Stereo Vision 3D Camera for Navigational Robots

Technology Overview

Visual Perception module (3D sensor, depth camera, stereo vision camera) that allows mobile robots to perceive their environment in 3D, localize themselves, recognize and identify objects of interest, avoid obstacles, and create a 3D map (SLAM - Simultaneous Localization and Mapping).

Visual Perception module (3D sensor) includes a pair of passive RGB cameras and powerful computer GPU an CPU. Visual Perception camera can run computer vision applications without using an external PC.

Technology Features & Specifications

Visual Perception module (3D sensor, depth camera, stereo vision camera) recognizes its environment both in natural light outdoors and in enclosed spaces with poor lighting (passive perception - indoor/outdoor use).

Visual Perception module uses his own computational power to process all algorithms and AI applications. No external PC is needed. 

The platform is open for new apps development. 

Long range: 0,5m - 30m

Dense point cloud - more information for your robot navigation

Main functions:

  • Real-time
  • Avoid obstacles while navigating
  • Plan path in an unknown environment, re-route
  • Recognize and identify objects of interest - human, pallets, charging stations etc.
  • Calculate distance to the object, object size

Potential Applications

  • Autonomous civilian and industrial transportation - AGV's (automated guided vehicle), VGV's (vision guided vehicles), autonomous forklifts, stackers, last mile delivery robots etc.
  • Service robots / Industrial robots / Collaborative robots navigation, obstacle avoidance, object recognition and identification
  • Infrastructure-free robot navigation
  • Safety sensor: pedestrian / machinery anti-collision camera. The sensor is capable to distinguish a person from another obstacle in real time and alert the operator in case of danger

Visual Perception module could be used for computer vision application development and testing.

Customer Benefits

  • Standalone - the truly 'bolt-on' off-the-shelf unit, easy to integrate.
  • Bespoke if needed - available to adapt to a tailor-made application
  • Standard Perception Apps - human detection and tracking; object detection and pose estimation; simultaneous localization and mapping; extensible with third-party perception apps; open for new app development
  • Saves Power - low energy consumption
  • Powerful - integrated very powerful award-winning graphics unit
  • Reliable - ingress protected (IP65), zero maintenance required
  • Intelligent - auto-calibrated, learning, extensible with perception apps
  • Smaller - compact and light enough to be wrist-mounted on a robot
  • Long range - 3-5x longer range than the competition
  • Neutral - non-interfering passive optical sensor

Make an Enquiry