Detection of unsafe cabin conditions in autonomous vehicles
Devices, systems and processes for the detection of unsafe cabin conditions that provides a safer passenger experience in autonomous vehicles are described. One example method for enhancing passenger safety includes capturing at least a set of images of one or more passengers in the vehicle, determining, based on the set of images, the occurrence of an unsafe activity in an interior of the vehicle, performing, using a neural network, a classification of the unsafe activity, and performing, based on the classification, one or more responsive actions.
1. A system for enhancing passenger safety in a vehicle, comprising:
a processor; and
an internal sensor system, coupled to the processor, configured to capture at least a set of images of one or more passengers in the vehicle,
wherein the processor is configured to:
determine, based on the set of images, the occurrence of an unsafe activity,
perform, using a neural network, a classification of the unsafe activity, and
perform, based on the classification, one or more responsive actions.
2. The system of claim 1 , wherein the unsafe activity is a protrusion of an object through a window or a door of the vehicle, and wherein the one or more responsive actions comprises at least one of warning the one or more passengers, documenting the unsafe activity, increasing a distance between the vehicle and one or more proximate vehicles, or stopping the vehicle if the unsafe activity cannot be mitigated.
3. The system of claim 1 , wherein the unsafe activity is an object thrown out of a window or a door of the vehicle, and wherein the one or more responsive actions comprises at least one of warning the one or more passengers, documenting the unsafe activity, or stopping the vehicle if the object is of critical value.
4. The system of claim 1 , wherein the unsafe activity is an unrestrained child amongst the one or more passengers, and wherein the one or more responsive actions comprises documenting the unsafe activity or ensuring that the vehicle does not start until the unsafe activity is mitigated.
5. The system of claim 1 , wherein the unsafe activity is a presence of a dangerous object in a cabin of the vehicle, and wherein the one or more responsive actions comprises at least one of documenting the unsafe activity, notifying a central ride monitoring system, or notifying authorities of the presence of the dangerous object.
6. The system of claim 1 , wherein the unsafe activity comprises vandalism of a cabin of the vehicle, and wherein the one or more response actions comprises documenting the unsafe activity or notifying a central ride monitoring system.
7. The system of claim 1 , wherein the unsafe activity comprises inappropriate behavior by at least one of the one or more passengers, and wherein the one or more response actions comprises at least one of documenting the unsafe activity, notifying a central ride monitoring system, or notifying authorities of the presence of the inappropriate behavior.
8. The system of claim 1 , wherein the unsafe activity comprises an incapacitated passenger, and wherein the one or more response actions comprises notifying a central ride monitoring system or notifying authorities of the presence of the incapacitated passenger.
9. The system of any of claim 1 , wherein the internal sensor system comprises one or more cameras, a millimeter wave sensor or an infrared sensor.
10. A method for enhancing passenger safety in a vehicle, comprising:
capturing at least a set of images of one or more passengers in the vehicle;
determining, based on the set of images, the occurrence of an unsafe activity in a cabin of the vehicle;
performing, using a neural network, a classification of the unsafe activity, wherein the unsafe activity is one of a predetermined number of unsafe activities; and
performing, based on the classification, one or more responsive actions.
11. The method of claim 10 , further comprising:
training, prior to performing the classification, the neural network based on a plurality of images depicting each of the predetermined number of unsafe activities.
12. The method of claim 10 , wherein the set of images is captured using at least one camera with depth-sensing capabilities.
13. The method of claim 10 , wherein the unsafe activity is at least one of a protrusion of an object through a window or a door of the vehicle, an object thrown out of the window or the door of the vehicle, an unrestrained child amongst the one or more passengers, a presence of a dangerous object in the cabin of the vehicle, vandalism of the cabin of the vehicle, inappropriate behavior by at least one of the one or more passengers, or an incapacitated passenger.
14. The method of claim 13 , wherein the one or more responsive actions comprises at least one of documenting the unsafe activity, notifying a central ride monitoring system, or notifying a law enforcement authority of the unsafe activity.