WeRide Wins 6th Consecutive China Intelligent Driving Competition

💡See how WeRide maintains dominance in autonomous driving benchmarks through consistent algorithmic performance.
⚡ 30-Second TL;DR
What Changed
Achieved six consecutive wins in the China Intelligent Driving Competition
Why It Matters
This consistent success validates WeRide's algorithmic robustness and sensor fusion strategies in real-world urban driving environments.
What To Do Next
Analyze WeRide's publicly available technical whitepapers to understand their approach to edge-case handling in urban autonomous driving.
🧠 Deep Insight
Web-grounded analysis with 11 cited sources.
🔑 Enhanced Key Takeaways
- •The latest competition round in Tianjin introduced Parking-to-Parking Navigation on ADAS (P2P NOA) as a new scoring criterion, alongside evaluations of automatic parking exit, gate passage, and complex public road navigation, with deductions for human takeovers.
- •WeRide's winning WRD 3.0 system, co-developed with Bosch, utilizes a one-stage end-to-end large model that unifies driving and parking scenarios, a departure from traditional modular solutions that can suffer from data fragmentation.
- •The WRD 3.0 system has secured mass-production design appointments for over 30 vehicle types from major OEMs like Chery Automobile and GAC Group, with 2026 being a pivotal year for its large-scale commercial deployment.
- •WeRide is a dual primary listed company on Nasdaq and the Hong Kong Stock Exchange, holding autonomous driving permits in eight markets across 12 countries, including China, the UAE, Singapore, France, Switzerland, Saudi Arabia, Belgium, and the US.
- •The victory was achieved using a Chery Exeed Sterra ES vehicle equipped with the WeRide Driving (WRD 3.0) system.
🛠️ Technical Deep Dive
- WeRide's WRD 3.0 is a one-stage end-to-end large model designed to cover both driving and parking scenarios, aiming to overcome data fragmentation and inconsistent decision-making issues found in modular solutions.
- The system is capable of generating precise and stable driving trajectories in low-speed parking and proficiently handling complex interactions with other vehicles, VRUs (Vulnerable Road Users), and various traffic participants in high-speed and intricate urban road conditions.
- It supports both high-precision map systems and map-less/light-map systems, enabling vehicles to navigate effectively using multi-sensor data and capable of real-time map construction.
- WeRide employs a hybrid approach that combines a deterministic overlay with an end-to-end model to balance adaptability, reliability, safety, and transparency.
- WRD 3.0 is adaptable across major compute platforms, including NVIDIA DRIVE Orin-X and Orin-Y, as well as Qualcomm SA8650.
- The company utilizes its WeRide GENESIS simulation platform for closed-loop data iteration and training optimization, enhancing the generalization capability and decision-making consistency of its AI foundation models.
🔮 Future ImplicationsAI analysis grounded in cited sources
⏳ Timeline
📎 Sources (11)
Factual claims are grounded in the sources below. Forward-looking analysis is AI-generated interpretation.
Weekly AI Recap
Read this week's curated digest of top AI events →
👉Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: 量子位 ↗