dSPACE Integrates Hesai Lidar Models into the AURELION Sensor Simulation Solution
March 21, 2024
Hesai Technology, a global leader in lidar technologies for autonomous mobility systems, ADAS and industrial robotics applications, and dSPACE, one of the world's leading providers of simulation and validation solutions for the automotive industry, have entered into a technology partnership to accelerate the development of ADAS and level 4 autonomous driving applications. As part of the partnership, dSPACE has integrated sensor models from Hesai into the dSPACE sensor simulation solution AURELION. Developers can now easily access Hesai lidar models via AURELION.
"Models for the most commonly used Hesai sensors are now part of our sensor simulation solution AURELION. By expanding our technology partnerships with the world's leading sensor manufacturers, we are extending our testing capabilities and reducing our customers' costs from the development phase through to validation," explains Caius Seiger, Product Manager Sensor Simulation at dSPACE.
Caius Seiger, Product Manager Sensor Simulation, dSPACE
AURELION can be operated both in the cloud and locally on the user’s premises and generates photo-realistic images for camera simulation in real time. Ray tracing is also used to calculate realistic raw data for radar and lidar. The solution can be implemented in all phases of the development process – for example, software-in-the-loop (SIL) testing, hardware-in-the-loop (HIL) testing, or in parallel validation in the cloud.
Hesai lidar products are proven in a wide range of applications worldwide, including passenger and commercial vehicles with advanced driver assistance systems (ADAS), autonomous vehicles, and robotic applications such as last-mile delivery robots and automated guided vehicles (AGV).
With the integration of the Hesai lidars, developers of applications for autonomous driving can flexibly use high-quality lidar models on the AURELION platform, which provides synthetic data for the development, testing, and validation of systems and solutions for autonomous driving. This reduces the costs for training corner cases and allows autonomous vehicles to be developed, tested, and validated more quickly.
Source : dspace.com
