AI Computer Vision is an AI skill that enables all UiPath Robots to see every element on a computer screen. Now, businesses and RPA developers can automate tasks on most virtual desktop interface (VDI) environments—regardless of framework or operating system.
With AI Computer Vision, your robot can see on-screen elements with human-like recognition.
AI Computer Vision datasheet 
Lets robots recognize and interact with more on-screen fields and components—even Flash, Silverlight, PDFs, and images
Relieves issues with failure-prone image automation techniques and with selector-based targeting on desktops
Includes VDI environments (Citrix, VMWare, Microsoft RDP, VNC, and others) for desktop and web applications
Provides details, validation, and notifications about on-screen selections via an on-screen wizard
Does not require advanced image recognition techniques; the recorder can generate full vision-based automation
Supports automation on Windows, Linux, Android, and other operating systems
Simplifies VDI-to-desktop automation by reducing necessary modifications
Deploys via SaaS; available on-premises for Linux and Windows. Desktop Server is now also available.
Enables automations that include drop-down and checkbox elements
UiPath robots' human-like vision comes from a neural network with a combination of custom screen OCR and text fuzzy matching with a multi-anchoring system.
See how AI Computer Vision compares to traditional selector-based activities as you see it at work in this training video.
AI Computer Vision eliminates the reliance on selectors, while still maintaining familiar workflows for RPA developers. With an increase in visible screen elements, more automations are possible.
