Cognitive state evaluation for vehicle navigation
Disclosed embodiments provide cognitive state evaluation for vehicle navigation. The cognitive state evaluation is accomplished using a computer, where the computer can perform learning using a neural network such as a deep neural network (DNN) or a convolutional neural network (CNN). Images including facial data are obtained of a first occupant of a first vehicle. The images are analyzed to determine cognitive state data. Layers and weights are learned for the deep neural network. Images of a second occupant of a second vehicle are collected and analyzed to determine additional cognitive state data. The additional cognitive state data is analyzed, and the second vehicle is manipulated. A second imaging device is used to collect images of a person outside the second vehicle to determine cognitive state data. The second vehicle can be manipulated based on the cognitive state data of the person outside the vehicle.
1. A computer-implemented method for vehicle manipulation comprising:
obtaining one or more images of a first occupant of a first vehicle using a first imaging device within the first vehicle, wherein the one or more images include facial data of the first occupant;
analyzing, using a first computing device, the one or more images to determine cognitive state data for the first occupant;
learning a set of layers and weights based on the cognitive state data;
collecting one or more images of a second occupant of a second vehicle, wherein the one or more images of the second occupant are analyzed to determine additional cognitive state data; and
manipulating the second vehicle based on the additional cognitive state data that was analyzed using the set of layers and weights that were learned.
2. The method of claim 1 wherein the second vehicle is an autonomous or semiautonomous vehicle.
3. The method of claim 1 wherein the second occupant is a driver of the second vehicle.
4. The method of claim 1 wherein the second occupant is a passenger of the second vehicle.
5. The method of claim 1 wherein the manipulating includes warning the second occupant when the additional cognitive state data indicates inattentiveness.
6. The method of claim 1 wherein the manipulating includes passing control from the second occupant to the semiautonomous second vehicle based on the additional cognitive state data.
7. The method of claim 1 wherein the manipulating includes passing control from the second occupant to the autonomous second vehicle based on the additional cognitive state data.
8. The method of claim 1 wherein the first occupant and the second occupant are the same occupant.
9. The method of claim 1 further comprising augmenting the cognitive state data based on audio data collected on the first occupant.
10. The method of claim 1 further comprising augmenting the additional cognitive state data based on audio data collected on the second occupant.
11. The method of claim 10 wherein the audio data includes speech.
12. The method of claim 1 further comprising collecting, using a second imaging device, images of a person outside of the second vehicle, wherein the images of the person outside of the second vehicle are analyzed to determine cognitive state data for the person outside of the second vehicle.
13. The method of claim 12 wherein the person outside of the second vehicle is a pedestrian.
14. The method of claim 12 wherein the images of a person outside of the second vehicle include facial images of the person.
15. The method of claim 12 wherein the images of a person outside of the second vehicle include body posture images of the person.
16. The method of claim 12 further comprising further manipulating the second vehicle based on the cognitive state data for the person outside of the second vehicle.
17. The method of claim 16 wherein the further manipulating includes automatically slowing the second vehicle.
18. The method of claim 16 wherein the further manipulating includes notifying a custodial driver of the second vehicle.
19. The method of claim 1 further comprising augmenting the additional cognitive state data based on images from one or more additional vehicle occupants of the second vehicle.
20. The method of claim 1 further comprising tagging the cognitive state data with sensor data.
21. The method of claim 20 wherein the sensor data includes one or more of vehicle temperature, outside temperature, time of day, level of daylight, weather conditions, headlight activation, windshield wiper activation, entertainment center selection, or entertainment center volume.
22. The method of claim 1 wherein the learning is performed using a deep neural network.
23. The method of claim 22 wherein the learning is performed using a convolutional neural network.
24. A computer program product embodied in a non-transitory computer readable medium for vehicle manipulation, the computer program product comprising code which causes one or more processors to perform operations of:
obtaining one or more images of a first occupant of a first vehicle using a first imaging device within the first vehicle, wherein the one or more images include facial data of the first occupant;
analyzing, using a first computing device, the one or more images to determine cognitive state data for the first occupant;
learning a set of layers and weights based on the cognitive state data;
collecting one or more images of a second occupant of a second vehicle, wherein the one or more images of the second occupant are analyzed to determine additional cognitive state data; and
manipulating the second vehicle based on the additional cognitive state data that was analyzed using the set of layers and weights that were learned.
25. A computer system for vehicle manipulation comprising:
a memory which stores instructions;
one or more processors attached to the memory wherein the one or more processors, when executing the instructions which are stored, are configured to:
obtain one or more images of a first occupant of a first vehicle using a first imaging device within the first vehicle, wherein the one or more images include facial data of the first occupant;
analyze, using a first computing device, the one or more images to determine cognitive state data for the first occupant;
learn a set of layers and weights based on the cognitive state data;
collect one or more images of a second occupant of a second vehicle,
wherein the one or more images of the second occupant are analyzed to determine additional cognitive state data; and
manipulate the second vehicle based on the additional cognitive state data that was analyzed using the set of layers and weights that were learned.