In various examples, systems and methods are disclosed that accurately identify driver and passenger in-cabin activities that may indicate a biomechanical distraction that prevents a driver from being fully engaged in driving a vehicle. In particular, image data representative of an image of an occupant of a vehicle may be applied to one or more deep neural networks (DNNs). Using the DNNs, data indicative of key point locations corresponding to the occupant may be computed, a shape and/or a volume corresponding to the occupant may be reconstructed, a position and size of the occupant may be estimated, hand gesture activities may be classified, and/or body postures or poses may be classified. These determinations may be used to determine operations or settings for the vehicle to increase not only the safety of the occupants, but also of surrounding motorists, bicyclists, and pedestrians.

A vehicle may receive sensor data captured by a sensor, determine that the sensor data represents an object in the environment, and determine a collision probability associated with a predicted collision between the vehicle and the object. Based at least in part on the collision probability, a position of a headrest of the vehicle may be determined relative to a head of an occupant of the vehicle. The headrest may be adjusted in one or more directions prior to occurrence of the predicted collision to minimize injury to the occupant due to the collision.

A device for restraining a passenger in a relaxed position for a vehicle seat and a method for controlling the device are configured such that when a seated passenger in an autonomous vehicle enters a relaxed mode, and thus is seated in a relaxed posture in the vehicle seat, and when a vehicle speed is greater than or equal to a predetermined speed, the device automatically operates such that legs of the seated passenger can be restrained, thereby effectively protecting the passenger in the relaxed position if an accident occurs. The device includes a rod member coupled to a seat cushion and configured to have a variable length; and a support foam connected to one end of the rod member and positioned in front of the seated passenger to restrain the legs of the seated passenger.

Disclosed herein is an apparatus for predicting movement of a user of a vehicle. The apparatus may include an acceleration sensor that senses an acceleration of the vehicle, a braking controller that automatically controls a deceleration of the vehicle, a steering controller that automatically controls a direction of the vehicle, and a control circuit electrically connected to the acceleration sensor, the braking controller, and the steering controller, where the control circuit may monitor an operation of the braking controller, and predict a movement of the user of the vehicle based on a longitudinal acceleration of the vehicle sensed by the acceleration sensor and a first predetermined parameter when braking by the braking controller is detected.

A system may present notifications to an occupant of a vehicle and determine whether the occupant has given attention to the notification. The system oscillates a visual notification at an output frequency. The system captures images of an eye of the occupant to determine an eye pupil oscillation frequency associated with the occupant. The system compares the eye pupil oscillation frequency to the output frequency. The system determines whether attention was given to the notification based on whether the output frequency and the eye pupil oscillation frequency match. If the system determines that attention was not given, the system may cause performance of one or more follow-up operations.

An airbag deployment control apparatus for a vehicle, comprising: a first sensing unit configured to sense yaw rate information including yaw rate and acceleration values of a vehicle; a second sensing unit configured to sense whether a passenger in the vehicle wears a seat belt; a collision sensing unit configured to sense whether the vehicle collides; a communication unit configured to receive seat position information and ADAS operation information of the vehicle; and a control unit configured to calculate dynamic behavior information of the passenger and decide an airbag deployment point based on the dynamic behavior information of the passenger and the collision sensing result of the collision sensing unit.

A device for protecting a person standing in a motor vehicle comprises numerous airbags installed in a motor vehicle, a scanner for determining where there is empty space adjacent to the person, and a control unit that is configured to only deploy those airbags that inflate into the empty space that has been determined.

Disclosed is a system for controlling a vehicle safety device, the system including: a vehicle safety device configured to protect an occupant; a first occupant detection unit configured to detect a position of the occupant's movable body part; a second occupant detection unit configured to detect a position of the occupant's body part fixed to the safety device; a calculation unit configured to calculate information on the occupant's behavior in the event of a collision accident of a vehicle based on the position of the occupant's movable body part detected by the first occupant detection unit and the position of the occupant's body part fixed to the safety device detected by the second occupant detection unit; and a control unit configured to control an operation of the vehicle safety device for protecting the occupant based on the information on the occupant's behavior calculated by the calculation unit.

An airbag deployment control apparatus for a vehicle, comprising: a first sensing unit configured to sense yaw rate information including yaw rate and acceleration values of a vehicle; a second sensing unit configured to sense whether a passenger in the vehicle wears a seat belt; a collision sensing unit configured to sense whether the vehicle collides; a communication unit configured to receive seat position information and ADAS operation information of the vehicle; and a control unit configured to calculate dynamic behavior information of the passenger and decide an airbag deployment point based on the dynamic behavior information of the passenger and the collision sensing result of the collision sensing unit.

A system for determining when an occupant in a motor vehicle seat and restrained by a seatbelt restraint system has improper posture. The system and method include: a seatbelt buckle sensor, a seatbelt payout sensor, an occupant posture sensor. Moreover, a control module executes code to: determine the presence of the seatbelt latchplate in the seatbelt buckle, determine whether the difference between the first seatbelt payout length when the seatbelt is buckled and the second seatbelt payout length is greater than a seatbelt payout length threshold, compare the image of the occupant to at least one of a stored image and a posture zone when the seatbelt payout length threshold is exceeded, and determine whether the occupant has improper posture based on the comparison of the captured image of the occupant and the at least one of the stored image and the posture zone.