Partnering with Infineon to Power Full Intelligent Perception for Commercial Robots
From restaurant delivery to hotel guidance, from building cleaning to campus patrol, commercial robots are gradually integrating into our work and daily lives. As application scenarios grow increasingly complex, traditional solutions such as the combination of LDS (LiDAR) and obstacle-avoidance modules can no longer meet production requirements.
The Nebula 400 depth camera from DEPTRUM integrates the Infineon IRS2975C and IRS9102C, and can be widely applied to delivery robots, logistics robots, cleaning robots, outdoor robots, quadrupeds, humanoid robots and many other intelligent terminals. Built on Infineon's advanced REAL3(TM) ToF technology, it offers a solution in which “one device handles SLAM mapping, obstacle avoidance and cliff detection,” delivering smarter and more efficient perception for commercial robots.
The Infineon REAL3(TM) ToF sensor provides real-time depth data with millisecond-level capture speed. The sensor is contact-free, fast, and unaffected by any ambient lighting conditions. Thanks to its patented background light suppression (SBI) technology, REAL3(TM) supports camera deployment under all lighting conditions. REAL3(TM) time-of-flight image sensors enable electronic devices to build a 3D map of the scene in front of them — whether a room, moving or static objects, or people — and convert that map into the digital world in real time.
Nebula 400:
From Single-Function to Full-Scenario Intelligent Technology
Early commercial robots relied on mechanical LDS and low-precision infrared sensors, which were bulky, noisy, and performed poorly in dark environments or scenes with complex textures. Built on Infineon's advanced REAL3(TM) ToF technology, the Nebula 400 achieves the following breakthroughs:
Ultra-Wide FOV and Precise Ranging
With an ultra-wide field of view (FOV) of 98°(H) × 75°(V) and a range covering 3 cm to 8 m, it easily handles demanding scenarios such as long corridors, narrow passages (e.g., dining-delivery passages as narrow as 55 cm) and low-clearance spaces (e.g., cleaning under sofas).
Multi-Light-Source Fusion Recognition
By combining speckle infrared, LED infrared and depth imaging, it accurately recognizes thin lines, transparent objects (such as glass doors) and black high-reflectivity surfaces (such as tile floors). Even outdoors under strong light of 100,000 lux (such as backlit whiteboard recognition), it still recognizes targets stably.
Efficient Computing
Its built-in highly efficient 3D SLAM algorithm significantly reduces CPU load and is well suited to embedded platforms. Combined with AI algorithms, perception accuracy is further enhanced, enabling classified obstacle avoidance for special targets such as liquid stains and short-pile carpets — raising cleaning coverage by more than 30%.
Powered by Infineon REAL3(TM) ToF technology:
From Cost Reduction to Experience Upgrade
Behind the Nebula 400's outstanding performance lies Infineon's deep enablement in hardware integration and algorithm optimization.
This module combines SLAM mapping and obstacle avoidance in one, replacing the traditional large LDS, infrared camera and low-precision line laser with a compact, efficient solution — significantly reducing the number of sensor types and installation complexity. It saves system cost and volume while lowering assembly difficulty and power consumption.
At the structural design level, a single module delivers both navigation and obstacle avoidance, shrinking the robot's size so it can enter more confined spaces; the compact front camera design also frees up room for larger motors. In addition, its excellent environmental compatibility keeps robots running stably in the dark, and paired with 3D AI obstacle-avoidance algorithms, it perceives its surroundings even more precisely.
In real-world use, the Nebula 400 delivers high-resolution obstacle avoidance and fine navigation, greatly reducing collisions and maintenance costs. Meanwhile, it does not rely on RGB image input — protecting user privacy while breaking through the limits of traditional 2D mapping, providing strong support for whole-home 3D modeling and path optimization for robots.
In actual deployments, the Nebula 400 combination shows outstanding environmental adaptability:
Logistics and warehousing: when mounted at a height of 1.8 m looking obliquely downward, it stably recognizes small objects and edge contours, effectively improving sorting efficiency.
Medical, restaurant and hotel delivery: it precisely identifies elevator metal doors, objects dropped on the floor, tiles and other obstacles, providing a stable data source for path planning.
Outdoor cleaning: even under high-intensity lighting, it still builds maps stably, guaranteeing navigation reliability.
From module performance to real-world results, DEPTRUM will continue working hand in hand with Infineon to push robots from “stacked functions” toward “perceptual intelligence,” bringing stronger technological momentum to a new generation of commercial robots.
