Disclosed are safety improvements for vehicles, including methods and systems of child seat detection in collaboration with a seat occupancy classification system. Corresponding systems, vehicles, and computer programs are also presented. In an aspect, a method includes receiving a current image showing a region of a vehicle seat currently captured inside the vehicle and retrieving one or more reference images, wherein at least one reference image is a previously stored first reference image of the vehicle seat being unoccupied. The method further includes determining a seat state of the vehicle seat by processing the current image and one or more reference images with a pre-trained machine learning classification network and determining, based on an output from the network, the seat state indicating at least whether the vehicle seat in the current image includes a mounted child seat. Finally, the method forwards the seat state to the seat occupancy classification system.

An occupant support adapted for use in a vehicle includes a seat bottom coupled to a floor of the vehicle and a seat back configured to pivot about a seat-back pivot axis relative to the seat bottom. The occupant support further includes a seatback-motion controller configured to control movement of the seat back relative to the seat bottom between a blocked arrangement and a freed arrangement.

A system capable of determining a type of a passenger sitting on a seat according to a body type is disclosed. The system includes a seat detecting means detecting a position of a seat and an angle of a seat back, a passenger detecting means detecting a passenger based on a state where a specific passenger normally sits on the seat, and a controller detecting a passenger's body part along with a seat-back area where the seat back is positioned and a passenger area where the passenger is positioned using information detected by the seat detecting means and the passenger detecting means, and learning a parameter value that is input as a relationship of detected information and a classification result for a body type of the passenger that is output by the parameter value, thus setting a body-type classification model.

[TASK]

In a reclining seat device, the behavior of the vehicle is accurately conveyed to a seated occupant without regard to the reclining angle of the seat back with respect to the seat cushion.

[SOLUTION]

The air cells 30 of the seat cushion 22 are vibrated with a higher intensity than those of the seat back 26 when the reclining angle is smaller than a predetermined value, and the air cells 30 of the seat back 26 are vibrated with a higher intensity than those of the seat cushion 22 when the reclining angle is equal to or greater than the predetermined value.

A system capable of determining a type of a passenger sitting on a seat according to a body type is disclosed. The system includes a seat detecting means detecting a position of a seat and an angle of a seat back, a passenger detecting means detecting a passenger based on a state where a specific passenger normally sits on the seat, and a controller detecting a passenger's body part along with a seat-back area where the seat back is positioned and a passenger area where the passenger is positioned using information detected by the seat detecting means and the passenger detecting means, and learning a parameter value that is input as a relationship of detected information and a classification result for a body type of the passenger that is output by the parameter value, thus setting a body-type classification model.

The invention relates to a method for triggering protective means, in particular an airbag and/or a belt tensioner, in a child restraint device, in particular according to one of claims 18 to 20, comprising the steps of: a) determining at least one measurement direction and/or a measurement direction corridor; b) receiving acceleration sensor signals from at least two acceleration sensors (74x, 74y, 74z), which are preferably orientated differently; c) calculating at least one first acceleration value (aX) along the measurement direction and/or within the measurement direction corridor; d) determining a triggering signal based at least on the at least one first acceleration value (aX); e) triggering at least one protective means based on the triggering signal.

A seat control device includes: a vehicle inclination sensor which obtains inclination information indicative of an inclination angle of a vehicle on which a seat is mounted with respect to a traveling surface; a rocking mechanism which rocks the seat; and a controller which controls the rocking mechanism, the controller executing a rocking adjustment process of adjusting rocking of the seat by driving the rocking mechanism on the basis of the obtained inclination information of the vehicle.

In at least one embodiment, a seat assembly is provided. The seatback receives an occupant in a vehicle. A headrest is coupled to the seatback. The headrest includes a motor, at least one sensor, and at least one controller. The motor rotates the headrest to orient an occupant's head relative to one or more loudspeakers positioned in the vehicle. The at least one sensor is configured to detect a location of the headrest. The at least one controller is programmed to control the motor to move the headrest to a predetermined location relative to the one or more loudspeakers positioned in the vehicle to optimize a listening experience for the occupant in the vehicle.

A cockpit system for use in a vehicle is provided. The cockpit system includes a camera, a flexible touch screen, a steering wheel, and a controller. The camera provides a driving image. The flexible touch screen has a flexible mechanism to control a flexible state of the flexible touch screen. The steering wheel has a foldable mechanism to control a folding state and turning of the steering wheel, and the flexible touch screen is arranged on the steering wheel. The controller is coupled to the camera, the flexible touch screen, and the steering wheel, and the controller determines an operational requirement of a driver based on the driving image and controls the flexible mechanism and the foldable mechanism according to the operational requirement.

Disclosed are safety improvements for vehicles, including methods and systems of child seat detection in collaboration with a seat occupancy classification system. Corresponding systems, vehicles, and computer programs are also presented. In an aspect, a method includes receiving a current image showing a region of a vehicle seat currently captured inside the vehicle and retrieving one or more reference images, wherein at least one reference image is a previously stored first reference image of the vehicle seat being unoccupied. The method further includes determining a seat state of the vehicle seat by processing the current image and one or more reference images with a pre-trained machine learning classification network and determining, based on an output from the network, the seat state indicating at least whether the vehicle seat in the current image includes a mounted child seat. Finally, the method forwards the seat state to the seat occupancy classification system.