Table of Content

1 Foundation of End-to-end Intelligent Driving Technology
1.1 Terminology and Concept of End-to-end Intelligent Driving
Terminology Explanation of End-to-end Intelligent Driving
Terminology Explanation of End-to-end Intelligent Driving
Connection and Difference between End-to-end Related Concepts

1.2 Introduction to and Status Quo of End-to-end Intelligent Driving
1.2.1 Overview
Background of End-to-end Intelligent Driving
Deduction of Impacts of AI Foundation Models on Intelligent Driving Industry Pattern
Reason for End-to-end Intelligent Driving: Business Value
Transformer Empowers Autonomous Driving
Difference between End-to-end Architecture and Traditional Architecture (1)
Difference between End-to-end Architecture and Traditional Architecture (2)
End-to-end Architecture Evolution
End-to-end Architecture Evolution
End-to-end Autonomous Driving Evolution Path
Progress in End-to-end Intelligent Driving (1)
Progress in End-to-end Intelligent Driving (2)
Progress in End-to-end Intelligent Driving (2)
Comparison between One Model and Two Model End-to-end Intelligent Driving
Performance Parameter Comparison between One Model/segmented End-to-end Systems
Significance of Introducing Multi-modal Models to End-to-end Intelligent Driving
Problems and Solutions for End-to-end Mass Production: Computing Power Supply/Data Acquisition
Problems and Solutions for End-to-end Mass Production: Team Building/Explainability
Progress and Challenges of E2E-AD: Generative World Model + Neural Network Simulator + RL Will Accelerate Innovation
Perception Layer under End-To-End Architecture

1.2.2 End-to-end Model Implementation Modes
Two Implementation Modes for End-To-End
End-To-End Implementation Modes: Imitation Learning
End-to-end Implementation Method: Reinforcement Learning
Mainstream reinforcement learning algorithms

1.2.3 End-to-end Model Verification Modes
Evaluation Methods for End-to-End Autonomous Driving Datasets
Closed Loop Benchmarking Platform for Evaluating End-To-End Autonomous Driving Systems (E2E-AD) Capabilities
Three Major Simulation Tests for End-to-end Autonomous Driving Models (2) ? HUGSIM
Three Major Simulation Tests for End-to-end Autonomous Driving Models (3) ? DriveArena

1.3 Typical End-to-End Intelligent Driving Cases
SenseTime UniAD: Path Planning-oriented AI Foundation Model Provides E2E Commercial Scenario Applications (1)
SenseTime UniAD: Path Planning-oriented AI Foundation Model Provides E2E Commercial Scenario Applications(2)
Technical Principle and Architecture of SenseTime UniAD
Technical Principle and Architecture of Horizon Robotics VAD
Technical Principle and Architecture of Horizon Robotics VADv2
VADv2 Training
Technical Principle and Architecture of DriveVLM
Li Auto Adopts MoE
MoE and STR2
Shanghai Qi Zhi Institute’s E2E-AD Model SGADS: A Safe and Generalized E2E-AD System Based on Reinforcement Learning and Imitation Learning
Shanghai Jiao Tong University’s E2E Active Learning ActiveAD Case: Breaking the Data Labeling Bottleneck of Intelligent Driving, and Data-driven
End-to-end Intelligent Driving System Based on Foundation Models

1.4 Foundation Models
1.4.1 Foundation Models Introduction
Core of End-to-end System - Foundation Models
Foundation Models (1) - Large Language Models: Application Case in Intelligent Driving
Foundation Models (2) - Vision Foundation Models: Application in Intelligent Driving
Foundation Models (2) - Vision Foundation Models: Latent Diffusion Model Framework
Foundation Models (2) - Vision Foundation Models: Wayve GAIA-1
Foundation Models (2) - Vision Foundation Models: DriveDreamer Framework
Foundation Models (3) - Large Multimodal Models: MFM
Foundation Models (3) - Large Multimodal Models: Application of GPT-4V in Intelligent Driving

