Aurora S' NEW

Fully integrated Al spatial perception system that builds world models

The dedicated eyes for embodied intelligence

Built-in computing algorithms with direct           Self-developed AI-VSLAM engine         180° fisheye colour camera         120° Ultra-wide angle stereo depth vision                 Pixel-level semantic 

            output of mapping                       designed to meet                                                       (end-to-end deep learning solution)         recognition of over

          and localization result               demanding requirements                                                                                                                 hundred of objects

           Multi-modal fusion for                One-click dense 3D           Seamless integration with VLA/VLN    Open platform supporting      Compact fully integrated 

             semantic mapping                 reconstruction, support         training systems for embodied AI     various SDKs including C++,                 design

                                                                3DGS solutions                                                                      ROS1/ROS2, and Python

Aurora S is the new-generation fully integrated AI spatial perception system from SLAMTEC's Insight Series. By deeply integrating vision, inertial navigation, and SLAMTEC's self-developed AI-VSLAM technology, it provides robots and intelligent agents with out-of-the-box high-precision 3D perception, mapping, and semantic understanding. This greatly lowers integration and development barriers, accelerates the deployment of intelligent applications, and serves as a dedicated perception system for the era of embodied intelligence.

Built-in Intelligence , Beyond a Sensor

Aurora S integrates AI-VSLAM for full-scene 3D mapping and localization, stereo depth estimation, semantic recognition, and dedicated compute hardware. It delivers real-time, high-quality spatial perception outputs—mapping, localization, and more—directly to the user, without the need for additional compute resources or in-house algorithm development.

PhotoReal Mapping : Redefining SLAM for the Embodied AI Era

Unlike traditional SLAM systems that output only sparse point clouds, Aurora S employs built-in deep learning multimodal perception to generate dense, richly textured maps with precise localization. Its semantic recognition engine enhances geometric maps with real-time semantic labeling, ushering spatial navigation into the multimodal perception era—purpose-built for embodied intelligence.

                                     Traditional SLAM System                                                   Dense Textured Map by Aurora

Next-Generation Al-VSLAM:Built for Extreme Challenges

Aurora S integrates SLAMTEC's self-developed Al-VSLAM system, replacing traditional rule-based methods with deep learning. From uneven open fields to vast outdoor spaces spanning millons of square meters, and even highly complex indoor environments,Aurora S has proven its stability and reliability under the toughest conditions 

                      Unordered feature points with traditional extraction                                   Aurora Deep Learning Solution

Unshaken by Swaying Grass，Delivering Outstanding Performance

environmental disturbances,keenlycapturessubtlefeaturesinthescene,

andcontinuouslydelivershigh-qualitylocalizationand mapping data. 

                    Traditional Solution Localization Gap                                     Aurora Solution Stable Localization

Real-Time Loop Closure & Relocalization

Built-in Al-VSLAM enables online loop detection an and error correction,delivering precise,reliable mapping without external compute.

Dense Depth Perception Without Extra Sensors

Aurora S integrates a binocular dense depth sensing system that delivers wide-angle point clouds (120° HFOV) at 15 fps. Powered by an end-to-end deep learning pipeline, it maintains stable performance even in weak-texture or high-glare environments, with strict pixel-level alignment to RGB imagery. Users can directly leverage this data for real-time obstacle detection and 3D scene reconstruction—without additional sensors.

From Spatial Localization to Spatial Intelligence

Aurora S integrates a high-performance real-time semantic segmentation and object recognition engine, delivering pixel-level results. It supports recognition of 18 outdoor scene categories and over 80 indoor object types, providing foundational support for VLN and VLA. The system also allows customized recognition tasks, integrates depth data to generate semantic maps, and advances spatial intelligence.

Plug-and-Play , No External Dependencies

Rich interfaces and expandability, supporting DC 9–24V power supply or USB Type-C PD3.0

Open and Flexible Platform
Support Various SDKs and platforms

Aurora provides the Remote UI visualization tool and Remote SDK, enabling fast implementation of advanced functions such as dense mapping, semantic mapping, and 3DGs reconstruction.