Quick Takeaways
- ADAS computing platform from Black Sesame Technologies enters commercial deployment phase.
- The launch strengthens global rollout of advanced assisted driving systems.
On January 28, Black Sesame Technologies announced the launch of its FAD 2.0 ADAS computing platform, marking a significant step in the commercialization of high-performance assisted driving solutions. The announcement was made through the company’s official communication channel following key regulatory approvals.
The release comes after the company’s flagship Huashan A2000 assisted driving chip received regulatory clearance from the US Department of Commerce and the Department of Defense. These approvals allow the chip to be sold and deployed globally, positioning Black Sesame Technologies as the only Chinese company to achieve this milestone and enabling large-scale commercial adoption.
ADAS Computing Platform Built for Full-Scenario Assisted Driving
FAD 2.0 is designed as a near-production-ready open ADAS computing platform that integrates the A2000 high-computing hardware with a comprehensive software development kit. It combines AI toolchains, reference models for end-to-end and VLA architectures, and support for third-party algorithm models within a scalable ecosystem.
The platform is engineered to support a stable and extensible third-party software environment and is scheduled for official release in the first quarter of 2026. Black Sesame Technologies stated that the A2000 will add Open VLA support and continue adapting to emerging model architectures across the industry.
Flexible Deployment and High-Bandwidth Support
From an implementation standpoint, the A2000-based ADAS computing platform supports both in-vehicle installation and prototype validation. Its scalable core-board architecture and dual desktop-grade and automotive-grade interfaces reduce peripheral replacement costs and shorten system integration timelines.
Key platform capabilities include:
An integrated Ubuntu environment further simplifies software iteration and debugging.
Optimized AI Toolchains and Automotive-Grade Software
The AI toolchain is built on the MLIR framework, enabling efficient optimization and deployment of CNN, BEV, end-to-end, and VLA models. Enhanced tooling improves quantization accuracy, sparse acceleration efficiency, and performance analysis, helping developers fine-tune models more effectively.
On the software side, FAD 2.0 integrates established third-party solutions including Classic AUTOSAR and Hypervisor plus RTOS configurations, supporting automotive-grade reliability and readiness for mass production.
Safety and Rapid Commercial Readiness
Safety is embedded at the chip level, with the Huashan A2000 complying with ISO 26262 ASIL-D functional safety standards and integrating a hardware security module. This foundation meets stringent automotive safety requirements for advanced driver-assistance systems.
The A2000 has demonstrated rapid algorithm adaptability, completing its first model deployment within 10 days. At CES 2026, Black Sesame Technologies showcased bench demonstrations of VLM and point-to-point functions on the FAD 2.0 platform, highlighting its maturity and usability for VLA and end-to-end application development.
As the Huashan A2000 moves toward global-scale deployment, Black Sesame Technologies continues to pursue an open and collaborative technology strategy, working with partners across the automotive value chain to accelerate the adoption of advanced assisted driving solutions worldwide.
The release comes after the company’s flagship Huashan A2000 assisted driving chip received regulatory clearance from the US Department of Commerce and the Department of Defense. These approvals allow the chip to be sold and deployed globally, positioning Black Sesame Technologies as the only Chinese company to achieve this milestone and enabling large-scale commercial adoption.
ADAS Computing Platform Built for Full-Scenario Assisted Driving
FAD 2.0 is designed as a near-production-ready open ADAS computing platform that integrates the A2000 high-computing hardware with a comprehensive software development kit. It combines AI toolchains, reference models for end-to-end and VLA architectures, and support for third-party algorithm models within a scalable ecosystem.
The platform is engineered to support a stable and extensible third-party software environment and is scheduled for official release in the first quarter of 2026. Black Sesame Technologies stated that the A2000 will add Open VLA support and continue adapting to emerging model architectures across the industry.
Flexible Deployment and High-Bandwidth Support
From an implementation standpoint, the A2000-based ADAS computing platform supports both in-vehicle installation and prototype validation. Its scalable core-board architecture and dual desktop-grade and automotive-grade interfaces reduce peripheral replacement costs and shorten system integration timelines.
Key platform capabilities include:
- Support for more than 24 camera channels
- Four 10-gigabit Ethernet links for high-bandwidth data
- Open Linux kernel and driver source code with real-time patches
- Flexible sensor selection and deep system customization
An integrated Ubuntu environment further simplifies software iteration and debugging.
Optimized AI Toolchains and Automotive-Grade Software
The AI toolchain is built on the MLIR framework, enabling efficient optimization and deployment of CNN, BEV, end-to-end, and VLA models. Enhanced tooling improves quantization accuracy, sparse acceleration efficiency, and performance analysis, helping developers fine-tune models more effectively.
On the software side, FAD 2.0 integrates established third-party solutions including Classic AUTOSAR and Hypervisor plus RTOS configurations, supporting automotive-grade reliability and readiness for mass production.
Safety and Rapid Commercial Readiness
Safety is embedded at the chip level, with the Huashan A2000 complying with ISO 26262 ASIL-D functional safety standards and integrating a hardware security module. This foundation meets stringent automotive safety requirements for advanced driver-assistance systems.
The A2000 has demonstrated rapid algorithm adaptability, completing its first model deployment within 10 days. At CES 2026, Black Sesame Technologies showcased bench demonstrations of VLM and point-to-point functions on the FAD 2.0 platform, highlighting its maturity and usability for VLA and end-to-end application development.
As the Huashan A2000 moves toward global-scale deployment, Black Sesame Technologies continues to pursue an open and collaborative technology strategy, working with partners across the automotive value chain to accelerate the adoption of advanced assisted driving solutions worldwide.
Company Press Release
Click above to visit the official source.
Share: