Redefining Radar Perception with AI
Next-level Radar based AI Perception. Tackle any environment, in any condition.
Order our Radar Kit >
Our Technology >
Serving 50+ satisfied companies
And counting - we work with diverse partners across industries and governments.
All-Weather, Any Condition
Rain, night, fog or smoke. Robust perception, no matter what - helping you go further.
A fraction of the cost of LiDAR
LiDAR-like performance, at a fraction of the cost of compareble perception systems.
Compatible with any robot
On-road, off-road, indoor or in-air, we help any robot understand their environment.
Meet our solutions
Perciv’s product line contains solutions for the four main challenges every robot faces. We are passionate about our technology and continiously work on improving it - helping our customers go further.
Perciv Freespace
Detects all obstacles with collision-risk, providing an occupancy or height map for planning and safety.
Perciv Objects
Provides a reliable and customizable list of objects with state-of-the-art classification.
Perciv Egotrack
provides reliable odometry even in GNSS denied environments or harsh weather.
Perciv Fusion
Increases accuracy and robustness by fusing multiple sensors to combine their strenghts.
Technology grounded in science
In our effort to continously advance our technology, our team regularly publishes state-of-the-art research in peer-reviewed papers and conferences.
-
This work introduces Label Any Pointcloud (LeAP), leveraging 2D VFMs to automatically label 3D data with any set of classes in any kind of application whilst ensuring label consistency. Using a Bayesian update, point labels are combined into voxels to improve spatio-temporal consistency. A novel 3D Consistency Network (3D-CN) exploits 3D information to further improve label quality. Through various experiments, we show that our method can generate high-quality 3D semantic labels across diverse fields without any manual labeling. Further, models adapted to new domains using our labels show up to a 34.2 mIoU increase in semantic segmentation tasks.
-
In this experimental study, we apply a state-of-the-art object detector (PointPillars), previously used for LiDAR 3D data, to such 3+1D radar data (where 1D refers to Doppler). To facilitate our experimental study, we present the novel View-of-Delft (VoD) automotive dataset. It contains 8693 frames of synchronized and calibrated 64-layer LiDAR-, (stereo) camera-, and 3+1D radar-data acquired in complex, urban traffic. It consists of 123106 3D bounding box annotations of both moving and static objects, including 26587 pedestrian, 10800 cyclist and 26949 car labels.The VoD dataset is made freely available for scientific benchmarking at https://intelligent-vehicles.org/datasets/view-of-delft/.
Try our ground-breaking perception
Radar Kit
Radar Kit for off-highway applications. Perfect for physical AI, both indoors and outdoors.
New
Explore >
Explore the capabilities of our radar perception on your system. Whether you are trying radar for the first time, or want a model fine-tuned for your usecase - We have you covered!
Development Kit
Radar Kit for long-range applications. Ideal for automotive and highway type scenarios.
Contact Us >
Coming soon
Helping you achieve your goal - in any condition
Perciv AI’s products have been deployed on cars, trucks, forklifts, off-roaders, drones, and beyond. We help any robot to understand their environment -regardless of the conditions.
Agriculture
Logistics
Construction
Defense
Our mission: Make reliable pereception affordable for anyone
At Perciv, we believe robust, reliable perception should not be reserved for those who can afford it. We are driven to innovate beyond the current status quo, working with our customers and partners to advance perception to new levels.