1.4.2 Foundation Models: Large Multimodal Models
Development of and Introduction to Large Multimodal Models
Large Multimodal Models VS Single-modal Foundation Models (1)
Large Multimodal Models VS Single-modal Foundation Models (2)
Technology Panorama of Large Multimodal Models
Multimodal Information Representation

1.4.3 Foundation Models: Multimodal Large Language Models
Multimodal Large Language Models (MLLMs)
Architecture and Core Components of MLLMs
MLLMs - Mainstream Models
Application of MLLMs in Intelligent Driving
Clip Model
LLaVA Model

1.5 VLM & VLA
Application of Vision-Language Models (VLMs)
Development History of VLMs
Architecture of VLMs
Application Principle of VLMs in End-to-end Intelligent Driving
Application of VLMs in End-to-end Intelligent Driving
?VLM?VLA
VLA (Vision-Language-Action Model)
VLA Principle
Classification of VLA Models
VLA Is Not Yet Mature, and Waymo EMMA Is Relatively Complete Overall
Core Functions of End-to-end Multimodal Model for Intelligent Driving (EMMA)

1.6 World Models
Definition and Application
Basic Architecture
Difficulties in Framework Setting and Implementation
Video Generation Methods based on Transformer and Diffusion Model
WorldDreamer’s Technical Principle and Path
World Model May Be One of the Ideal Ways to Achieve End-to-end
Generation of Virtual Training Data
Tesla’s World Model
Nvidia
InfinityDrive: Breaking Time Limits in Driving World Models
Parameter Performance of SenseAuto InfinityDrive
SenseAuto InfinityDrive Pipeline
SenseTime DiT Architecture and Main Indicators (FID/FV) for Evaluating Video Generation

1.7 Comparison between E2E-AD Motion Planning Models
E2E-AD Trajectory Planning: Comparison between Several Classical Models in Industry and Academia
Tesla: Perception and Decision Full Stack Integrated Model
Tesla: Perception and Decision Full Stack Integrated Model
Momenta: End-to-end Planning Architecture Based on BEV Space
Horizon Robotics 2023: End-to-end Planning Architecture Based on BEV Space
DriveIRL: End-to-end Planning Architecture Based on BEV Space
GenAD: Generative End-to-end Model
GenAD: Generative End-to-end Model

1.8 VLA Model
VLA Concept
One Core of End-to-end: Large Language Models
VLA Technical Architecture and Key Technologies
Advantages of VLA (1)
Advantages of VLA (2)
Advantages of VLA (2)
Challenges in VLA Model Deployment (1)
Real-time and Memory Usage Challenges for VLA Model Deployment
Challenges in VLA Model Deployment (2)
Challenges of End-to-end Deployment - Data ( 2 )
Challenges of VLA Model Deployment - Planning Capabilities for Long Time Series Tasks

1.9 Diffusion Models
Four Mainstream Generation Models
Diffusion Model Principle
Diffusion Model Optimizes the Core Links of Autonomous Driving Trajectory Generation
Diffusion Model Optimizes Autonomous Driving Trajectory Generation
Application of Diffusion Model in the Field of Assisted Driving
Practical Application Cases of Diffusion Model

1.10 Embodied Language Models (ELM)
ELMs Accelerate the Implementation of End-to-end Solutions
ELMs Accelerate the Implementation of End-to-end Solutions
Application Scenarios (1)
Application Scenarios (2) Data Close Loop
Application Scenarios (3) Data Collecting
Application Scenarios (4) Location/ Description Labeling
Application Scenarios (5) Token Selection
Application Scenarios (6) Benchmark
Application Scenarios (7) Experiments
Application Scenarios (7) Experiments
Limitations and Positive Impacts

