China Autonomous Driving Algorithm Research Report, 2023
  • Jan.2023
  • Hard Copy
  • USD $4,200
  • Pages:220
  • Single User License
    (PDF Unprintable)       
  • USD $4,000
  • Code: WWJ003
  • Enterprise-wide License
    (PDF Printable & Editable)       
  • USD $6,000
  • Hard Copy + Single User License
  • USD $4,400
      

Autonomous Driving Algorithm Research: BEV Drives Algorithm Revolution, AI Large Model Promotes Algorithm Iteration

The core of the autonomous driving algorithm technical framework is divided into three parts: environment perception, decision planning, and control execution.

Environment perception: convert sensor data into machine language of the scenario where the vehicle is located, which can include object detection, recognition and tracking, environment modeling, motion estimation, etc.;

Decision planning: Based on the output results of perception algorithm, the final behavioral action instructions are given, including behavioral decisions (vehicle following, stopping and overtaking), action decisions (car steering, speed, etc.), path planning, etc.;

Control actuation: according to the output results of decision-making level, the underlying modules are mobilized to issue instructions to the core control components such as accelerator and brake, and promote vehicle to drive according to the planned route.

BEV drives algorithm revolution
In recent years, BEV perception has received extensive attention. BEV model mainly provides a unified space to facilitate the fusion of various tasks and sensors. It has following advantages:

BEV unifies the multimodal data processing dimension and makes multimodal fusion easier
The BEV perception system converts the information obtained from multiple cameras or radars to a bird's-eye view, and then do tasks such as object detection and instance segmentation, which can more intuitively display the dimension and direction of objects in BEV space.

In 2022, Peking University & Ali proposed a fusion framework of LiDAR and vision - BEVFusion. The processing of radar point clouds and image processing are carried out independently, using neural networks to encode, project to a unified BEV space, and then merge the two in BEV space.

自驾算法 1.png

Realize timing information fusion and build 4D space
In the 4D space, the perception algorithm can better complete the perception tasks such as speed measurement, and can transmit the results of motion prediction to the decision and control module.

PhiGent Robotics proposed BEVDet4D in 2022, which is a version based on BEVDet to increase timing fusion. BEVDet4D extends BEVDet by retaining intermediate BEV features of past frames, and then fuses features by aligning and splicing with the current frame, so that time clues can be obtained by querying two candidate features.

自驾算法 2.png

Imagine occluded objects to realize object prediction

In the BEV space, the algorithm can predict the occluded area based on prior knowledge, and imagine whether there are objects in the occluded area.

FIERY, proposed by Wayve in cooperation with the University of Cambridge in 2021, is an end-to-end road dynamic object instance prediction algorithm that does not rely on high-precision maps and is only based on aerial views of monocular cameras.

自驾算法 3.png

Promoting development of an end-to-end autonomous driving framework

In the BEV space, perception and prediction can be directly optimized end-to-end through neural networks in a unified space, and the results can be obtained at the same time. Not only the perception module, but also the BEV-based planning decision-making module is also the direction of academic research.
 
In 2022, autonomous driving team of Shanghai Artificial Intelligence Laboratory and the team of associate professor Yan Junchi of Shanghai Jiao Tong University collaborated on paper ST-P3 to propose a spatiotemporal feature learning solution that can simultaneously provide a set of more representative features for perception, prediction and planning tasks.

自驾算法 4.png

AI large model drives algorithm iteration

After 2012, deep learning algorithms are widely applied in autonomous driving field. In order to support larger and more complex AI computing needs, AI large models with the characteristics of "huge data, huge computing power, and huge algorithms" were born, which accelerated the iteration speed of algorithms.

Large Model and Intelligent Computing Center

In 2021, HAOMO.AI launched research and landing attempts on large-scale Transformer model, and then gradually applied it on a large scale in projects including multi-modal perception data fusion and cognitive model training. In December 2021, HAOMO.AI released autonomous driving data intelligence system MANA (Chinese name "Snow Lake"), which integrates perception, cognition, labeling, simulation, computing and other aspects. In January 2023, HAOMO.AI together with Volcano Engine unveiled MANA OASIS, a supercomputing center with a total computing power of 670 PFLOPS. After deploying HAOMO.AI's training platform, OASIS can run various applications including cloud large-scale model training, vehicle-side model training, annotation, and simulation. With the help of MANA OASIS, the five major models of HAOMO.AI have ushered in a new appearance and upgrade.

自驾算法 5.png

In August 2022, based on Alibaba Cloud intelligent computing platform, Xpeng Motors built an autonomous driving intelligent computing center "Fuyao", which is dedicated to training of autonomous driving models. In October 2022, Xpeng also announced the introduction of Transformer large model.

