RoboSense E2 and EM4 Officially Integrated with NVIDIA HSB

Edited by Sissi From Gasgoo
Main productsLiDAR
Main productsAutomotive System-on-Chips High-Performance Automotive SoCs Centralized Automotive Computing SoCs In-Vehicle High-Performance Computing Platforms Autonomous Driving In-Vehicle Computing Platforms Centralized Automotive Computing Platforms Autonomous Vehicle Reference Hardware Platforms Autonomous Vehicle Reference Platforms: In-Vehicle Compute Units, Cameras, Radars, Lidars, Ultrasonic Sensors Automotive Operating Systems Safety-Certified Automotive Operating Systems Autonomous Driving Software Full-Stack Autonomous Driving Software Autonomous Driving Perception, Planning & Control Software Autonomous Driving AI Models Vision-Language-Action Reasoning Models

Gasgoo Munich-On September 28 that RoboSense integrated its E2 and EM4 digital LiDARs with the NVIDIA Holoscan Sensor Bridge (HSB). The E2 is a second-generation, high-precision, all-solid-state device. The EM4 is an automotive-grade, "thousand-line" unit with ultra-long-range capabilities.

NVIDIA HSB is an Ethernet-based sensor streaming technology for real-time data transmission. It simplifies high-speed sensor fusion and actuator integration across NVIDIA edge AI platforms.

HSB offers ultra-low latency, ease of use, scalability, and security. This helps developers shorten integration cycles for sensor drivers and systems. Teams can then dedicate more resources to algorithms, models, and applications.

RoboSense previously joined the NVIDIA Jetson, DRIVE, and Omniverse ecosystems. The HSB integration extends this partnership beyond AI computing and simulation to real-time sensor data ingestion.

Image Credit: RoboSense

The E2 and EM4 now natively support NVIDIA HSB. Developers can use HSB's standard APIs and open-source software to integrate these products into systems based on NVIDIA Jetson and IGX platforms.

High-quality 3D data from RoboSense's digital LiDAR transmits via Ethernet into AI processing pipelines. On compatible hardware, this data writes directly to GPU memory. This reduces CPU load and enables multi-sensor fusion, real-time inference, and application deployment.

The E2 is the first mass-produced model built on RoboSense's proprietary "Peacock" SPAD-SoC chip. It uses an all-solid-state scanning architecture for high precision and a wide field of view. Applications include humanoid robots, quadrupeds, robotic mowers, drones, and spatial intelligence devices.

The EM4 offers a maximum resolution of 2,160 lines and an imaging capability of 41.04 million points per second. It has a detection range of up to 600 meters. The unit provides ultra-high-definition 3D perception for advanced intelligent driving systems.

RoboSenseSupplierCompany Insights
Location: China/Guangdong/Shenzhen/Nanshan District
Main productsLiDAR
NvidiaSupplierCompany Insights
Location: USA/California/Santa Clara County
Main productsAutomotive System-on-Chips High-Performance Automotive SoCs Centralized Automotive Computing SoCs In-Vehicle High-Performance Computing Platforms Autonomous Driving In-Vehicle Computing Platforms Centralized Automotive Computing Platforms Autonomous Vehicle Reference Hardware Platforms Autonomous Vehicle Reference Platforms: In-Vehicle Compute Units, Cameras, Radars, Lidars, Ultrasonic Sensors Automotive Operating Systems Safety-Certified Automotive Operating Systems Autonomous Driving Software Full-Stack Autonomous Driving Software Autonomous Driving Perception, Planning & Control Software Autonomous Driving AI Models Vision-Language-Action Reasoning Models

Gasgoo not only offers timely news and profound insight about China auto industry, but also help with business connection and expansion for suppliers and purchasers via multiple channels and methods. Buyer service: buyer-support@gasgoo.com Seller Service: seller-support@gasgoo.com

All Rights Reserved. Do not reproduce, copy and use the editorial content without permission. Contact us: autonews@gasgoo.com