2 Technology Roadmap and Development Trends of E2E-AD
2.1 Technology Trends of End-to-End Intelligent Driving
Trend 1 - Paradigm Revolution in Intelligent Driving ADS: 2024 Can be Considered as the First Year of E2E-AD (E2E-AD)
Trend 2 - Major Development Frameworks of AGI: Robot and Intelligent Driving will be the Two Mainstream E2E Application Scenarios (1)
Trend 2 - Major Development Frameworks of AGI: Robot and Intelligent Driving will be the Two Mainstream E2E Application Scenarios (2)
Trend 2 - Major Development Frameworks of AGI: Robot and Intelligent Driving will be the Two Mainstream E2E Application Scenarios (3)
Trend 3: Development Direction of E2E-AD Is to Achieve Humanized Driving
Trend 4: Generative AI and E2E-AD Fused and Innovate, Scale of Data and Model Parameters Further Unleashes Potential of Basic Models (1)
Trend 4: Generative AI and E2E-AD Fused and Innovate, Scale of Data and Model Parameters Further Unleashes Potential of Basic Models (2)
Trend 5: E2E-AD Requires Higher Costs and Computing Power
Trend 6: General World Model is One of the Best Implementation Paths for Intelligent Driving (1)
Trend 6: General World Model is One of the Best Implementation Paths for Intelligent Driving (2)
Trend 6: General World Model is One of the Best Implementation Paths for Intelligent Driving (3)
Trend 7 - End-to-end Test Begins to Move from Open to Closed Loop
Trend 8: Application Ideas and Implementation Pace of Foundation Model in E2E-AD
End-to-end Trend 2: Foundation Model
End-to-end Trend 3: Zero-shot Learning

2.2 Market Trends of End-to-End Intelligent Driving
Layout of Mainstream E2E System Solutions
Comparison of End-to-end System Solution Layout between Tier 1 Suppliers (1)
Comparison of End-to-end System Solution Layout between Tier 1 Suppliers (2)
Comparison of End-to-end System Solution Layout between Tier 1 Suppliers (3)
Comparison of End-to-end System Solution Layout between Other Intelligent Driving Companies
Comparison of End-to-end System Solution Layout between OEMs (1)
Comparison of End-to-end System Solution Layout between OEMs (2)
Comparison of End-to-end System Solution Layout between OEMs (3)
Comparison of End-to-end System Solution Layout between Other Intelligent Driving Companies
Comparison of End-to-end System Solution Layout between OEMs (1)
Comparison of End-to-end System Solution Layout between OEMs (2)
Comparison of End-to-end System Solution Layout between OEMs (3)
E2E System Enables Leading OEMs to Implement Map-free City NOA on a Large Scale
Comparison 1 of NOA and End-to-end Implementation Schedules between Sub-brands of Domestic Mainstream OEMs: Changan, GWM, BYD
Comparison 2 of NOA and End-to-end Implementation Schedules between Sub-brands of Domestic Mainstream OEMs ?FAW, GAC and Geely
Comparison 3 of NOA and End-to-end Implementation Schedules between Sub-brands of Domestic Mainstream OEMs : BAIC, SAIC, Chery and Dongfeng
Comparison 4 of NOA and End-to-end Implementation Schedules between Sub-brands of Domestic Mainstream OEMs: NIO, Xpeng Motors, Li Auto, Xiaomi and Leapmotor

