Stereolabs Unveils Terra AI, the Next Generation of General-Purpose Artificial Intelligence for Robots

New technology is capable of changing the face of agriculture, construction and logistics by improving autonomous capabilities

Stereolabs, a pioneer in vision-based sensing technology, today introduced the latest addition to the company's vision platform portfolio, Terra AI. This new technology is a groundbreaking, general-purpose AI, enabling robots and systems to operate with heightened safety and exceptional precision. Designed for an optimized implementation of front, back, and surround cameras for autonomous robots, Terra AI leverages monocular and stereo vision to provide 4D volumetric perception with unprecedented accuracy. This new technology performs depth, localization, semantic, obstacle detection and fusion from multiple cameras in both space and time. It represents a leap forward in the ability of autonomous robotics to perceive space.


Vision-based full autonomy for robots is a non-trivial task that requires multiple features to be performed simultaneously and efficiently on embedded hardware: depth estimation for spatial awareness, visual-inertial odometry for indoor and outdoor localization, semantic understanding for obstacle classification, terrain mapping and robust detection of people surrounding the robot for safety. Terra AI is a groundbreaking large Neural Network Architecture crafted with fast, memory-efficient, low-level code to perform those tasks concurrently on low-power embedded computers, enabling the processing of high-frequency, high-volume data from ZED cameras on the embedded NVIDIA® Jetson™ platform.

Combining the high-performance NVIDIA® Jetson™ module with Terra AI, the Stereolabs vision platform is engineered with a blend of industry-proven hardware - the ZED cameras (including stereo and new mono cameras) - and software solutions. As such, Stereolabs supports various functions needed for enhanced perception around machines to allow for safe navigation and manipulation.

Many industries - from agriculture to logistics to construction and beyond - must produce at a higher volume and execute faster than ever before, all with fewer resources. At the same time, they're contending with labor shortages and what can be hazardous working conditions. Autonomous robots are key to solving these challenges, but they need the ability to evaluate their surroundings, interpret data and complete tasks independently to be effective. Advanced sensing technology is crucial for unlocking those capabilities, and Terra AI is answering the call.

Terra AI offers a scalable way to deploy autonomous machines - such as tractors, mowers, utility vehicles, AMR, robotic arms and more - by leveraging low-cost cameras combined with NVIDIA® Jetson™ Orin GPU to provide a panoramic 360-degree surround view around the robot. The elimination of LiDAR or radar indicates a significant shift towards lower-cost scalable solutions.

"As we further collaborate with manufacturers and system integrators, our latest Terra AI technology aims to address a growing need for a more open, adaptable and scalable vision platform delivering 360-degree perception and driving true autonomy," said Cecile Schmollgruber, Chief Executive Officer of Stereolabs. "Terra AI will allow companies across industries to invest in autonomous robotics at scale, helping them run their operations with greater efficiency and precision at lower cost."

Availability

Terra AI is now in research preview. It will be available to Stereolabs Enterprise customers in Q2 2024, and later on to all users via the ZED SDK. The ZED SDK is one of the industry's most advanced, open and scalable AI Vision platforms, used by 100,000+ developers around the world. It is designed to help makers and industry leaders produce safe, smart autonomous applications running 24/7.

As one of the industry's most scalable and open systems for autonomous robotics, the ZED SDK supports flexible deployment options with its ability to scale from entry-tier front camera applications to higher levels of automation that require comprehensive surround-view camera applications, allowing for a common implementation of features and requirements across virtually all machine types. The ZED SDK offers a uniquely designed modular architecture to extend the flexibility for manufacturers to integrate depth sensing, indoor and outdoor localization, obstacle detection and people detection to support better customization and integration.

To learn more about Terra AI, visit https://www.stereolabs.com/our-technology.

About Stereolabs

Stereolabs is the leading provider of 3D depth and motion sensing solutions based on stereo vision and artificial intelligence. From robots to drones and cars, Stereolabs empowers machines with the ability to see and understand. We enable developers across multiple industries to create truly intelligent machines and applications that improve our daily lives. Stereolabs offers an expanded ecosystem with various industry-proven hardware and software stacks.

Featured Product

3D Vision: Ensenso B now also available as a mono version!

3D Vision: Ensenso B now also available as a mono version!

This compact 3D camera series combines a very short working distance, a large field of view and a high depth of field - perfect for bin picking applications. With its ability to capture multiple objects over a large area, it can help robots empty containers more efficiently. Now available from IDS Imaging Development Systems. In the color version of the Ensenso B, the stereo system is equipped with two RGB image sensors. This saves additional sensors and reduces installation space and hardware costs. Now, you can also choose your model to be equipped with two 5 MP mono sensors, achieving impressively high spatial precision. With enhanced sharpness and accuracy, you can tackle applications where absolute precision is essential. The great strength of the Ensenso B lies in the very precise detection of objects at close range. It offers a wide field of view and an impressively high depth of field. This means that the area in which an object is in focus is unusually large. At a distance of 30 centimetres between the camera and the object, the Z-accuracy is approx. 0.1 millimetres. The maximum working distance is 2 meters. This 3D camera series complies with protection class IP65/67 and is ideal for use in industrial environments.