Reading time ( words)
RoboSense, a world-leading provider of smart LiDAR sensor systems, today announced it is now connected to the NVIDIA Omniverse ecosystem, using the development platform based on Universal Scene Description (USD) to accelerate the development, testing, and validation of its sensor technology.
“NVIDIA Omniverse is an open platform that includes leading LiDAR models from manufacturers worldwide. RoboSense's outstanding technical strength and customer base help strengthen our ecosystem and will accelerate the development and validation of autonomous vehicles while bringing more flexibility to developers.”
RoboSense's second-generation smart solid-state LiDAR model is integrated into NVIDIA DRIVE Sim, built on Omniverse, enabling physically based, high-fidelity sensor simulation. With this integration, autonomous vehicle developers can directly access state-of-the-art LiDAR for development and testing.
DRIVE Sim is a reference application built on NVIDIA Omniverse, the connecting fabric between software ecosystems. It combines NVIDIA’s core technologies to deliver digital twin environments for developing and testing autonomous driving systems. With DRIVE Sim, developers can perform diverse and repeatable testing scenarios at a large scale, accelerating development and reducing cost.
As part of the Omniverse ecosystem, RoboSense will use the simulation platform to test and validate its new LiDAR systems - as well as provide ADAS developers access to highly accurate simulation models.
RoboSense's M-Series LiDAR is the world's first second-generation smart solid-state LiDAR to achieve mass production for automotive applications. It is currently the LiDAR with the most designated partnerships worldwide and has been implemented in a variety of vehicle models including the GAC Aion LX Plus, GAC Aion Hyper GT, SAIC IM LS7, SAIC IM L7, Lotus Eletre, XPeng G9, XPeng P7i, Great Wall WEY Mocha DHT-PHEV, Great Wall Motor WEY DHT-PHEV, and Chery Exeed STERRA ES, STERRA ET.
The M-Series LiDAR features a revolutionary two-dimensional MEMS scanning architecture, with unique “GAZE” function that can dynamically switch scanning modes and change scanning patterns based on the scenario, improving vehicle perception in complex environments. Based on RoboSense's leading patented technology, the M-Series LiDAR delivers point-cloud with outstanding quality, helping to address corner cases in autonomous driving perception.
By joining the NVIDIA Omniverse ecosystem, RoboSense enables developers to create complex road environments with high physical accuracy using its LiDAR model on the DRIVE Sim platform. The M series LiDAR model offers the flexibility to simulate its performance in beam control, custom scan patterns, and resolutions, which can then be used to generate synthetic datasets for training and validation of autonomous driving solutions.
Mark Qiu, co-founder and executive president of RoboSense, said, “The global automotive industry is undergoing a massive transformation, with ADAS and LiDAR markets continuing to gain traction. Leveraging the NVIDIA Omniverse ecosystem, RoboSense LiDAR technology and industry experience can be applied in a wider field, providing strong support for the development and verification of autonomous vehicles. RoboSense will work with NVIDIA to fully leverage the advantages of LiDAR technology, continuously improve the perception capabilities of autonomous vehicles, and achieve more efficient, safer, and smarter autonomous driving applications. We are committed to promoting the development of the global automotive and autonomous driving industries.”
Zvi Greenstein, a general manager at NVIDIA, said, “NVIDIA Omniverse is an open platform that includes leading LiDAR models from manufacturers worldwide. RoboSense's outstanding technical strength and customer base help strengthen our ecosystem and will accelerate the development and validation of autonomous vehicles while bringing more flexibility to developers.”