自驾算法 6_副本.png

In November 2022, Baidu released Wenxin Big Model. Leveraging more than 1 billion parameters, it recognizes thousands of objects, helping to enlarge the scope of semantic recognition. At present, it is mainly used in three aspects: distance vision, multimodality and data mining.

自驾算法 7_副本.png

1. Overview of Autonomous Driving Algorithms
1.1 Overview of Autonomous Driving Algorithms 
1.1.1 Overview of Environment Perception Algorithms - Vision
1.1.2 Overview of Environment Perception Algorithms - LiDAR
1.1.3 Overview of Environment Perception Algorithms - Radar
1.1.4 Overview of Environment Perception Algorithms - Multi-Sensor Fusion
1.2 Overview of Decision Planning and Control Actuation Algorithms 
1.3 Development of Neural Networks 
1.4 Autonomous Driving Algorithm Supply Mode

2. Research on Chip Vendor Algorithm
2.1 Huawei
2.1.1 Smart Vehicle Solutions Department 
2.1.2 ADS Autonomous Driving Full-Stack Solution 
2.1.3 Core Algorithms 
2.1.4 Autonomous Driving Algorithm Development Plan and Ecological Partners
2.2 Horizon Robotics
2.2.1 Profile 
2.2.2 Cooperation Model 
2.2.3 On-board Computing Platform and Monocular Front-View Solution Algorithm 
2.2.4 Autonomous Driving Perception Algorithm Design 
2.2.5 Core Algorithm Model 
2.2.6 Pilot Assisted Driving Solution and Super Driving Solution Algorithm 
2.2.7 Software Open API 
2.2.8 Mass Production Results and Algorithm Planning 
2.2.9 Cooperation
2.3 Black Sesame
2.3.1 Profile 
2.3.2 Perception Algorithm 
2.3.3 Latest Algorithm Achievements
2.3.4 Shanhai Tool Chain 
2.3.5 Partners 
2.3.6 Cooperation
2.4 Genesys Microelectronics
2.5 Mobileye
2.5.1 Profile 
2.5.2 Object Recognition Technology 
2.5.3 Chip Algorithm Development Process 
2.5.4 Vision Algorithms 
2.5.5 Current Development and Cooperation
2.6 Qualcomm Arriver
2.6.1 Intro of Arriver 
2.6.2 Arriver Visual Perception Algorithm
2.7 NXP
2.8 NVIDIA
2.8.1 Profile 
2.8.2 Cooperation Model 
2.8.3 Autonomous Vehicle Software Stack 
2.8.4 Perception Algorithm 
2.8.5 Perception Algorithm Model 
2.8.6 Latest Cooperation and Partners

3. Research on Tier 1 & Tier 2 Algorithm
3.1 Momenta
3.1.1 Profile 
3.1.2 Core Technology and Products 
3.1.3 Application of Momenta Algorithm 
3.1.4 Cooperation
3.2 Nullmax
3.2.1 Profile 
3.2.2 Visual Perception Module and Product Landing Process 
3.2.3 Introduction to the Latest Visual Perception Algorithm
3.2.4 The Landing Process of Algorithm Products 
3.2.5 Cooperation and Development Plan
3.3 ArcSoft
3.3.1 Profile 
3.3.2 ADAS Technology 
3.3.3 BSD and AVM Technologies 
3.3.4 One-Stop Vehicle Vision Solution 
3.3.5 Recent Dynamics and Major Customers 
3.4 JueFX
3.4.1 Profile 
3.4.2 Visual Feature Fusion Positioning Solution 
3.4.3 Development History of BEV Perception Technology 
3.4.4 LiDAR Fusion Location Solution 
3.4.5 LiDAR-based Fusion Solution 
3.4.6 Cooperation
3.5 ThunderSoft
3.6 Holomatic
3.6.1 Profile 
3.6.2 HoloPilot and Its Main Algorithms 
3.6.3 HoloParking and Its Main Algorithms 
3.6.4 Middleware 
3.7 Enjoy Move
3.7.1 Profile 
3.7.2 Autonomous Driving Software 
3.7.3 Cooperation 
3.8 Haomo.ai
3.8.1 Profile 
3.8.2 Product Portfolio
3.8.3 Latest Dynamics
3.8.4 MANA system 
3.8.5 MANA System - Vision, LiDAR Perception Module 
3.8.5 MANA System - Fusion Sensing Module 
3.8.5 MANA System - Cognitive Module 
3.8.6 Evolution of Perception 
3.8.7 Evolution of Cognitive Abilities 
3.8.8 New Technology Practice 
3.8.9 Recent Algorithm Achievements
3.9 Huanyu Zhixing
3.9.1 Profile
3.9.2 Autonomous Driving Software 
3.9.3 Athena 5.0 
3.9.4 Development Achievements and Planning
3.10 Valeo
3.10.1 Profile
3.10.2 Typical Algorithm Models
3.11 StradVision
3.11.1 Profile 
3.11.2 Vision Product Category & Customers & Timeline 
3.11.3 Autonomous Driving Algorithm 
3.11.4 Development Trends of Vision Products