2.3 End-to-end Intelligent Driving Team Building
Impacts of End-to-end Foundation Models on Organizational Structure (1)
Impacts of End-to-end Foundation Models on Organizational Structure (2)
Leading People in End-to-end Intelligent Driving For Domestic OEMs and Suppliers
E2E-AD Team Building of Domestic OEMs (1): XIAOMI
End-to-end Intelligent Driving Team Building of Domestic OEMs: Baidu /Li Auto
End-to-end Intelligent Driving Team Building of Domestic OEMs: Xiaomi Auto /Baidu
End-to-end Intelligent Driving Team Building of Domestic OEMs: Li Auto
E2E-AD Team Building of Domestic OEMs (4): Li Auto
E2E-AD Team Building of Domestic OEMs (5): XPeng
End-to-end Intelligent Driving Team Building of Domestic OEMs: BYD
End-to-end Intelligent Driving Team Building of Domestic OEMs: NIO
Team Building of End-to-end Intelligent Driving Suppliers: Momenta
Team Building of End-to-end Intelligent Driving Suppliers: DeepRoute.ai
End-to-end Intelligent Driving Team Building of Domestic OEMs: Huawei
Team Building of End-to-end Intelligent Driving Suppliers: Zhuoyu Technology
Team Building of End-to-end Intelligent Driving Suppliers: Horizon Robotics


3 End-to-end Intelligent Driving Suppliers
3.1 MOMENTA
Profile
R6 Flywheel Large Model to be Released in 2025H2
One-model End-to-end Solutions (1)
One-model End-to-end Solutions (2)
End-to-end Planning Architecture
One-model End-to-end Mass Production Empowers the Large-scale Implementation of NOA in Mapless Cities
High-level Intelligent Driving and End-to-end Mass Production Customers
Mass Production and Clients

3.2 DeepRoute.ai
Product Layout and Strategic Deployment
End-to-end Layout
Difference between End-to-end Solutions and Traditional Solutions
Implementation Progress in End-to-end Solutions
DeepRoute.ai Announces Deep Cooperation with Volcano Engine
RoadAGI Platform?AI Spark
DeepRoute.ai VLA Model Architecture
End-to-end VLA Model Analysis
Designated End-to-end Mass Production Projects and VLA Model Features
Mass Production of DeepRoute.ai’s End-to-end Solutions
Hierarchical Hint Tokens
End-to-end Training Solution - DINOv2
Application Value of DINOv2 in the Field of Computer Vision
Intelligent Driving VQA Task Evaluation Data Sets
BLEU (Bi-Lingual Evaluation Understudy) and Consensus-based Image Description Evaluation (CIDEr)
Score Comparison between HoP and Huawei

3.3 Huawei
End-to-end Evolution Path
ADS 4’s All-New WEWA Architecture
Deep Integration of ADS 4 with XMC and Cloud-based Simulation Validation
ADS 4: Highway L3 Commercial Solution
End-to-End Mass Production Status
Development History of Huawei’s Intelligent Automotive Solution Business Unit
ADS 2.0 (1): End-to-end Concept and Perception Algorithm of ADS
ADS 2.0 (2): End-to-end Concept and Perception Algorithm of ADS
Summary of Huawei ADS 2.0
ADS 3.0 (1)
ADS 3.0 (2): End-to-end
ADS 3.0 (3): End-to-end
ADS 3.0 (3): ASD 3.0 VS. ASD 2.0
End-to-end Solution Application Cases of ADS 3.0 (1): STELATO S9
End-to-end Solution Application Cases of ADS 3.0 (2): LUXEED R7
End-to-end Solution Application Cases of ADS 3.0 (3): AITO
End-to-end Intelligent Driving Solutions of Multimodal LLMs
End-to-end Testing?VQA Tasks
Architecture of DriveGPT4
End-to-end Training Solution Examples
The Training of DriveGPT4 Is Divided Into Two Stages
Comparison between DriveGPT4 and GPT4V

3.4 Horizon Robotics
Profile
Main Partners
Urban Driving Assistance System HSD
Journey 6 Series Chips
UMGen: Unified Multimodal Driving Scene Generation Framework
GoalFlow: Goal Point Driven, Unlocking Future End-To-End Generative Policies
MomAD: Momentum-Aware Planning for End-To-End Autonomous Driving
DiffusionDrive: Towards Generative Multimodal End-To-End Autonomous Driving
RAD: End-To-End Reinforcement Learning Post-Training Paradigm Based On 3DGS Digital Twin World
Mass Production
End-to-end Super Drive and Its Advantages
Architecture and Technical Principle of Super Drive
Senna Intelligent Driving System (Foundation Model + End-to-end)
Core Technology and Training Method of Senna
Core Module of Senna

