Siemens and Arm Collaborate to Advance Digital Twin Solutions for AI-Defined Vehicles
Siemens and Arm Collaborate to Advance Digital Twin Solutions for AI-Defined Vehicles: Accelerating AI-Defined Vehicle Development through Software-Defined Systems
Siemens Digital Industries Software and Arm have expanded their collaboration to enhance development of AI-defined and software-defined vehicles (SDVs) through digital twin innovation. At the heart of this collaboration is Siemens’ PAVE360 platform, which now offers cloud-based access to virtual models of Arm® automotive IP, including the latest Arm Zena™ Compute Subsystems (CSS)—well ahead of chip production.
Previously, Siemens was a launch partner for the Arm Cortex®-A720AE virtual platform. Today, it continues that legacy by extending early access support to Zena CSS. Designed to handle mixed-criticality and AI-intensive automotive workloads, Zena CSS requires sophisticated simulation environments to meet future vehicle development needs. PAVE360 fulfills this role by enabling early software validation and system-level integration testing before physical hardware is available.
What distinguishes Siemens is its ability to combine EDA tools with PLM and ALM systems, enabling a multi-domain and multi-industry digital twin workflow. This holistic approach facilitates early detection of integration challenges, supports full-system validation, and enhances system reliability from design through deployment.
The Evolution of Software-Defined Systems for Automotive Applications
Software-defined vehicles are a specific instance of a broader Software-Defined Systems (SDS) methodology—where both hardware and software are refined in tandem, allowing for seamless system optimization. This parallel development strategy improves performance, reduces cost, increases safety, and extends product longevity, ultimately supporting new business models for vehicle OEMs.
As David Fritz, VP of Hybrid and Virtual Systems at Siemens Digital Industries Software, notes, modern vehicles have evolved into multifunctional ecosystems that serve not just as transportation, but also as extensions of consumers’ work and home lives. Traditional vehicle development methods are inadequate for this complexity. To succeed, automakers must adopt two critical principles:
- Software-first design to deliver customizable, differentiable user experiences.
- System-aware development, where integration issues are addressed early—well before real-world deployment.
Identifying system failures in the design phase requires a “threaded” validation approach. This method links every layer of testing—from high-level requirements to unit tests—with full traceability. Without such threading, teams face serious integration risks that often result in platform delays or cancellations, undermining competitiveness.
Building a Scalable Software-Defined Vehicle Platform
To help automotive enterprises scale effectively, Siemens has developed an SDV framework that integrates its extensive software portfolio with third-party tools and in-house models. At its core is PAVE360, which supports multi-layer abstraction for digital twins—spanning SoC simulation, virtual ECUs, systems modeling, and even real hardware.
Virtual Reference Model for Zena CSS using PAVE360
One key reference example uses PAVE360 combined with Innexis™ Architecture Native Acceleration (ANA), allowing developers to run software workloads at near-hardware speeds even without physical chips. Simcenter™ Prescan and Simcenter™ Amesim™ inject real-world scenarios and stimuli, while the Innexis™ CodeBench IDE simplifies configuration and analysis.
This virtual setup comes packaged with reference software for Zena CSS and integrates requirements and verification management via Siemens’ Teamcenter™ and Polarion™ platforms. Many leading OEMs and Tier 1 suppliers already use this method to improve software maturity pre-silicon, reducing risk and avoiding late-stage design reversals.
Hybrid Reference Model for Deep SoC Exploration
For more granular analysis, Siemens offers a hybrid simulation model. This transitions from ANA to Innexis Developer Pro and RTL emulation using Veloce Strato CS, enabling mixed-fidelity simulations. Developers can toggle between “Run Fast” mode on virtual models and “Run Accurate” mode on RTL hardware to assess latency, bandwidth, and power consumption precisely.
This hybrid method boosts debugging and simulation efficiency—critical for validating safety-critical software, which demands precise performance metrics across varied operating conditions. Combined with Simcenter tools, the platform supports accurate modeling of algorithms and physical systems.
Threaded Requirements and Verification
Especially during hybrid simulation, requirements and validation threading becomes indispensable. It helps surface issues that may only arise during integrated real-world workloads. By tracking timing, CPU usage, and functional correctness from simulation back to initial requirements, Siemens ensures integration problems are caught early—before physical production. PAVE360 is currently the only toolchain enabling this type of high-fidelity coverage.
More info here – Have a Story? Submit it here
Disclaimer
The information provided in this article is for general informational purposes only and from publicly available sources. While we strive for accuracy, we do not make any representations or warranties, express or implied, regarding the completeness, reliability, or validity of the content. This article does not make any direct claims about specific companies, individuals, or organizations. Any references to reports or external sources are for context and do not imply endorsement or verification of any specific allegations. Readers are encouraged to conduct their own research and seek professional advice before making business decisions. We disclaim any liability for any losses or damages incurred as a result of reliance on the information provided.