Nvidia patents robotaxi system with AI dispatcher and virtual rails
Nvidia describes a self-driving shuttle system that uses sensors like LIDAR and cameras to navigate public or private roads. The vehicle follows a set route called a virtual rail but can change paths when needed, while an AI dispatcher manages the fleet to optimize performance.
In the filing’s own words
A system and method for an on-demand shuttle, bus, or taxi service able to operate on private and public roads provides situational awareness and confidence displays. The shuttle may include ISO 26262 Level 4 or Level 5 functionality and can vary the route dynamically on-demand, and/or follow a predefined route or virtual rail. The shuttle is able to stop at any predetermined station along the route. The system allows passengers to request rides and interact with the system via a variety of interfaces, including without limitation a mobile device, desktop computer, or kiosks. Each shuttle preferably includes an in-vehicle controller, which preferably is an AI Supercomputer designed and optimized for autonomous vehicle functionality, with computer vision, deep learning, and real time ray tracing accelerators. An AI Dispatcher performs AI simulations to optimize system performance according to operator-specified system parameters.
What exactly they claim (claim 1)
1. A shuttle comprising: a body comprising a compartment to accommodate at least one passenger; a propulsion, drive train, and steering system to propel the body; sensors disposed on the body including at least one light detection and ranging (LIDAR) sensor, at least one camera, and at least one global positioning system (GPS) sensor; and a processing arrangement comprising at least one central processing unit (CPU), at least one hardware accelerator supporting at least one neural network, and at least one graphics processing unit (GPU) communicatively coupled to the sensors, the processing arrangement to: define a virtual rail comprising a predefined route and one or more stopping points; control the propulsion, drive train, and steering system to propel the body along at least one of the virtual rail or a deviation from the virtual rail, the deviation from the virtual rail being used when one or more conditions are satisfied; identify passengers to ride in the shuttle; and based at least in part on situational awareness provided by the at least one neural network, autonomously determining whether to selectively stop the shuttle at individual stopping points of the one or more stopping points of the virtual rail to at least one of take on or discharge passengers.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- Robotaxi
- Patent number
- US12735069B2
- Application number
- 18407108
- Filed
- Jan 8, 2024
- Granted
- Sep 15, 2026
- Inventors
- 12
- Claims
- 23
Classified under
B60W 60/00253 Operations & transportG01C 21/3415 Physics & computingG01C 21/3438 Physics & computingG01C 21/3617 Physics & computingG05B 13/027 Physics & computingG05D 1/0055 Physics & computingMore from Nvidia in Cars & transport
- Nvidia patents car drowsiness check that uses your body clock Oct 13, 2026
- Nvidia patents 3D camera system to measure passengers in vehicles Oct 13, 2026
- Nvidia patents cruise control that predicts driver's next move Oct 20, 2026
- Nvidia patents dual-brain system for self-driving cars Sep 17, 2026
- Nvidia patents method for self-driving cars to see around corners Sep 17, 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.