Products
Hardware‑software integrated spatial intelligence solutions empowering full‑stack perception capabilities for robots
Insight Series spatial AI cameras
The World’s First Spatial AI Module Powered Entirely by Dedicated AI Compute
The First Spatial AI Module Officially Sponsored and Co-Launched by ROS, the World’s Largest Robot Operating System
The Insight Series spatial AI cameras are integrated hardware–software spatial perception systems purpose-built for robotics. An onboard 10-TOPS AI accelerator runs depth estimation and high-precision VSLAM natively on the device, without consuming host compute resources. Linux and ROS 2 come preinstalled, making the cameras ready to use without complex deployment. A 188° ultra-wide vertical field of view provides human-like panoramic perception, while a high-range 24 g IMU is designed to withstand the intense vibration of legged robots. A fully CNC-machined aluminum enclosure ensures stable, industrial-grade operation.
Computing Power
10 TOPS
Field of View
188°
IMU
24g High Dynamic Range
System
Linux + ROS2
Complete Robot Platforms
Industrial-Grade Autonomous Working Robot Platforms
Robot Platforms with Full Autonomy in Navigation and Manipulation
RANGERIndustrial Autonomous Quadruped Robot
RANGER delivers autonomous, all-terrain mobility across rugged surfaces, slopes, stairs, and other complex terrain. It maintains centimeter-level localization and precise obstacle avoidance even in challenging, dynamic environments.
Designed for autonomous industrial inspection, environmental monitoring, and material transport, RANGER combines a highly reliable, industrial-grade body with a flexible toolchain that allows tasks to be customized for specific operating requirements.
NOMAD | Biped Robot for Research and Commercial Applications
NOMADResearch‑oriented & Commercial‑grade Intelligent Biped Robot
NOMAD is a humanoid biped robot designed for research and commercial service applications. It comes pre-integrated with full-stack spatial perception and autonomous navigation, enabling stable balance and safe, real-time obstacle avoidance in dynamic indoor environments.
Centimeter-level visual localization and semantic navigation make NOMAD well suited to indoor services, guided tours and reception, and commercial demonstrations.
End-to-End Visual Localization Platform for Spatial AI
The world’s first vision-only localization product capable of building and continuously updating its own maps across indoor and outdoor environments, built on an end-to-end architecture comparable to Tesla FSD.
The platform uses deep learning-based 6-DoF visual pose estimation to deliver centimeter-level localization accuracy. Its complete algorithm pipeline runs as a closed loop at the edge and can be deployed across a wide range of robots and unmanned aerial vehicles, providing reliable spatial localization for embodied AI systems in diverse environments.
Integrated Perception and Planning System for Real-Time Autonomous Motion Planning
A core navigation and decision-making system purpose-built for embodied robots, integrating environmental perception and path planning into a single pipeline.
Using obstacle-avoidance models built on centimeter-level spatial AI data, the system identifies both static and moving obstacles in real time. It computes optimal paths and smooths trajectories in milliseconds, enabling precise dynamic obstacle avoidance in complex environments.
Spatial AI Data Acquisition Platform Powered Entirely by Dedicated AI Compute
The platform converts fine-grained human motion trajectories and force feedback into kinematic features that robots can interpret. Backed by a proprietary dataset containing tens of millions of real-world household action samples, its integrated hardware design minimizes motion-retargeting error and supports the learning of complex, multi-step skills.
This substantially improves robot task performance and generalization in unfamiliar environments.