Give robots of every shape and size the perception stack they need for navigation, manipulation, data capture, and human-aware autonomy.

The eyes and brains
for intelligent robots

Give robots of every shape and size the perception stack they need for navigation, manipulation, data capture, and human-aware autonomy.

Case Studies

Real-world use cases from businesses leveraging Luxonis for smarter vision systems.

Clearpath Robotics

Case Study

Clearpath Robotics

Clearpath Robotics by Rockwell Automation is redefining how mobile robots are built, tested, and deployed. Through platforms like the TurtleBot 4 and Husky A300, they give researchers, educators, and enterprises a developer-friendly foundation to accelerate autonomy, whether in a classroom or on rugged industrial terrain.

Pollen Robotics

Case Study

Pollen Robotics

Pollen Robotics is a French startup focused on creating open and ethical robotics platforms that empower developers and researchers worldwide. They are best known for Reachy, an open-source humanoid robot designed for human-robot interaction, manipulation, and embodied AI research.

Proven applications for
Robotics & AMRs

These are the field-proven scenarios where OAK consistently fits best

Humanoid Robots

Humanoid Robots

Add real-time depth and visual understanding so humanoids can navigate spaces, interact with objects, and operate safely around people.

Recommended device

OAK FFC-4P

A modular FFC vision platform for custom stereo baselines, synced sensors, and on-device processing in robotics flexible and advanced robotic applications.

OAK-D S2

A USB stereo camera with high-resolution color imaging and on-device AI, well suited for robotics, prototyping, and embedded vision workflows.

Customer Story

Why Choose Luxonis

Find out what advantages our products offer specifically for your industry

Modular FFC camera systems

Flexible camera modules make it easier to embed high-performance vision into custom robot designs, compact chassis, and unusual sensor layouts.

Custom baselines

Compact integration

Robotics-friendly form factors

Validate faster with prebuilt examples

Start with apps, reference implementations, and ready-to-evaluate models that help you prove an OAK-powered workflow before building everything from zero.

Industry Examples

References for robotics teams evaluating ROS-native deployment, SLAM, and real-world autonomy workflows.

Running ROS2 onboard OAK4-D

Running ROS2 onboard OAK4-D

A practical reference for keeping perception local to the robot instead of offloading it.

Visual SLAM on ROS 2

Visual SLAM on ROS 2

See how wheel odometry and OAK perception can work together in a robotics stack.

Hub Apps

Fast ways to validate data capture and exploratory perception workflows on real robotic platforms.

Data Collection

Capture synchronized edge data to train and improve custom robotics models.

DINO Tracking

Useful in prototyping phases when custom detection models are not ready yet.

Open Vocabulary Object Detection

A flexible prototyping tool for early-stage robotics workflows before custom models exist.

OAK-examples

Core building blocks for obstacle avoidance, ROS, and 3D scene understanding.

Collision Avoidance

Strong starting point

Collision Avoidance

A strong base for mobile autonomy, navigation, and obstacle-aware behavior.

Strong starting point

Spatial Detections

A practical 3D detection building block for object localization and navigation.

ROS Follow Object

A practical ROS-native reference for person-following, spatial detections, and mobile robotics behaviors.

Strong starting point

Human Pose

A strong starting point for imitation, safety, and human-aware robotics applications.

Strong starting point

Hand Pose

Useful for demonstration learning, tool interaction, and close-range manipulation research.

RGBD Pointcloud

A clear starting point for 3D scene understanding and spatial robotics workflows.

Model Zoo

Ready-to-evaluate models for navigation, open-vocabulary perception, low-light recovery, and depth-first robotics stacks.

eWaSR

eWaSR

A segmentation model for obstacle-aware autonomous navigation in water and maritime robotics workflows.

YOLO-World L

YOLO-World L

A flexible open-vocabulary detection model for robotics teams exploring new objects and tasks quickly.

Zero-DCE

Zero-DCE

Useful for brightening difficult low-light camera feeds before downstream perception or navigation.

Foundation Stereo

Foundation Stereo

A strong depth-estimation option for robots that need robust spatial understanding and obstacle geometry.

Contact Our Team

Our dedicated team is available for technical support, business solutions, and more. Let us provide the help you need.