Extra-vehicular threat predictor
First Claim
1. A method of facilitating safe operation of a vehicle, the vehicle having a vehicle operator and having a vehicle environment including an object, the method comprising:
- obtaining sensor data relating to the vehicle environment;
predicting a vehicle path within the vehicle environment, the vehicle path having a vehicle path uncertainty;
predicting an object path for the object within the vehicle environment;
identifying a collision risk if the vehicle path and the object path intersect;
identifying a vehicle risk if the vehicle path uncertainty is greater than a threshold uncertainty;
providing an alert on identifying the collision risk or the vehicle risk, the alert facilitating tile safe operation of the vehicle;
determining an object oath uncertainty for the object path;
identifying an object risk if the object oath uncertainty is greater than an object threshold uncertainty;
providing the alert on identifying the object risk; and
wherein predicting the vehicle path includes;
creating a world model of the vehicle environment using the sensor data;
detecting changes in the world model at intervals, the vehicle path and the object oath being predicted from the changes in the world model.
3 Assignments
0 Petitions
Accused Products
Abstract
An apparatus for facilitating the safe operation of a vehicle comprises a sensor system, a sensor signal to object identifier, and a world model implemented using, for example, a multiple-input multiple-output (MIMO) algorithm such as a spiking neuron algorithm. Alerts may be provided to the vehicle operator under several conditions, such as the identification of a collision risk between the vehicle and an object, identification of a vehicle risk due to excessive uncertainty in the predicted vehicle path, or identification of an object risk due to excessive uncertainty in a predicted object path.
-
Citations
21 Claims
-
1. A method of facilitating safe operation of a vehicle, the vehicle having a vehicle operator and having a vehicle environment including an object, the method comprising:
- obtaining sensor data relating to the vehicle environment;
predicting a vehicle path within the vehicle environment, the vehicle path having a vehicle path uncertainty;
predicting an object path for the object within the vehicle environment;
identifying a collision risk if the vehicle path and the object path intersect;
identifying a vehicle risk if the vehicle path uncertainty is greater than a threshold uncertainty;
providing an alert on identifying the collision risk or the vehicle risk, the alert facilitating tile safe operation of the vehicle;
determining an object oath uncertainty for the object path;
identifying an object risk if the object oath uncertainty is greater than an object threshold uncertainty;
providing the alert on identifying the object risk; and
wherein predicting the vehicle path includes;
creating a world model of the vehicle environment using the sensor data;
detecting changes in the world model at intervals, the vehicle path and the object oath being predicted from the changes in the world model. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
- obtaining sensor data relating to the vehicle environment;
-
14. A method of facilitating safe operation of a vehicle, the vehicle having a vehicle operator and a vehicle environment including an object, the method comprising:
- collecting sensor data representative of the vehicle environment;
identifying the object within the vehicle environment using the sensor data;creating a world model, the world model including an object model for the object and a vehicle model for the vehicle;
detecting changes in the world model at intervals;predicting a vehicle path for the vehicle from changes in the world model, the vehicle path having a vehicle path uncertainty;
predicting an object path from changes in the world model, the object path having an object path uncertainty; and
providing a collision risk alert if a collision between the vehicle and the object is predicted from the vehicle path and the object path, providing a vehicle risk alert if the vehicle path uncertainty exceeds a vehicle uncertainty threshold, and providing an object risk alert if the object path uncertainty exceeds an object uncertainty threshold, so as to facilitate the safe operation of the vehicle; and
wherein providing the vehicle risk includes;
determining vehicle parameters from the changes in the world model;
determining long-term statistics for the vehicle parameters; and
identifying the vehicle risk using the long-term statistics of the vehicle parameters.
- collecting sensor data representative of the vehicle environment;
-
15. An apparatus for reducing an accident risk for a vehicle, the vehicle having a vehicle operator and a vehicle environment including an object, the apparatus comprising:
- a world modeler, the world modeler receiving object data correlated with objects in the vehicle environment and creating a world model including object parameters and vehicle parameters;
a world model change detector, detecting changes in the world model at intervals, the world model change detector identifying vehicle parameter changes and object parameter changes;
a vehicle path predictor, using the vehicle parameters to predict a vehicle path;
an object path predictor, using the object parameters to predict an object path;
a behavior evaluator, providing a collision alert on establishing a collision risk from the vehicle path and the object path, providing a vehicle risk alert if the vehicle path has an uncertainty greater than a first threshold value, and providing an object risk alert if the object path has an uncertainty greater than a second threshold value; and
wherein providing the vehicle risk includes;
determining vehicle parameters from the changes in the world model;
determining long-term statistics for the vehicle parameters; and
identifying the vehicle risk using the long-term statistics of the vehicle parameters. - View Dependent Claims (16, 17, 18, 19, 20, 21)
- a world modeler, the world modeler receiving object data correlated with objects in the vehicle environment and creating a world model including object parameters and vehicle parameters;
Specification