From Sensor Data to Simulation
dSPACE demonstrates AI-powered simulation workflows using NVIDIA Halos SAFE and NVIDIA Omniverse NuRec at NVIDIA GTC Berlin

Paderborn, Germany / Santa Clara, USA - October 21, 2026. At NVIDIA GTC in Berlin, dSPACE demonstrated how recorded real-world sensor data can be converted into highly realistic simulation scenarios for the development and validation of advanced driver-assistance systems (ADAS) and automated driving functions. The demonstrations showed how dSPACE integrates its simulation tool chain with the NVIDIA Halos SAFE safety evaluation framework to expand test coverage and accelerate AV validation, using NVIDIA Omniverse NuRec within the dSPACE Automotive Simulation Models (ASM) tool suite to combine neural reconstruction with established models for vehicle dynamics and traffic simulation. 

Visitors experienced the NVIDIA Halos SAFE framework integrated with dSPACE technology at two locations during the event. At the NVIDIA booth, a software-in-the-loop (SIL) setup from dSPACE was presented, while a hardware-in-the-loop (HIL) system was showcased at the dSPACE booth. Together, the demonstrations highlighted how real-world sensor recordings can be converted into virtual environments and used throughout the validation process, from software testing to hardware verification.

The SIL and HIL workflows in NVIDIA Halos SAFE also support the automated execution of Euro NCAP tests, with the goal of advancing the virtual homologation and validation of ADAS systems. The same technology can also be applied to higher levels of automation, including robotaxis.

NVIDIA Omniverse NuRec is a neural reconstruction technology used in the Halos SAFE workflow to create high-fidelity 3D environments from recorded camera and lidar data. These reconstructed environments can form the basis for realistic simulation scenarios that can be expanded, modified, and enriched with new traffic situations. By integrating NVIDIA Halos SAFE and Omniverse NuRec into its SIL and HIL tool chain, dSPACE provides developers with an efficient way to combine real-world and synthetic data for comprehensive testing and validation.

"By integrating NVIDIA Halos SAFE and Omniverse NuRec into our simulation tool chain, we are helping developers bring real-world sensor data into scalable virtual validation workflows," said Tino Schulze, Vice President Automated Driving & Software Solutions dSPACE. "This enables teams to reproduce real traffic situations, vary relevant scenarios, and increase test coverage for ADAS and automated driving functions in a more efficient way. Drawing on our decades of experience and in-depth expertise, we are able to offer our customers exceptionally high-performance solutions."

As simulation-driven development continues to gain importance, dSPACE is showing how NVIDIA-accelerated technologies can support the creation of realistic virtual environments for the development and validation of safer and more reliable automated driving systems.