driving system integration and engineering implementation: FCW, LDW, ALC, APA/AVP, etc.
- Intelligent driving assistance software: ADAS performance assessment, 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: computer platform hardware system architecture design, vehicle chip system design, vehicle sensor system design, etc.
As for automakers, emerging automakers with strong R&D capabilities will be more inclined to build a fully independent “core kernel + chip” intelligent driving system:
- Tesla: Tesla created its own RTOS (RT Linux, written in C language) based on the Linux system. Based on this, Tesla built domain controllers, reconstructed the automotive EEA and applied its own development of FSD SoC;
- Li Car: deeply customized on the Linux kernel, Li OS will be the first to be installed on Li Auto’s all-electric models. It will also feature Li Auto’s own development SoC for intelligent driving in the future;
- NIO: SkyOS, an all-domain vehicle operating system based on the Linux kernel, is the core operating system for NIO cars. It is installed on models based on the NT3.0 platform (eg 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 SoC for intelligent driving.
Chinese operating system providers have launched open source plans.
Currently, China accelerates the pace of open source vehicle OS development:
- In 2021, Huawei HarmonyOS was fully donated to the OpenAtom Foundation to build the OpenHarmony open source project.
- In 2022, Banma Zhixing announced that AliOS Drive will effectively enable layered separation, cross-domain sharing, and open collaboration.
How to build an intelligent cockpit architecture for Software Defined Vehicles (SDV)?
Intelligent cockpit R&D links mainly include software engineering and hardware engineering:
- Basic software in the cockpit: 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 is based on QNX, and TBOX software development is based on Linux;
- Cockpit Interface Design: User Interface 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 began to be used in multimodal cockpit interaction;
- Cloud services: integrated vehicle and cloud platform, native cloud platform, information security, OTA development and operation strategy, etc.
Key topics covered:
1 How to build a software system for intelligent driving?
1.1 Overall software and hardware architecture of the intelligent cockpit
1.2 Basic software: Operating system for real-time vehicle control (OS in the narrower sense)
1.3 Basic software: Intelligent Driving Middleware (ROS, CyberRT, DDS, AutoSAR)
1.4 Core software: How to systematically build a generalized OS for autonomous driving?
1.5 Construction of universal algorithms for intelligent driving: from small models to large models
1.6 Intelligent Driving General Algorithm Architecture: AI Deep Learning Software Platform
1.7 General Construction of Intelligent Driving Algorithm : Intelligent Driving Training Data Set
1.8 Construction of a general intelligent driving algorithm: Autonomous driving system integration and engineering strategy
1.9 Terminal and cloud integration for intelligent driving: Closed-loop data
1.10 Intelligent integration of the terminal and driving cloud: data collection and notes
1.11 Terminal and Cloud Integration for Intelligent Driving: Simulation Testing: Scenario Library
1.12 Terminal and cloud integration for intelligent driving: Simulation testing: Simulation platform
1.13 Terminal and Cloud Integration for Intelligent Driving: Native Cloud and Storage Platform
1.14 Intelligent integration of terminal and driving cloud: HD map
1.15 Intelligent driver assistance software: ADAS performance assessment
1.16 Intelligent driving assistance software: ADAS data recording
2 How to build an intelligent cockpit software system?
2.1 Overall software and hardware architecture of the intelligent cockpit
2.2 Core software: automotive non-RTOS (in the narrow sense)
2.3 Basic software: Intelligent Cockpit Operating System (in a broad sense)
2.4 Basic software: hypervisor
2.5 Application algorithm: Application of the GPT model in the intelligent cockpit
2.6 Application Algorithm: User Interface Design Software
2.7 Application algorithm: Voice software
2.8 Application algorithm: software for acoustics
The mentioned companies
- CETC iSOFT Infrastructure software
- ZTE
- RT thread
- Banma Zhixing
- ZLingsmart
- Kernelsoft Photon
- Aptiv
- QNX
- Xpeng
- Tesla
- LI Car
- Chang’an
- Toyota
- Geely
- ZEEKR
- The Great Wall
- SAIC Z-ONE
- Greenstone
- Baidu
- Bosch
- HoloMatrix
- Technically
- Photography
- Neusoft Reach
- A moment
- iMotion
- Black Sesame Technologies
- PhiGent Robotics
- AGE
- DeepRoute
- MAXIEYE
- JueFX
- Huawei
- Thundersoft
- Megatronix
- ECARX
- E Planet
- UAES
- NXP
- Dassault Systemes
- Luxoft
- LinearX
- Kernelsoft
- Hi Rain
For more information on this report, visit https://www.researchandmarkets.com/r/e8yr07
About ResearchAndMarkets.com
ResearchAndMarkets.com is the world’s leading source for international market research reports and market data. We provide you with the latest data on international and regional markets, key industries, top companies, new products and the latest trends.
Media contact:
Research and markets
Laura WoodSenior manager
[email protected]
For EST office hours, call +1-917-300-0470
For USA/CAN call toll free +1-800-526-8630
For GMT office hours, call +353-1-416-8900
US Fax: 646-607-1907
Fax (outside USA): +353-1-481-1716
Logo: https://mma.prnewswire.com/media/539438/Research_and_Markets_Logo.jpg
SOURCE Research and markets
