QCraft Demonstrates Urban NOA on Qualcomm's Latest Snapdragon Ride SoC, Targets 2026 Global Mass Production

At Qualcomm's Automotive Technology and Cooperation Summit, attendees rode in SA8650P-equipped production vehicles running QCraft's urban NOA, marking the latest milestone since the partnership formed in 2025.

WUXI, China--(BUSINESS WIRE)--QCraft and Qualcomm gave attendees at the 2026 Qualcomm Automotive Technology and Cooperation Summit the opportunity to experience QCraft’s urban NOA (Navigate-on-Autopilot) solution in SA8650P-equipped production vehicles, marking a key step toward global mass production in 2026.

Held June 5, the summit marked the latest milestone since QCraft and Qualcomm formed a strategic partnership in September 2025. In under a year, QCraft has completed development and on-road validation of highway and urban NOA on Qualcomm’s SA8775P and SA8650P platforms, with global delivery planned for 2026. A higher-compute solution based on Qualcomm’s QAM8797P platform is now in joint development.

During the summit’s live urban test rides, SA8650P-equipped vehicles handled unprotected left turns, mixed pedestrian-vehicle traffic, tunnels, transitions between main and side roads and congested maneuvering with smooth, human-like control. “QCraft’s development on the Snapdragon Ride™ platform has entered the fast lane toward mass production,” said CTO Dr. Dong Li, who delivered a keynote on the shift “from autonomous driving to general-purpose physical AI.”

Mass production at scale

QCraft’s QPilot assisted-driving solution has now shipped on nearly 30 production models, with more than 50 additional models expected in 2026. Across its fleet, the system has supported more than 3.5 billion user-driven kilometers and over 100 million parking-assist uses, while maintaining an AEB false-trigger rate of less than once per 500,000 kilometers. QCraft estimates the technology helps users avoid more than 146,000 potential accidents each year, underscoring the company’s focus on bringing safe, scalable assisted driving from technical validation to mass-market deployment.

World models and reinforcement learning

In his keynote, Dr. Li said the industry has reached an inflection point toward general-purpose physical AI, with world models and reinforcement learning as the essential bridge. He detailed QCraft’s cloud-based world model, which offers controllable, physics-aligned video generation; a zero-shot engine that uses natural language to synthesize long-tail and adverse-weather scenarios on command; and low-cost closed-loop simulation for continuous reinforcement learning. The approach, he said, lets AI develop “defensive driving instincts” for proactive safety. “Safety will always be our highest priority,” he added.