A bolt on set of 'Eyes' equipped with AI enhanced 'Brain' when better, more affordable environmental perception is needed. VIPER TM enables intelligent automation with the turn-key set of hardware and AI software.

Request Quote
Request Demo

Lack of perception is a sandbag of intelligent automation

Industry 4.0 revolution is all about unleashing the power of intelligent machines so they can leave their safety cages. Unless they are versatile, modular, and reusable in different scenarios, they will not comply with the new standard.


industry 4.0

The new generation of robotic machines strongly depend on the ability to acquire, organize, and interpret surrounding visual data in real-time in order to stay aware of environmental situation and act both safely and adequately.


Depth Camera System

  • Depth range from 1m to over 30m
  • Diagonal field of view up to 92° (77° x 55°)
  • Industrial grade Alu with IP65 protection
  • Built-in NVIDIA® JetsonTM TX2 Module

Standard Perception Apps

  • Human detection and tracking
  • Object detection and pose estimation
  • Simultaneous localization and mapping
  • Extensible with third-party perception apps

Bespoke Perception Apps

  • Exclusive to a particular customer
  • Adapted to a tailor-made application
  • Pre-integrated with customer’s host system

Customization & Support

  • Custom baseline, optics, and sensors
  • Housing-free assembly for integration
  • Flexible support options


image modalities

Multiple real-time image modalities

2D/3D video, point cloud output, etc.

ROS integration

ROS and OpenCV integration

Supports industry standard APIs

image processing

On-board image processing

Uses internal GPU for image processing

object tracking

Object detection & tracking

Humans, gestures, infrastructure

Unlimited perception capacity

Unlimited perception capacity

Extensible with perception apps

Compatible with other sensors

Compatible with other sensors

Modular image processing pipeline


Saves Power

Low energy consumption


Ingress protected, zero maintenance required

Long range

3-5x longer than the competition


The truly ‘bolt on’ off-the-shelf unit, easy to integrate


Auto-calibrated, learning, extensible with perception apps


Non-interfering passive optical sensor


Integrated very powerful award-winning graphics unit


Compact and light enough to be wrist-mounted on a robot

Bespoke if needed

Available to adapt to a tailor-made application

application examples

Rubedo flexible software and tailor-made sensors enable 2D/3D computer vision application accross all domains.

service robotics

Service robotics

GPS-free navigation, interaction

material handling

Material handling

Navigation, manipulation



Crop inspection



Intruder detection and localization



Quality inspection



Navigation, interaction

technical data

Technical Specifications


Dimensions   246 x 98 x 35mm
Stereo Baseline   200mm
Weight   0.8kg (without cables)
Power Consumption   0.4 – 2.0A @ 12V (min – max)
Operating Temperature   -10°C to 40°C
Communication Interface   1Gb/s Ethernet
Mounting Interface   1/4" - 20 UNC, M4 mounting holes
Ingress Protection   IP65


Lens   3.6mm, fixed focus
Sensor   2 x 1/3" @ 3.4 MP low light, 16:9 aspect ratio
Field of View   70° x 43° x 82° (H x V x D)
Embedded Computer   NVIDIA® Jetson™ TX2 Module
Memory   8GB
Data Storage   32GB


Algorithm Family   Semi-global Block Matching, adjustable
Depth Frame Rate   up to 40FPS, adjustable
Depth Range   up to 50m (1-15m optimal range)
Depth Resolution   up to HD (1280 x 720), adjustable
Depth Disparities   32-256, adjustable
Output   disparity map, RGBD point cloud
Synchronization   per frame (outgoing data timestamped)

System Requirements

OS   Linux + ROS, Windows 10 + .NET4.5
Processor   Intel Core i3 or faster
RAM   4GB or more
Interface   Ethernet/TCP

Evaluation Kit

VIPER™ Evaluation Kit is shipped with ROS Kinetic Kame based SDK, which provides C++ API to both low- and high-level access to the device: from controlling common parameters (video mode, frame rate, exposure, WB, gain) to outputting 3D point cloud, normals, depth map. In addition, API provides functions for dominant plane detection, background subtraction, bounding geometrical shape fitting, box detection, and natural object detection based on pre-trained reference models. Available 3rd party APIs: OpenCV and PCL. Sample code is provided that clarifies API features. Supported Linux compilers: gcc-4.8 or higher. Package contents: VIPER™ 3D Visual Perception System, AC adapter, Ethernet cable, Tripod, User Guide.

Request Quote