VinFast has announced a collaboration with Autobrains and Nvidia to develop a Level 4 autonomous driving program for Southeast Asia, as the Vietnamese electric vehicle manufacturer seeks to advance autonomous mobility technologies in one of the world’s most challenging traffic environments.
The initiative, unveiled at GTC Taipei, will be built on Nvidia’s Drive Hyperion 10 platform and combines Autobrains’ Agentic AI software with Nvidia’s autonomous driving hardware and software ecosystem.
The companies said the program will focus on validating autonomous driving capabilities in Southeast Asia’s dense and often unpredictable traffic conditions.
Targeting Complex Urban Environments
Southeast Asia presents a unique challenge for autonomous vehicle development due to a combination of congested urban roads, diverse vehicle types, varying driving behavior and rapidly changing traffic conditions.
The partners said these characteristics make the region a valuable testing ground for advanced autonomous driving systems.
Autobrains’ Agentic AI technology takes a different approach from conventional end-to-end autonomous driving models by using specialized AI agents that activate only when specific driving situations require them.
The company said this modular approach is designed to improve decision-making in complex traffic scenarios while reducing computational demands.
Built on Nvidia Drive Hyperion
The program will utilize Nvidia’s Drive Hyperion 10 platform, which integrates autonomous driving compute hardware, sensors and software components.
According to the companies, the platform provides a pre-validated foundation that can reduce development complexity and shorten deployment timelines compared with building autonomous systems from the ground up.
Autobrains said its software architecture is intended to address some of the technical challenges that have slowed broader adoption of Level 4 autonomous driving systems, particularly in situations involving unusual or unpredictable traffic conditions.
Focus on Scalable Deployment
The collaboration is intended to explore a commercially viable pathway toward autonomous mobility that does not rely on highly customized hardware configurations.
The companies said the goal is to support autonomous driving using automotive-grade computing systems and standard sensor configurations, potentially lowering deployment costs.
For VinFast, the project represents an effort to expand its advanced technology capabilities while pursuing future mobility opportunities in Southeast Asia.
VinFast Highlights Accessibility
Duong Nguyen, Deputy Chief Executive for Advanced Driver Assistance Systems at VinFast Global, said the company aims to develop autonomous driving solutions that can be deployed at scale.
“Advanced mobility shouldn’t be a luxury. VinFast is committed to building scalable and accessible autonomous driving solutions through collaboration with global technology leaders,” Nguyen said.
“Together with Autobrains and Nvidia, we are exploring a practical and cost-efficient path toward Level 4 mobility for Southeast Asia’s highly dynamic real-world traffic environments.”
Autonomous Driving Development Continues
Level 4 autonomous driving systems are designed to operate without human intervention under defined operating conditions, although commercial deployment remains limited in most markets.
Automakers and technology companies continue to test different software architectures and hardware approaches as the industry works to address technical, regulatory and cost-related challenges.
The VinFast partnership highlights ongoing efforts to adapt autonomous driving technologies to a wider range of traffic environments beyond the more structured conditions often used in early deployments.
If successful, the program could provide additional insight into how autonomous vehicle systems perform in complex urban environments common across Southeast Asia.