Vehicle threat detection and response

1. A method, comprising:

based on host vehicle sensor data, determining host vehicle velocities and target vehicle velocities, at respective times within a predefined time interval, and then determining a velocity risk assessment based on comparing the host vehicle velocities and the target vehicle velocities;

based on the host vehicle sensor data, determining host vehicle paths and target vehicle paths within the predefined time interval, and determining a path risk assessment based on a ratio of (1) a number of target vehicle paths that match the host vehicle paths to (2) a number of the host vehicle paths;

based on the host vehicle sensor data, determining host vehicle lane selections and target vehicle lane selections within the predefined time interval, and determine a lane risk assessment based on a ratio of (1) a number of target vehicle lane selections that match the host vehicle lane selections to (2) a number of the host vehicle lane selections;

determining a following risk assessment for the target vehicle relative to the host vehicle based on the velocity risk assessment, the path risk assessment, and the lane risk assessment;

determining the target vehicle is following the host vehicle based on the following risk assessment being above a threshold;

then transmitting data identifying the target vehicle to a remote computer and actuating vehicle components to operate the host vehicle to a location specified by the remote computer; and

transmitting, from the remote computer, a message to an assistance vehicle in response to receiving the data identifying the target vehicle, the message instructing the assistance vehicle to operate to the location.

2. The method of claim 1 , further comprising detecting a distance between the host vehicle and the target vehicle and determining the following risk assessment further based on the distance.

3. The method of claim 1 , wherein the data identifying the target vehicle includes at least one of image data or video data of the target vehicle.

4. The method of claim 1 , wherein the remote computer is one of a portable device, a vehicle computer, or a computer associated with the location.

5. The method of claim 1 , wherein determining the following risk assessment includes obtaining the following risk assessment as output from a machine learning program.

6. The method of claim 1 , further comprising outputting an alert identifying the target vehicle to the host vehicle based on the following risk assessment being above the threshold.

7. The method of claim 1 , wherein comparing a velocity includes determining whether a velocity of the target vehicle adapts to a velocity of the host vehicle.

8. The method of claim 1 , wherein comparing a lane selection includes determining whether lane selections of the target vehicle correspond to two or more lane selections of the host vehicle.

9. A system, comprising a computer including a processor and a memory, the memory storing instructions executable by the processor to:

based on host vehicle sensor data, determine host vehicle velocities and target vehicle velocities, at respective times within a predefined time interval, and then determine a velocity risk assessment based on comparing the host vehicle velocities and the target vehicle velocities;

based on the host vehicle sensor data, determine host vehicle paths and target vehicle paths within the predefined time interval, and determine a path risk assessment based on a ratio of (1) a number of target vehicle paths that match the host vehicle paths to (2) a number of the host vehicle paths;

based on the host vehicle sensor data, determine host vehicle lane selections and target vehicle lane selections within the predefined time interval, and determine a lane risk assessment based on a ratio of (1) a number of target vehicle lane selections that match the host vehicle lane selections to (2) a number of the host vehicle lane selections;

determine a following risk assessment of the target vehicle relative to the host vehicle based on the velocity risk assessment, the path risk assessment, and the lane risk assessment;

determine the target vehicle is following the host vehicle based on the following risk assessment being above a threshold; and

then transmit data identifying the target vehicle to a remote computer and actuate vehicle components to operate the host vehicle to a location specified by the remote computer; and

the remote computer including a second processor and a second memory, the second memory storing instructions executable by the second processor to transmit a message to an assistance vehicle in response to receiving the data identifying the target vehicle, the message instructing the assistance vehicle to operate to the location.

10. The system of claim 9 , wherein the instructions further include instructions to detect a distance between the host vehicle and the target vehicle and to determine the following risk assessment further based on the distance.

11. The system of claim 9 , wherein the data identifying the target vehicle includes at least one of image data and video data of the target vehicle.

12. The system of claim 9 , wherein the remote computer is one of a portable device, a vehicle computer, or a computer associated with the location.

13. The system of claim 9 , wherein determining the following risk assessment includes obtaining the following risk assessment as output from a machine learning program.

14. The system of claim 9 , wherein the instructions further include instructions to output an alert identifying the target vehicle to the host vehicle based on the following risk assessment being above the threshold.

15. The system of claim 9 , wherein comparing a velocity includes determining whether a velocity of the target vehicle adapts to a velocity of the host vehicle.

16. The system of claim 9 , wherein comparing a lane selection includes determining whether lane selections of the target vehicle correspond to two or more lane selections of the host vehicle.

17. A system, comprising a computer including a processor and a memory, the memory storing instructions executable by the processor to:

based on host vehicle sensor data, determining host vehicle velocities and target vehicle velocities, at respective times within a predefined time interval, and then determining a velocity risk assessment based on comparing the host vehicle velocities and the target vehicle velocities;

based on the host vehicle sensor data, determining host vehicle paths and target vehicle paths within the predefined time interval, and determining a path risk assessment based on a ratio of (1) a number of target vehicle paths that match the host vehicle paths to (2) a number of the host vehicle paths;

based on the host vehicle sensor data, determining host vehicle lane selections and target vehicle lane selections within the predefined time interval, and determine a lane risk assessment based on a ratio of (1) a number of target vehicle lane selections that match the host vehicle lane selections to (2) a number of the host vehicle lane selections;

determine a following risk assessment of the target vehicle relative to the host vehicle based on the velocity risk assessment, the path risk assessment, and the lane risk assessment;

determine the target vehicle is following the host vehicle based on the following risk assessment being above a threshold; and

then transmit data identifying the target vehicle to a remote computer and actuate vehicle components to operate the host vehicle to a location specified by the remote computer.