Globally innovative multi-sensor fusion becomes the key puzzle piece for robots' 'human-like cognition'!

The World Artificial Intelligence Conference (WAIC) is in full swing, and humanoid robots are once again in the spotlight. Their smooth movements, precise grasping, and intelligent interactions all rely on a key component: the spatial computing and perception module. Like the robot's "eyes," it enables it to understand three-dimensional space, locate itself, and perceive its environment. It is the core foundation for autonomous navigation, obstacle avoidance, and interaction.

High-end spatial computing and perception modules are the core hardware that enables robots' intelligent vision. Their technological strengths lie in the integration of spatial perception algorithms, exemplified by VSLAM (Visual Simultaneous Localization and Mapping), and hardware. Xvisio Technology has been deeply engaged in this field for many years, and its technological expertise was recognized by the industry with the 2018 CES Innovation Award (eXLAM80). In response to the market's urgent need for high-performance, highly integrated, and localized processing modules, Xvisio Technology has launched its latest product, the SeerSense® DS80 Intelligent Perception Module. The DS80, for the first time, integrates five core engines (binocular depth, Time of Flight, VSLAM, AI, and video encoding) into a single platform. This marks a significant milestone in Xvisio's spatial computing and perception technology innovation, providing a powerful "Chinese machine eye" for intelligent devices, including humanoid robots.

Why spatial computing perception module

Is it the "humanoid robot perception center"?

For humanoid robots to move freely in complex environments, they must solve three core problems in real time:

DS80 was born to solve these problems. It integrates the five core units required to realize these functions, namely the binocular depth engine, TOF engine, VSLAM engine, AI engine, and video encoding engine, into a single module for the first time, realizing "multi-sensory fusion and device-level localized deployment."

SeerSense® DS80

Multi-sensory fusion defines a new benchmark for spatial perception

The DS80 boasts advantages in depth perception (6-meter field of view), ruggedness (industrial-grade protection, adaptable to harsh environments), compact design, cross-platform support (Windows/Linux/Android), and a rich SDK. It also achieves breakthroughs in the following key areas:

DS80 uses self-developed SLAM technology with high speed, low latency and high precision.

High-performance SOC with significantly improved computing power, supporting multiple advanced working modes such as high-speed and high-precision independent VIO, SLAM/CSLAM, end-cloud collaboration, real-time loop detection, and high-speed QR code/spatial anchor assisted positioning.

Deep collaboration among multiple sensors enables faster, more accurate, and more stable positioning.

Passive binocular vision: Large field of view (110°), high resolution (640*480@60fps), 5.5m effective range (error <3%), excellent performance in bright light environments, suitable for open scene modeling and obstacle avoidance.

Active iTOF (Sony VGA): 940nm interference-resistant wavelength, ultra-high accuracy (<1%) within 0.2-4 meters, 30fps frame rate, and output of depth maps, point clouds, and IR images. Its accuracy far exceeds that of binoculars in low-light and indoor environments. It supports switching between single-frequency (1.5 meters) and dual-frequency (4 meters) modes.

The dual engines can work simultaneously and seamlessly integrate with VSLAM to provide real-time environmental depth information, laying a solid foundation for navigation, obstacle avoidance, and 3D reconstruction.

The independent hardware CNN engine is a key breakthrough! It eliminates dependence on the main control system's computing power and enables localized real-time AI reasoning.

Supports access to multiple video sources such as fisheye, TOF, and RGB, and enables the parallel deployment of multiple AI models.

Combining VSLAM with depth information, it enables advanced intelligent functions such as 3D gesture recognition and tracking, human skeleton extraction, 3D face anti-counterfeiting recognition, object recognition and spatial semantic segmentation, and scene understanding.

Perfectly compatible with OpenCV and Open VINO, it allows for easy deployment of models from open source communities (such as the Open Model Zoo) or user-trained models. This plug-and-play approach significantly shortens R&D cycles.

Intelligent video compression: Hardware-based H.265 video compression significantly saves valuable transmission bandwidth and reduces overall system load.

Plug and Play: Localized processing capabilities significantly lower the development and integration threshold.

Rich SDK: Supports Windows/Linux/Android, provides wrapper APIs such as ROS/ROS2, Unity, C/C++, Python, Java JNI, etc., and seamlessly connects to various development frameworks.

Highly expandable: USB Type-C connects to the host controller, and can be connected to sensors such as lidar through expansion interfaces, supporting multi-machine cascading to meet complex system requirements.

Global Certifications: CE, FCC, RoHS, CB, FDA Class I laser safety certifications, suitable for global markets.

Empowering thousands of industries and leading the future

The SeerSense® DS80 is a dazzling demonstration of Xvisio's spatial perception technology strength. The core technology matrix behind it not only provides the "smart eyes" for humanoid robots to achieve autonomous navigation, dexterous operation, and intelligent interaction, but also has broader application potential:

Industry: AGV/AMR navigation, industrial inspection, and automated sorting.

Daily life : smart access control, personnel behavior analysis.

Medical : surgical navigation, rehabilitation assistance, and telemedicine perception.

Logistics and retail: volume measurement, shelf analysis, and unmanned delivery.

AR /VR & Metaverse: High-precision positioning tracking and immersive interaction.

Office and entertainment: virtual meetings, somatosensory games, and film and television production.

Smart home: service robots, intelligent monitoring.

The WAIC stage showcased the boundless potential of humanoid robots. One of the cornerstones of turning this potential into reality is advanced and reliable spatial computing and perception modules like the SeerSense® DS80. Xvisio Technology is deeply engaged in the field of spatial computing and perception. The launch of the DS80 is not only a milestone for domestically produced high-end modules, but also a powerful demonstration of its commitment to breaking monopolies and empowering innovation. Choosing the DS80 means choosing a powerful, autonomous, and future-oriented "robot eye," enabling your products to see more clearly, navigate more steadily, and understand more in the robotics wave!