3.5 Zhuoyu Technology
Profile
R&D and Production
Evolution of ClixPilot End-To-End Algorithm
Architecture of End-To-End World Model
Two-Phase Training Model of End-To-End World Model
Core Functions of Generative Intelligent Driving GenDrive
Key Technologies of Generative Intelligent Driving
Mass Production of End-To-End
Two-model End-to-end Parsing
One-model Explainable End-to-end Parsing
End-to-end Mass Production Customers

3.6 NVIDIA
Profile
Hydra-MDP++: NVIDIA’s End-to-End Autonomous Driving Framework Combining Human Demonstrations and Rule-Based Expert Knowledge
World Foundation Model Development Platform ? Cosmos
Cosmos Training Paradigm
Intelligent Driving Solution
DRIVE Thor
Basic Platform for Intelligent Driving: NVIDIA DriveOS
Core Design Philosophy of NVIDIA Multicast
Drive Thor
Latest End-to-end Intelligent Driving Framework: Hydra-MDP
Self-developed Model Architecture: Model Room
IM, NVIDIA and Momenta Collaborate to Create a Production-ready Intelligent Driving Solution Based on Thor
Latest End-to-end Intelligent Driving Framework: Hydra-MDP

3.7 Bosch
Vertical and Horizontal Assisted Driving Solution
Urban Assisted Driving Solution Based on End-to-End Model
End-to-End Mass Production Status
Intelligent Driving China Strategic Layout (1)
Based on the End-to-end Development Trend, Bosch Intelligent Driving initiates the Organizational Structure Reform
After Launching the BEV+Transformer High-level Intelligent Driving Solution, Bosch Accelerates Its End-to-end Intelligent Driving Layout
Intelligent Driving Algorithm Evolution Planning

3.8 Baidu
DriVerse: Novel Navigation World Model Enabled by Multimodal Trajectory Prompts and Motion Alignment
Profile of Apollo
Strategic Layout in the Field of Intelligent Driving
Two-model End-to-end: Adopting Strategy of Segmented Training before Joint Training
Production Models Based on Two-model End-to-end Technology Architecture: Jiyue 07
Baidu Auto Cloud 3.0 Enables End-to-end Systems from Three Aspects

3.9 SenseAuto
Profile
Evolution of Intelligent Driving End-To-End Algorithm
Architecture of R-UniAD
R-UniAD Practical Demonstration: Complex Scenario Mining, 4D Simulation Reproduction, Reinforcement Learning, Generalization Verification
Kaiwu World Model 2.0
Mass Production
UniAD End-to-end Solution
DriveAGI: The Next-generation Intelligent Driving Foundation Model and Its Advantages
DiFSD: SenseAuto’s End-to-end Intelligent Driving System That Simulates Human Driving Behavior
DiFSD: Technical Interpretation

3.10 QCraft
Profile
"Safe End-to-End" Architecture
"Safe End-to-End" Data and Model Training Closed Loop
Driven-by-QCraft Mid-to-High Level ADAS Solutions
End-to-End Mass Production Status
"Driven-by-QCraft" High-level Intelligent Driving Solution
End-to-end Layout
Advantages of End-to-end Layout

3.11 Wayve
Profile
Advantages of AV 2.0
GAIA-1 World Model - Architecture
GAIA-1 World Model - Token
GAIA-1 World Model - Generation Effect
LINGO-2

3.12 Waymo
Waymo Foundation Model
End-to-end Multimodal Model for Intelligent Driving (EMMA)
EMMA Analysis: Multimodal Input
EMMA Analysis: Defining Driving Tasks as Visual Q&A
EMMA Analysis: Introducing Thinking Chain Reasoning to Enhance Interpretability
Limitations of EMMA