4. Algorithm Research of Emerging Automakers and OEMs  
4.1 Tesla 
4.1.1 Profile
4.1.2 Tesla Algorithm 
4.1.3 Multi-camera Fusion Algorithm 
4.1.4 Environment Awareness Algorithm 
4.1.5 Latest Planning and Decision-making Algorithm 
4.2 NIO 
4.2.1 Profile
4.2.2 Evolution of NIO Autonomous Driving System 
4.2.3 Comparison of NIO Pilot System and NAD System 
4.3 Li Auto
4.3.1 Profile
4.3.2 Intelligent Driving Route 
4.3.3 Algorithm History 
4.3.4 AD Max Intelligent Driving Algorithm Architecture 
4.3.5 Layout in Intelligent Driving 
4.3.6 Future Development Plan
4.4 Xpeng 
4.4.1 Profile
4.4.2 Algorithm and Autonomous Driving Ability Evolution Route 
4.4.3 Autonomous Driving Algorithm Architecture 
4.4.4 New Perception Architecture 
4.4.5 Data Collection, Labeling and Training 
4.5 Rising Auto 
4.5.1 Profile 
4.5.2 RISING PILOT 
4.5.3 Full Fusion Algorithm 
4.5.4 Full Fusion Algorithm: Application Effect
4.6 Leapmotor
4.6.1 Profile
4.6.2 Full Domain Self-Research 
4.6.3 Algorithm Capabilities and Future Planning
4.7 ZEEKR
4.7.1 Profile
4.7.2 ZEEKR's Mobileye Solution 
4.7.3 Cooperation between ZEEKR and Waymo and Self-Developed Algorithm Solution
4.8 BMW 
4.8.1 Profile
4.8.2 Algorithms for BMW 
4.8.3 Cooperation in Autonomous Driving
4.9 SAIC 
4.9.1 SAIC Motor Autonomous Driving Layout 
4.9.2 Introduction to Z-ONE Tech
4.9.3 Z-ONE Tech Computing Platform 
4.9.4 SAIC Artificial Intelligence Laboratory
4.10 General Motors 
4.10.1 General Motors Autonomous Driving Layout 
4.10.2 Introduction to Cruise 
4.10.3 Cruise perception Algorithm 
4.10.4 Cruise Decision Algorithm 
4.10.5 Cruise Autonomous Driving Development Tool Chain 
4.10.6 Cruise's Robotaxi and Future Plans

5. Research on Robtaxi Algorithm for L4 Autonomous Driving
5.1 Baidu Apollo 
5.1.1 Profile 
5.1.2 Driverless Technology Architecture History 
5.1.3 Introduction to Perception Algorithm 
5.1.4 Autonomous Vehicle Positioning Technology 
5.1.5 Latest Highlights Technology
5.2 Pony.ai
5.2.1 Profile 
5.2.2 Main Business and Business Model 
5.2.3 Core Technology and the Latest Autonomous Driving System Configuration 
5.2.4 Sensor Fusion Solution 
5.2.5 Cooperation
5.3 WeRide
5.3.1 Profile 
5.3.2 WeRide One 
5.3.3 Algorithm Modules for WeRide One 
5.3.4 Cooperation
5.4 Deeproute.ai
5.4 Deeproute.ai 
5.4.1 Profile
5.4.2 Technology 
5.4.3 Self-Developed Algorithm 
5.4.4 Cooperation and Latest Dynamics
5.5 QCraft
5.5.1 Profile 
5.5.2 Products 
5.5.3 Hyperfusion Perception Solution
5.5.4 Prediction Algorithm 
5.5.5 Planning Algorithm 
5.5.6 Classical Algorithm Model
5.5.7 Cooperation
5.6 UISEE Technology
5.6.1 Profile 
5.6.2 U-Drive Intelligent Driving System 
5.6.3 Visual Positioning Technology 
5.6.4 Latest Algorithm
5.6.5 R & D Planning and Partners
5.7 AutoX
5.7.1 Profile 
5.7.2 Self-Driving Technology 
5.7.3 Self-Driving Fusion Perception System xFusion
5.8 DiDi Autonomous Driving
5.8.1 Profile
5.8.2 Autonomous Driving Technology
5.9 Waymo
5.9.1 Profile
5.9.2 Sensor Product Portfolio
5.9.3 Technology 
5.9.4 Behavior Prediction Algorithm 
5.9.5 Latest News

6. Development Trend of Autonomous Driving Algorithms 

6.1 Algorithm Trend I
6.2 Algorithm Trend II
6.3 Algorithm Trend III 
6.4 Algorithm Trend IV 
6.5 Algorithm Trend V
6.6 Algorithm Trend VI 
6.7 Algorithm Trend VII
 

AI/AR Glasses Industry Research Report, 2025

ResearchInChina released the " AI/AR Glasses Industry Research Report, 2025", which deeply explores the field of AI smart glasses, sorts out product R&D and ecological layout of leading domestic a...

