Nvidia patents traffic simulation that predicts how other drivers will move
This patent describes a method for simulating traffic in a virtual environment to test self-driving car software. It uses probability models to predict the likely paths of other vehicles and pedestrians, allowing the system under test to react to realistic, collision-free scenarios.
In the filing’s own words
In various examples, systems and methods are presented for model-based trajectory simulation of agents in a simulated environment. Traffic simulators mimic reality so that autonomous or semi-autonomous vehicle design teams can validate driving models in environments that have diversity and complexity. In some embodiments, for a model-controlled agent of a simulation environment, a plurality of navigation probability distributions are generated, each of the plurality of navigation probability distributions defining a candidate trajectory for the agent to follow. A trajectory is selected for the agent based at least on at least one of the plurality of navigation probability distributions, and the agent is moved within the simulation environment based at least on the selected trajectory. In some embodiments, a search algorithm may be applied across multiple time-steps of a simulation, for example, to identify the occurrence of collision-free sequences of navigation probability distributions.
What exactly they claim (claim 1)
1. One or more processors comprising: one or more circuits to: generate a simulation environment for testing at least one of hardware or software of a system under test, the simulation environment corresponding to a scene including at least one path for vehicle traffic, a representation of the system under test, and a plurality of agents that each represent a vehicle, actor, or object distinct from the representation of the system under test; execute one or more time-steps of a simulation; for at least one agent of the plurality of agents: generate navigation probability distributions for the at least one agent, individual navigation probability distributions of the navigation probability distributions defining a candidate trajectory for the at least one agent to follow with respect to the at least one path that is predicted to avoid collisions between the at least one agent and one or more other agents of the plurality of agents; select a trajectory for the at least one agent corresponding to a selected navigation probability distribution of the navigation probability distributions for the at least one agent; and control movement of the at least one agent within the simulation environment during execution of the one or more time-steps of the simulation based at least on the selected trajectory for the at least one agent; generate sensor data corresponding to one or more sensors of the system under test based at least on the movement of the at least one agent within the simulation environment; output the sensor data to the system under test; receive one or more signals from the system under test; and update a state of the representation of the system under test within the simulation environment based at least on the one or more signals received from the system under test, wherein the one or more signals are generated by the system under test based at least on the sensor data.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- Virtual agent trajectory prediction and traffic modeling for machine simulation systems and applications
- Patent number
- US12789845B2
- Application number
- 17949991
- Filed
- Sep 21, 2022
- Granted
- Nov 10, 2026
- Inventors
- 4
- Claims
- 22
Classified under
B60W 60/0015 Operations & transportB60W 30/0953 Operations & transportB60W 50/0097 Operations & transportB60W 50/14 Operations & transportB60W 60/0011 Operations & transportB60W 2050/146 Operations & transportMore from Nvidia in Cars & transport
- Nvidia patents robotaxi system with AI dispatcher and virtual rails Sep 15, 2026
- 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 system to rate how much a car's sensors can trust their own data Nov 3, 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.