3.13 GigaAI
Profile
World Model Evolution
4D Generative World Model Layered Architecture
World Model Implementation
ReconDreamer
DriveDreamer
DriveDreamer4D

3.14 LightWheel AI
Profile
Data Requirements for End-to-End Architecture
Tsinghua x LightWheel AI: Autonomous Driving World Model for Generating and Understanding Accident Scenarios
Core Technology Stack: Real2Sim2Real + Realism Validation
Data Annotation and Synthetic Data

3.15 PhiGent Robotics
Profile
Full-Domain End-To-End Driving Assistance Solution PhiGo Max
Detailed Explanation of Progressive One-Model End-To-End Solution Based on End-To-End Technology Paradigm
Detailed Explanation of End-To-End Technology

3.16 Nullmax
Profile
MaxDrive Driving Assistance Solution
Next-Generation Autonomous Driving Technology - Nullmax Intelligence
End-To-End Technology Architecture
End-To-End Data Platform
HiP-AD: Nullmax’s End-To-End Autonomous Driving Framework Based on Multi-Granularity Planning and Deformable Attention
Mass Production

3.17 Mobileye
Profile
CAIS (Composite AI System) Route
Surround ADAS?
SuperVision?/Chauffeur
Production

3.18 Motovis
Profile
Full-stack End-to-end Intelligent Driving System
Production


4 End-to-end Intelligent Driving Layout of OEMs
4.1 Xpeng’s End-to-end Intelligent Driving Layout
End-to-end System Evolution Path
World Foundation Model
Core Technical Approach of the World Foundation Model
Cloud Model Factory
Three Phased Achievements in World Foundation Model Development
End-to-end System (1): Architecture
End-to-end System (2): Intelligent Driving Model
End-to-end System (3): AI+XNGP
End-to-End System (4): Organizational Transformation
Data Collection, Annotation and Training

4.2 Li Auto’s End-to-end Intelligent Driving Layout
End-To-End Evolution
From E2E+VLM Dual System to MindVLA
Architecture of MindVLA Model
Key Technology Point 1 of MindVLA: Great 3D Physical Space Understanding Capability
Key Technology Point 2 of MindVLA: Combination with LLM
Key Technology Point 3 of MindVLA: Combination of Diffusion and RLHF
Key Technology Point 4 of MindVLA: World Model and INVADE-Accelerated Reinforcement Learning
End-to-end Solutions (1): Iteration of System 1
End-to-end Solutions (2): System 1 (end-to-end model) + System 2 (VLM)
End-to-end Solutions (3): Next-generation Intelligent Driving Technology Architecture
End-to-end Solutions (4): DriveMLM: Architecture
End-to-end Solutions (5): DriveMLM: Rendering Effects
End-to-end Solutions (6): DriveVLM: Processing of BEV and Text Features
End-to-end Solutions (7)?L3 Intelligent Driving
End-to-end Solutions (8): Build a Complete Foundation Model from AD Max 3.0
Technical Layout: Chip
Technical Layout: Data Closed Loop

4.3 Tesla’s End-to-end Intelligent Driving Layout
Interpretation of the 2024 AI Conference
Development History of AD Algorithms
End-to-end Process 2023-2024
Development History of AD Algorithms (1)?Focus on Perception
Development History of AD Algorithms (2): Shadow Mode
Development History of AD Algorithms (3): Introduction of Occupancy Network
Development History of AD Algorithms (4): Occupancy Network
Development History of AD Algorithms (5): HydraNet
Development History of AD Algorithms (6)?FSD V12
Tesla: Core Elements of the Full-stack Perception and Decision Integrated Model
"End-to-end" Algorithms
World Models
Data Engines
Dojo Supercomputing Center: Overview
Dojo Supercomputing Center: D1 Chip-integrated Training Tile
Dojo Supercomputing Center: Computing Power Development Planning
Zeron Won Runner-up in International End-to-End Ground Challenge

4.4 Zeron’s End-to-end Intelligent Driving Layout
Profile
End-to-end Intelligent Driving System Based on Foundation Models
Advantages of End-to-end Driving System

4.5 Geely & ZEEKR’s End-to-end Intelligent Driving Layout
One-Model End-to-End Large Model
L3 Intelligent Driving Technology Architecture
“Qianli Haohan” Advanced Intelligent Driving Solutions
Geely’s ADAS Technology Layout: Geely Xingrui Intelligent Computing Center
Xingrui AI Foundation Model
Application of Geely’s Intelligent Driving Foundation Model Technology
Zeekr Overview
ZEEKR’s End-to-end System: Two-model Solution
ZEEKR Officially Released End-to-end Plus
Examples of Models with ZEEKR’s End-to-end System

4.6 Xiaomi Auto’s End-to-end Intelligent Driving Layout
Profile
End-to-End VLA Autonomous Driving Solution Orion
Analysis of the ORION Framework
Physical World Modeling Architecture
Multi-stage End-to-end Modeling Of Three Layers
Long Video Generation Framework?MiLA
End-to-end Technology Enables All-scenario Intelligent Driving from Parking Spaces to Parking Spaces
Road Foundation Models Build HD Maps through Road Topology
New-generation HAD Accesses End-to-end System
End-to-end Technology Route?end-to-end +VLM

4.7 NIO’s End-to-end Intelligent Driving Layout
Intelligent Driving R&D Team Reorganization with an Organizational Structure Oriented Towards End-to-end System
From Modeling to End-to-end, World Models Are the Next
World Model End-to-end System – NWM (NIO World Model)
Intelligent Driving Architecture: NADArch 2.0
End-to-end R&D Tool Chain
Imagination, Reconstruction and Group Intelligence of World Models
Nsim (NIO Simulation)
Software and Hardware Synergy Capabilities Continue to Strengthen, Moving towards the End-to-end System Era

4.8 Changan Automobile’s End-to-end Intelligent Driving Layout
Beidou Tianshu 2.0 - Tianshu Intelligent Driving
Tianshu Intelligent Driving Software Architecture
Brand Layout
ADAS Strategy: "Beidou Tianshu"
End-to-end System (1)?BEV+LLM+GoT
Production Models with End-to-end System: Changan NEVO E07
Production Models with End-to-end System: Changan NEVO E07

4.9 Mercedes-Benz’s End-to-end Intelligent Driving Layout
Mercedes-Benz and Momenta team up to develop driver assistance systems
Brand New "Vision-only Solutions without Maps, L2++ All-scenario High-level Intelligent Driving Functions"
Brand New Self-developed MB.OS
Cooperation with Momenta

4.10 Chery’s End-to-end Intelligent Driving Layout
Profile of ZDRIVE.AI
Five Intelligent Driving Technologies
E2E Autonomous Driving Architecture and Advantages
E2E Autonomous Driving Digital Assessment Technology
Falcon Intelligence Driving E2E Solution
Falcon Solution Models and Future Planning
Chery’s End-to-end System Development Planning

4.11 GAC
X-Soul Zhixing E2E Embodied Reasoning Model Architecture
Core Technologies
Intelligent Diviring Product Platform

4.12 Leapmotor
E2E Intelligent Driving
E2E Intelligent Driving Application Scenario

4.13 IM Motors
Iteration History of Intelligent Driving System
Cooperation with Momenta
IM AD E2E 2.0 Large Model
IM AD E2E 2.0 Intelligent Driving Large Model Technology
IM AD E2E 2.0 Intelligent Driving Large Model Application Scenario

4.14 Hongqi
Hongqi Sinan Intelligent Driving Technology Architecture
Sinan E2E Large Model Technology
Sinan Intelligent Driving Solution
Sinan Intelligent Driving Solution Models and Future Planning