Global and China Passenger Car T-Box Market Report 2025

T-Box Research: T-Box will achieve functional upgrades given the demand from CVIS and end-to-end autonomous driving ResearchInChina released the "Global and China Passenger Car T-Box Market Report 20...

Automotive Microcontroller Unit (MCU) Industry Report, 2025

Research on automotive MCUs: the independent, controllable supply chain for automotive MCUs is rapidly maturing Mid-to-high-end MCUs for intelligent vehicle control are a key focus of domestic produc...

Automotive LiDAR Industry Report, 2024-2025

In early 2025, BYD's "Eye of God" Intelligent Driving and Changan Automobile's Tianshu Intelligent Driving sparked a wave of mass intelligent driving, making the democratization of intelligent driving...

Software-Defined Vehicles in 2025: SOA and Middleware Industry Research Report

Research on automotive SOA and middleware: Development towards global SOA, cross-domain communication middleware, AI middleware, etc. With the implementation of centrally integrated EEAs, OEM softwar...

Global and Chinese OEMs’ Modular and Common Technology Platform Research Report, 2025

Modular platforms and common technology platforms of OEMs are at the core of current technological innovation in automotive industry, aiming to enhance R&D efficiency, reduce costs, and accelerate...

Research Report on the Application of AI in Automotive Cockpits, 2025

Cockpit AI Application Research: From "Usable" to "User-Friendly," from "Deep Interaction" to "Self-Evolution" From the early 2000s, when voice recognition and facial monitoring functions were first ...

Analysis on Li Auto’s Layout in Electrification, Connectivity, Intelligence and Sharing, 2024-2025

Mind GPT: The "super brain" of automotive AI        Li Xiang regards Mind GPT as the core of Li Auto’s AI strategy. As of January 2025, Mind GPT had undergone multip...

Automotive High-precision Positioning Research Report, 2025

High-precision positioning research: IMU develops towards "domain controller integration" and "software/hardware integrated service integration" According to ResearchInChina, in 2024, the penetration...

China Passenger Car Digital Chassis Research Report, 2025

Digital chassis research: Local OEMs accelerate chassis digitization and AI   1. What is the “digital chassis”? Previously, we mostly talked about concepts such as traditional chassis, ch...

Automotive Micromotor and Motion Mechanism Industry Report, 2025

Automotive Micromotor and Motion Mechanism Research: More automotive micromotors and motion mechanisms are used in a single vehicle, especially in cockpits, autonomous driving and other scenarios. Au...

Research Report on AI Foundation Models and Their Applications in Automotive Field, 2024-2025

Research on AI foundation models and automotive applications: reasoning, cost reduction, and explainability Reasoning capabilities drive up the performance of foundation models. Since the second ha...

China's New Passenger Cars and Suppliers' Characteristics Research Report, 2024-2025

Trends of new cars and suppliers in 2024-2025: New in-vehicle displays are installed, promising trend of AI and cars is coming  ResearchInChina releases the China's New Passenger Cars and Suppli...

Global and China Skateboard Chassis Industry Report, 2024-2025

Skateboard chassis research: already used in 8 production models, and larger-scale production expected beyond 2025 Global and China Skateboard Chassis Industry Report, 2024-2025 released by ResearchI...

Two-wheeler Intelligence and Industry Chain Research Report, 2024-2025

Research on the two-wheeler intelligence: OEMs flock to enter the market, and the two-wheeler intelligence continues to improve This report focuses on the upgrade of two-wheeler intelligence, analyz...

Automotive MEMS (Micro Electromechanical System) Sensor Research Report, 2025

Automotive MEMS Research: A single vehicle packs 100+ MEMS sensors, and the pace of product innovation and localization are becoming much faster. MEMS (Micro Electromechanical System) is a micro devi...

Intelligent Vehicle Cockpit-driving Integration (Cockpit-driving-parking) Industry Report, 2024-2025

Cockpit-driving integration is gaining momentum, and single-chip solutions are on the horizon   The Intelligent Vehicle Cockpit-driving Integration (Cockpit-driving-parking) Industry Repor...

Automotive TSP and Application Service Research Report, 2024-2025

TSP Research: In-vehicle connectivity services expand in the direction of cross-domain integration, all-scenario integration and cockpit-driving integration TSP (Telematics Service Provider) is mainl...

2005- www.researchinchina.com All Rights Reserved 京ICP备05069564号-1 京公网安备1101054484号