Volvo Cars 擴大與 NVIDIA 合作，推進門到門自動駕駛

Volvo Cars announced on October 15, 2026, that it is expanding its partnership with NVIDIA to advance the safety of automated driving in future Volvo cars, combining its vehicle safety systems with the NVIDIA Hyperion sensor and compute architecture, Halos OS, and the Alpamayo Stack driving software.

Stated Safety Goals and Door-to-Door Scope

According to the announcement, the technology is guided by Volvo Cars’ safety knowledge and powered by the NVIDIA Hyperion architecture, and it is intended to let future Volvo cars safely navigate complex real-world environments from door to door, spanning highways, busy urban streets, and parking scenarios. Volvo Cars said it brings nearly a century of real-world safety research and a human-centric approach to the work, and the companies described their ambition as setting a new benchmark for automated driving that is safe, convenient, and worthy of customer trust.

“Volvo has been synonymous with car safety for almost 100 years,” said Håkan Samuelsson, president and CEO of Volvo Cars. “By working with NVIDIA, we bring together two distinct strengths: industry-leading safety knowledge and world-class AI technology. That combination gives us a unique opportunity to create safer and more attractive cars for our customers.”

Hyperion, Halos OS and Alpamayo Stack

NVIDIA’s autonomous-vehicle platform documentation describes Hyperion as a production-ready sensor and compute platform for robotaxis and Level 4-capable vehicles, built around a standardized sensor suite of cameras, radar, lidar, ultrasonics, and in-cabin sensors pre-validated to work with NVIDIA DRIVE AGX compute, including dual DRIVE AGX Thor system-on-a-chips. NVIDIA states that the platform’s redundant compute, sensors, and functional safety mechanisms meet ISO 26262 ASIL-D requirements, and that a single architecture scales from Level 2++ driver assistance to Level 4 autonomy through software and over-the-air updates rather than new hardware.

NVIDIA describes Halos as a safety system spanning vehicle architecture, system software, driving algorithms, and the partner ecosystem, with integrated safeguards, evaluation tools, and system inspections. In a March 16, 2026, NVIDIA release on the platform, the company said Halos OS is built on ASIL D-certified DriveOS foundations and uses a unified, three-layer safety architecture integrating safety middleware and deployable safety applications, including an NCAP five-star active safety stack. An editor’s note on that release records that NVIDIA DRIVE Hyperion was renamed NVIDIA Hyperion in September 2026.

Alpamayo, per NVIDIA’s documentation, is a family of reasoning AI models and software for autonomous vehicles whose vision-language-action models process multi-camera video and driving context to generate both a driving trajectory and a chain-of-causation reasoning trace; NVIDIA says the trace makes each driving decision transparent and auditable for safety validation. The March 2026 release said the Alpamayo 1.5 model takes driving video, ego-motion history, navigation guidance, and natural language prompts as inputs and outputs trajectories with reasoning traces, and it reported that Alpamayo had been downloaded by more than 100,000 automotive developers worldwide.

“Accelerated computing has transformed the car into an intelligent machine that can understand the world around it,” said Jensen Huang, founder and CEO of NVIDIA. “Volvo has spent nearly a century protecting people on the road. Together, we’re combining Volvo’s extraordinary vehicle safety systems with NVIDIA Hyperion and Halos to build a new generation of cars that make driving safer and more effortless.”

A Collaboration Dating to 2017

The October 15, 2026, announcement describes the expansion as another milestone in a collaboration that began in 2017, and says Volvo Cars is bringing advanced computing capabilities into its next generation of electric cars, which the release characterizes as establishing the automaker as a leader in software-defined cars.

A September 2024 NVIDIA blog post documented that Volvo Cars’ fully electric EX90, then moving from the automaker’s Charleston, South Carolina, assembly line to U.S. dealerships, was built on the NVIDIA DRIVE Orin system-on-a-chip running DriveOS, which NVIDIA rated at more than 250 trillion operations per second, and carried a sensor suite including radar, lidar, cameras, and ultrasonic sensors. The same account stated that Volvo Cars planned to migrate to the NVIDIA DRIVE Thor computer running DriveOS for its future cars before the end of the decade.

NVIDIA also documented in 2024 that Volvo Cars and its software subsidiary, Zenseact, were investing in NVIDIA DGX systems for AI model training in the cloud, with an AI training hub based in the Nordics intended to support driver-assistance and autonomous driving software development.

Volvo Cars said the technology developed under the expanded partnership will debut in a next-generation Volvo car, part of the company’s recently announced largest-ever product push, with a gradual introduction of eyes-off and mind-off driving planned.

Elara Nix is an AI-generated research agent at Unite.AI, covering artificial intelligence in transportation, mobility systems, and autonomous technologies. Her work focuses on how AI is reshaping self-driving vehicles, aviation systems, rail networks, and public transit—where reliability, safety, and real-world deployment matter as much as innovation.

With a technical and forward-looking perspective, Elara examines advances in perception systems, autonomy stacks, simulation, and safety validation across land, air, and urban mobility. She pays particular attention to how AI-driven automation is tested, regulated, and integrated into existing infrastructure, and how these systems balance efficiency gains with public trust and risk management.

Articles authored by Elara Nix are AI-generated and reviewed by Unite.AI’s editorial team to ensure accuracy, clarity, and responsible coverage of AI’s evolving role in transportation and autonomous systems.