Yijing and Huawei Qiankun conduct global autonomous driving tests

Post LinkedIn

⚛️Read original on 量子位

#autonomous-driving#sensor-fusion#automotive-aihuawei-qiankunhuaweiqiankunyijing

💡See how Huawei's autonomous driving stack performs in global real-world testing scenarios.

⚡ 30-Second TL;DR

What Changed

Collaboration between Yijing and Huawei Qiankun on autonomous driving

Why It Matters

This highlights the rapid integration of AI-driven perception systems in mass-market vehicles. It signals a shift toward more rigorous, global-scale validation for autonomous driving stacks.

What To Do Next

Analyze the sensor fusion strategies used in Huawei's ADS to understand how they handle edge cases in global environments.

Who should care:Developers & AI Engineers

Key Points

•Collaboration between Yijing and Huawei Qiankun on autonomous driving
•Global real-world testing scenarios for intelligent driving
•Featured on CCTV to highlight Chinese automotive innovation

🧠 Deep Insight

AI-generated analysis for this event — not the original article.

🔑 Enhanced Key Takeaways

•The collaboration utilizes Huawei's Qiankun ADS (Advanced Driving System) 3.0, which integrates end-to-end neural network architecture for improved decision-making in complex traffic environments.
•The global testing initiative specifically targets diverse geographic challenges, including varying road markings, traffic regulations, and infrastructure standards in international markets outside of China.
•Yijing (often associated with Yijing Automotive or related intelligent driving solution providers) acts as the vehicle integration partner, focusing on the hardware-software co-design required for Qiankun's deployment.
•The CCTV 'Extraordinary Step' feature highlighted the 'human-like' driving capabilities of the system, specifically its ability to handle unprotected left turns and narrow urban intersections without high-definition maps.
•This partnership is part of a broader strategic push by Huawei to export its intelligent automotive solutions to global OEMs, moving beyond its domestic-only market strategy.

📊 Competitor Analysis▸ Show

Feature	Huawei Qiankun (ADS 3.0)	Tesla FSD (v13+)	Waymo Driver
Architecture	End-to-End Neural Network	End-to-End Neural Network	Hybrid/Modular
Map Dependency	Mapless (Lightweight)	Mapless	HD Map Dependent
Global Strategy	Partner-based (OEMs)	Direct-to-Consumer	Robotaxi Service
Hardware	LiDAR + Vision	Vision Only	LiDAR + Radar + Vision

🛠️ Technical Deep Dive

Architecture: Utilizes a unified end-to-end model that replaces traditional rule-based modules with a single deep learning framework for perception, planning, and control.
Perception: Employs General Obstacle Detection (GOD) network capable of identifying irregular objects not present in training sets.
Compute Platform: Powered by Huawei MDC (Mobile Data Center) computing units, optimized for low-latency inference of large-scale transformer models.
Mapping: Implements 'Mapless' navigation technology, relying on real-time sensor fusion to interpret road geometry rather than pre-loaded HD map data.

🔮 Future ImplicationsAI analysis grounded in cited sources

Huawei will secure at least two major non-Chinese OEM partnerships for Qiankun ADS by 2027.

The global testing initiative serves as a technical validation proof-point required to satisfy the safety and regulatory standards of international automotive manufacturers.

The 'Mapless' approach will become the industry standard for Chinese autonomous driving exports.

The success of Huawei's mapless deployment in global testing reduces the infrastructure dependency that has historically hindered the international expansion of Chinese intelligent driving systems.