Nvidia patents AI system to manage robot inventory movement
Nvidia describes a system that uses AI to create a digital copy of a physical space, like a store or warehouse, to track where items are in real time. The system then selects the best robots to move those items and calculates the most efficient paths for them to follow.
In the filing’s own words
In various examples, Artificial Intelligence (AI)-based systems and methods may be used to autonomously manage the movement of items in a variety of environments, such as a retail space. For instance, the systems and methods of the present disclosure may (e.g., using one or more AI models) continuously update a virtual representation (e.g., digital twin) of an environment based on images depicting the environment. The virtual representation of the environment may be used to track locations of various objects in real time. In some examples, the systems of the present disclosure may use the virtual representation of the environment to select optimal machines for moving items, select optimal paths for the machines to follow, etc. Additionally, the systems of the present disclosure may use 3D models of items in the virtual representation to determine grasps and/or control commands for manipulators of the machines to pick up the items.
What exactly they claim (claim 1)
1. A method comprising: generating, based at least on using one or more language models to process input data corresponding to a request, text data representing one or more tasks associated with moving one or more items in an environment; generating, based at least on image data representing one or more images depicting one or more portions of the environment, a simulated version of the environment; determining, using the simulated version of the environment and based at least on the text data, one or more machines from among a plurality of machines that are located within a threshold proximity of one or more first locations in the environment corresponding to the one or more items; and based at least on the one or more machines being located within the threshold proximity of the one or more first locations, causing the one or more machines to perform one or more control operations to move the one or more items from the one or more first locations to one or more second locations in the environment.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- ARTIFICIAL INTELLIGENCE-BASED INVENTORY MANAGEMENT FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
- Publication number
- US20260299557A1
- Application number
- 19091183
- Filed
- Mar 26, 2025
- Published
- Oct 1, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G05B 19/4155 Physics & computingG06F 30/13 Physics & computingG06T 11/60 Physics & computingG05B 2219/50391 Physics & computingMore from Nvidia in Robots & automation
- Nvidia patents robot control using language models to predict 3D positions Sep 10, 2026
- Nvidia patents method to teach humanoid robots to use hands via simulation Oct 15, 2026
- Nvidia patents 3D scene mapping that lets robots understand objects by name Oct 15, 2026
- Nvidia patents robot system that learns tasks from visual data Sep 29, 2026
- Nvidia patents method for robots to estimate object positions from images Oct 13, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.
