View source for 17949991. VIRTUAL AGENT TRAJECTORY PREDICTION AND TRAFFIC MODELING FOR MACHINE SIMULATION SYSTEMS AND APPLICATIONS simplified abstract (NVIDIA Corporation)

=VIRTUAL AGENT TRAJECTORY PREDICTION AND TRAFFIC MODELING FOR MACHINE SIMULATION SYSTEMS AND APPLICATIONS=


==Organization Name==

[[:Category:NVIDIA Corporation|NVIDIA Corporation]]


[[Category:NVIDIA Corporation]]

==Inventor(s)==

[[:Category:Jonah Philion of Toronto (CA)|Jonah Philion of Toronto (CA)]][[Category:Jonah Philion of Toronto (CA)]]

[[:Category:Jeevan Devaranjan of Toronto (CA)|Jeevan Devaranjan of Toronto (CA)]][[Category:Jeevan Devaranjan of Toronto (CA)]]

[[:Category:Xue Bin Peng of Vancouver (CA)|Xue Bin Peng of Vancouver (CA)]][[Category:Xue Bin Peng of Vancouver (CA)]]

[[:Category:Sanja Fidler of Toronto (CA)|Sanja Fidler of Toronto (CA)]][[Category:Sanja Fidler of Toronto (CA)]]

==VIRTUAL AGENT TRAJECTORY PREDICTION AND TRAFFIC MODELING FOR MACHINE SIMULATION SYSTEMS AND APPLICATIONS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17949991 titled 'VIRTUAL AGENT TRAJECTORY PREDICTION AND TRAFFIC MODELING FOR MACHINE SIMULATION SYSTEMS AND APPLICATIONS

==Simplified Explanation==

The patent application describes systems and methods for model-based trajectory simulation of agents in a simulated environment, specifically focusing on traffic simulators for autonomous or semi-autonomous vehicle design teams. 

* Generation of multiple navigation probability distributions for defining candidate trajectories for agents in a simulation environment.
* Selection of a trajectory for an agent based on the generated navigation probability distributions.
* Moving the agent within the simulation environment based on the selected trajectory.
* Application of a search algorithm across multiple time-steps to identify collision-free sequences of navigation probability distributions.

== Potential Applications ==
This technology can be applied in the development and testing of autonomous vehicle driving models, urban planning simulations, and traffic management systems.

== Problems Solved ==
1. Validation of driving models in diverse and complex environments.
2. Efficient trajectory planning for simulated agents.

== Benefits ==
1. Improved accuracy in simulating agent behavior.
2. Enhanced safety testing for autonomous vehicles.
3. Optimization of traffic flow simulations.

== Potential Commercial Applications ==
Optimized Traffic Flow Simulation Technology for Autonomous Vehicle Testing

== Possible Prior Art ==
Prior art may include existing traffic simulation software used for urban planning and transportation engineering studies.

== Unanswered Questions ==
=== How does this technology handle real-time changes in the simulated environment? ===
The patent application does not specify how the system adapts to dynamic changes during simulation.

=== What computational resources are required to implement this technology effectively? ===
The patent application does not provide details on the computational requirements for running the simulation.


==Original Abstract Submitted==

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.



[[Category:B60W60/00]]
[[Category:B60W30/095]]
[[Category:B60W50/00]]
[[Category:B60W50/14]]