Motor vehicles with blind spot modeling
Systems and methods for proactively monitoring when a driver's own motor vehicle may enter into the blind spot of another vehicle include a blind spot modeling system that identifies and builds models of nearby vehicles. The models, which include details about the vehicle mirrors, including their locations and orientations, are used to determine visible regions or zones and regions are zones that are not visible to the driver from the mirrors (blind spots). The blind spot modeling system may take action when the driver's own vehicle is in another vehicle's blind spot, including sending the driver alerts and/or modifying the operation of one or more vehicle systems to automatically move the driver's vehicle out of the blind spot of the other vehicle.
1 . A motor vehicle, comprising:
one or more sensors;
a vehicle safety system comprising a processor and memory storing instructions executable by the processor, the processor further configured to:
receive data for a target vehicle from the one or more sensors;
build a computer model of the target vehicle using the received data, wherein the computer model includes at least one model mirror having a modeled position and a modeled orientation;
determine a blind spot zone for the target vehicle using geometric optics software or ray tracing software to identify, based on the modeled position and the modeled orientation of the at least one model mirror, points that are not visible in the at least one model mirror;
determine a position of the motor vehicle relative to the target vehicle and determine that the motor vehicle is in the blind spot zone of the target vehicle; and
modify the operation of the motor vehicle to move the vehicle out of the blind spot of the target vehicle.
2 . The motor vehicle according to claim 1 , wherein the vehicle safety system is further configured to identify portions of the target vehicle using computer vision.
3 . The motor vehicle according to claim 2 , wherein the vehicle safety system is further configured to construct the computer model of the target vehicle using the identified portions of the target vehicle.
4 . The motor vehicle according to claim 3 , wherein the vehicle safety system is configured to retrieve archived vehicle data for use in building the computer model of the target vehicle.
5 . The motor vehicle according to claim 1 , wherein the vehicle safety system is further configured to identify one or more of a make, model, or year of the target vehicle using a classifier comprising a convolutional neural network, and retrieve archived vehicle data associated with the one or more of make, model, or year for use in building the computer model of the target vehicle.
6 . The motor vehicle according to claim 1 , wherein the vehicle safety system is further configured to determine the modeled orientation of the at least one model mirror from sensed data captured by the one or more sensors.
7 . The motor vehicle according to claim 1 , wherein the motor vehicle further includes a display and wherein the vehicle safety system is further configured to send information to the display to highlight the location of the target vehicle for a driver of the motor vehicle.
8 . The motor vehicle according to claim 1 , wherein the vehicle safety system is further configured to detect a location and orientation of a head of a driver and use the location and orientation of the head of the driver as an input to the geometric optics software or ray tracing software to determine, based on a viewing angle from the head of the driver to the at least one model mirror, the points that are not visible in the at least one model mirror.
9 . A motor vehicle, comprising:
one or more sensors;
a vehicle safety system comprising a processor and memory storing instructions executable by the processor, the processor further configured to:
receive data for a target vehicle from the one or more sensors;
build a computer model of the target vehicle using the received data, wherein the model includes at least one model mirror having a modeled position and a modeled orientation;
detect a location and orientation of a head of a driver of the target vehicle;
determine a blind spot zone for the target vehicle using geometric optics software or ray tracing software applied to the computer model of the target vehicle to identify, based on the modeled position and the modeled orientation of the at least one model mirror and based on the location and orientation of the head of the driver, points that are not visible to the driver in the at least one mirror;
determine a position of the motor vehicle relative to the target vehicle and determine that the motor vehicle is in the blind spot zone of the target vehicle; and
modify the operation of the motor vehicle to move the vehicle out of the blind spot of the target vehicle.
10 . The motor vehicle according to claim 9 , wherein the vehicle safety system is further configured to modify the operation of the motor vehicle by engaging an autonomous driving system to automatically move the vehicle out of the blind spot of the target vehicle.
11 . The motor vehicle according to claim 9 , wherein the vehicle safety system is further configured to modify the operation of the motor vehicle by automatically changing a speed of the motor vehicle to automatically move the vehicle out of the blind spot of the target vehicle.
12 . The motor vehicle according to claim 9 , wherein the vehicle safety system is further configured to modify the operation of the motor vehicle by automatically changing a steering direction of the motor vehicle to automatically move the vehicle out of the blind spot of the target vehicle.
13 . The motor vehicle according to claim 9 , wherein the vehicle safety system is further configured to determine the modeled orientation of the at least one model mirror from sensed data captured by the one or more sensors.
14 . A method for a safety system of a motor vehicle, the method comprising:
receiving, at a system comprising a processor and memory, data for a target vehicle from one or more sensors;
building, by the system, a computer model of the target vehicle using the received data, wherein the model includes at least one model mirror having a modeled position and a modeled orientation;
determining a blind spot zone for the target vehicle using geometric optics software or ray tracing software to identify, based on the modeled position and the modeled orientation of the at least one model mirror, points that are not visible in the at least one model mirror;
determining a position of the motor vehicle relative to the target vehicle and determining that the motor vehicle is in the blind spot zone of the target vehicle; and
modifying the operation of the motor vehicle to move the vehicle out of the blind spot of the target vehicle.
15 . The method according to claim 14 , wherein the vehicle system is a display and wherein controlling the vehicle system includes displaying an alert on the display.
16 . The method according to claim 14 , wherein the vehicle system is a display and wherein controlling the vehicle system includes indicating on the display a location of the target vehicle.
17 . The method according to claim 14 , wherein the method further comprises detecting a location and orientation of a head of a driver of the target vehicle, and wherein determining the blind spot zone is further based on the location and orientation of the head of the driver.
18 . The method according to claim 17 , wherein modifying the operation includes automatically changing a speed of the motor vehicle.
19 . The method according to claim 17 , wherein modifying the operation includes automatically engaging an autonomous driving system.
20 . The method according to claim 17 , wherein modifying the operation includes automatically controlling the motor vehicle to change lanes.