

























At a recent event, BYD executive Yang Dongsheng outlined the company’s rapid expansion of assisted driving technologies across its vehicle lineup.
Yang, who serves as BYD Group senior vice president and heads the Automotive New Technology Research Institute, said the automaker accelerated the rollout of intelligent driving systems at the beginning of 2025. He noted that Level 2 assisted driving features are now available across nearly all BYD passenger vehicles.
Usage data presented during the conference showed that navigation-assisted driving functions recorded activation rates of more than 50%, while parking-assistance systems were used in 86% of cases, highlighting growing consumer adoption of automated driving features.
BYD said its parking-assistance technology has significantly reduced low-speed accidents, with scratches and minor parking collisions dropping to around one-fiftieth of the rate seen in human-driven parking maneuvers.
The automaker linked the results to its “God’s Eye” intelligent driving platform and a parking-assistance guarantee program launched in July 2025, which was designed to strengthen consumer confidence in automated parking features. According to the company, the system has become a key part of its broader push to expand intelligent driving capabilities across its vehicle lineup, CarNewsChina reported.
BYD’s latest remarks arrive just days before the company’s intelligent-driving strategy event scheduled for later in May, where industry observers expect announcements related to an expanded rollout of upgraded God’s Eye systems and deeper integration of the technology across more vehicle models.
Dongsheng noted the company’s ability to rapidly integrate intelligent driving technologies is supported by its Xuanji Architecture, a vehicle platform that combines electronic systems with core electrification technologies. He explained that the architecture enables faster coordination between software and hardware across BYD’s growing lineup of smart vehicles.
Yang also revealed that BYD relies on cloud-based world models and reinforcement learning to train its assisted-driving systems through long-tail scenario simulations. According to figures presented, the automaker generates roughly 118 million miles of driving data every day, allowing engineers to refine algorithms at a rapid pace. He said BYD is currently updating and iterating its driving algorithms every three days.
The Chinese EV maker said its intelligent driving platform also incorporates physical AI models inside the vehicle to support predictive driving behavior and defensive-response calculations in real time. According to the company, the system is designed to improve how vehicles anticipate surrounding traffic conditions and react to potential hazards.
For parking situations, BYD stated that the technology combines visual occupancy network detection with lidar-based occupancy sensing to detect suspended or hollow obstacles that may be difficult for conventional parking systems to recognize. The company said the approach is intended to improve accuracy and safety during automated parking maneuvers.
Bojan Stojkovski is a freelance journalist based in Skopje, North Macedonia, covering foreign policy and technology for more than a decade. His work has appeared in Foreign Policy, ZDNet, and Nature.
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。