20240017746. ASSESSING PRESENT INTENTIONS OF AN ACTOR PERCEIVED BY AN AUTONOMOUS VEHICLE simplified abstract (Argo Al, LLC)

From WikiPatents
Jump to navigation Jump to search

ASSESSING PRESENT INTENTIONS OF AN ACTOR PERCEIVED BY AN AUTONOMOUS VEHICLE

Organization Name

Argo Al, LLC

Inventor(s)

Constantin Savtchenko of Sewickley PA (US)

Alexander Metz of München (DE)

Andrew T. Hartnett of West Hartford CT (US)

G. Peter K. Carr of Allison Park PA (US)

Greydon Foil of Pittsburgh PA (US)

Lorenzo Nardi of München (DE)

ASSESSING PRESENT INTENTIONS OF AN ACTOR PERCEIVED BY AN AUTONOMOUS VEHICLE - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240017746 titled 'ASSESSING PRESENT INTENTIONS OF AN ACTOR PERCEIVED BY AN AUTONOMOUS VEHICLE

Simplified Explanation

The patent application describes systems and methods for controlling an autonomous vehicle (AV) by generating candidate intentions of an actor (such as a pedestrian or another vehicle) based on the detected action of the actor and a classification associated with the actor. The overall probability for each candidate intention is determined based on the persistence of the candidate intention over a non-interrupted sequence of cycles. Candidate intentions are selected based on their overall probabilities. A subsequent future intention of the actor is forecasted after reaching a goal defined by the selected candidate intention(s). An actor trajectory that is consistent with the selected candidate intention(s) and the subsequent future intention is obtained. The actor trajectory is then used to influence a selected trajectory for the AV.

  • Systems and methods for controlling an autonomous vehicle (AV) are disclosed.
  • Candidate intentions of an actor are generated based on the detected action of the actor and a classification associated with the actor.
  • The overall probability for each candidate intention is determined based on the persistence of the candidate intention over a non-interrupted sequence of cycles.
  • Candidate intentions with higher overall probabilities are selected.
  • A subsequent future intention of the actor is forecasted after reaching a goal defined by the selected candidate intention(s).
  • An actor trajectory consistent with the selected candidate intention(s) and the subsequent future intention is obtained.
  • The actor trajectory is used to influence a selected trajectory for the AV.

Potential Applications

  • Autonomous vehicles can use this technology to better understand and predict the intentions of pedestrians and other vehicles on the road.
  • This can improve the safety and efficiency of autonomous vehicles in complex traffic situations.

Problems Solved

  • The technology solves the problem of accurately predicting the intentions of actors in the environment of an autonomous vehicle.
  • It addresses the challenge of selecting the most probable candidate intentions and forecasting future intentions of actors.

Benefits

  • Improved safety: By accurately predicting and understanding the intentions of actors, autonomous vehicles can make better decisions to avoid accidents.
  • Enhanced efficiency: By selecting the most probable candidate intentions and forecasting future intentions, autonomous vehicles can optimize their trajectories and improve overall traffic flow.


Original Abstract Submitted

systems and methods for controlling an autonomous vehicle (av). the methods comprise: generating candidate intentions of an actor based on a detected action of the actor and a classification associated with the actor; determining an overall probability for each candidate intention based on at least a persistence of the candidate intention over a non-interrupted sequence of cycles (where each cycle represents a time period over which the actor was sensed by a sensor); selecting candidate intention(s) based on the overall probabilities; forecasting a subsequent future intention that the actor may have after reaching a goal defined by the candidate intention(s) which was(were) selected; obtaining an actor trajectory that is consistent with the candidate intention(s) which was(were) selected and the subsequent future intention; and using the actor trajectory to influence a selected trajectory for av.