Abstract: Systems and methods for using image analysis techniques to facilitate adjustments to vehicle components are disclosed. According to aspects, a computing device may access and analyze image data depicting an individual(s) within a vehicle, and in particular determine a positioning of the individual(s) within the vehicle. Based on the positioning, the computing device may determine how to adjust a vehicle component(s) to its optimal configuration, and may facilitate adjustment of the vehicle component(s) accordingly.

Abstract: A method for controlling vehicle systems in a vehicle includes providing a steering wheel having a plurality of sensors configured to sense contact on the steering wheel. The steering wheel has a left zone and a right zone. The method includes determining a left contact value based on one or more signals received from at least one of the plurality of sensors. The left contact value indicates contact with the steering wheel within the left zone. The method includes determining a right contact value based on the one or more signals received from the at least one of the plurality of sensors. The right contact value indicates contact with the steering wheel within the right zone. The method includes determining a driver state index based on the left contact value and the right contact value and modifying control of the vehicle systems based on the driver state index.

Abstract: A vehicle includes a door sensor configured to detect opening and closing of a door; a radar provided in the vehicle and configured to acquire radar data regarding an object in the vehicle; a seatbelt sensor configured to detect a state of a seat belt provided on each seat of the vehicle; a seatbelt indicator configured to provide a notification regarding fastening of the seat belt; and a controller configured to control the radar in response to the opening and the closing of the door, perform a first check regarding the state of the seatbelt, check an occupancy and an occupied position of the object based on the radar data, identify a type of the object in the vehicle based on the radar data, and determine an operating state of the seatbelt indicator based on the type of the object and the occupied position of the object.

Abstract: An occupant protection system for a vehicle may include a seat-back actuator system, including a seat-back actuator configured to move a portion of a seat toward a back of an occupant of the vehicle during a collision in which the occupant is facing opposite a direction of travel of the vehicle. The seat-back actuator system may also include an actuator controller configured to receive a triggering signal indicative of one or more of an actual change in velocity of the vehicle, a predicted change in velocity of the vehicle, a collision, or a predicted collision, and cause the seat-back actuator to move the seat toward the back of the occupant. By moving the seat toward the back of the occupant, a maximum rate of change of velocity of the back of the person may be reduced, reducing the likelihood or severity of injury to the occupant due to the collision.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for monitoring a vehicle are disclosed. A vehicle monitoring system for monitoring a vehicle includes one or more processors and one or more computer storage media storing instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform operations. The operations include: receiving, from a vehicle occupancy monitor and by the vehicle monitoring system, vehicle occupancy data that indicates presence of a vehicle occupant; receiving, by the vehicle monitoring system and from a sensor, sensor data that indicates an attribute of the vehicle; analyzing, by the vehicle monitoring system, the vehicle occupancy data and the sensor data; and based on analyzing the vehicle occupancy data and the sensor data, performing a vehicle monitoring system action.

Abstract: Provided is a radar device and a rear seat detection method thereof, in which the method includes: (a) transmitting a radar signal in a form of a multi-channel high-speed FMCW to a periphery of the rear seat and receiving a signal reflected from a target by a transceiver; (b) detecting a motion of the passenger through a macro speed detection scheme by a signal processor; (c) detecting a change according to characteristics of the passenger through a micro speed detection scheme; and (d) determining, by a passenger detector, that the passenger is present on the rear seat when the motion or the change is detected in step (b) or step (c). Accordingly, a multi-channel high-speed FMCW radar waveform is employed to simultaneously detect the motion of the passenger detected through the macro speed detection scheme and a change caused by respiration of the passenger detected through the micro speed detection scheme, so that the passenger in the rear seat is accurately detected.

Abstract: Methods and devices for adjusting the position of a seat in a vehicle are described herein. The methods include obtaining pressure values output by a plurality of sub-sensors; calculating a mean square value and an average value of the pressure values output by the sub-sensors; judging whether a ratio of the mean square value to the average value is greater than a preset value; obtaining pressure values output by a front pressure sensor, a rear pressure sensor, a left pressure sensor and a right pressure sensor when the ratio of the mean square value to the average value is greater than the preset value; adjusting fore-and-aft positions of the seat according to the pressure values output by the front pressure sensor and the rear pressure sensor; and adjusting lateral positions of the seat according to the pressure values output by the left pressure sensor and the right pressure sensor.

Abstract: A driving assistance method includes: extracting a point where a travel lane of a host vehicle joins another lane on a planned travel route of the host vehicle, as a high difficulty point where autonomous driving is difficult; and guiding switching of a traveling state of the host vehicle from autonomous driving to manual driving, at a point located at a predetermined distance before the high difficulty point.

Abstract: According to an embodiment of the present disclosure, a safety equipment controlling apparatus of a vehicle may include an acceleration sensor, a collision detection sensor, a brake controller, a steering controller, an airbag, a seat belt actuator, and a control circuit electrically connected to the acceleration sensor, the collision detection sensor, the brake controller, the steering controller, the airbag, and the seat belt actuator. The control circuit may be configured to obtain a longitudinal acceleration and a lateral acceleration, which are generated by a brake of the brake controller and a steering of the steering controller, using the acceleration sensor and to calculate a predicted behavior of a user of the vehicle, based on the longitudinal acceleration and the lateral acceleration.

Abstract: An image capture device is mounted in a vehicle. The image capture device includes: an image capture unit; and a setting unit that sets an image capture condition for each region of the image capture unit each having a plurality of pixels, or for each pixel, based upon at least one of a state exterior to the vehicle and a state of the vehicle.

Abstract: According to various embodiments, there is provided a robot including: a spherical shell; a cart in the spherical shell, the cart including a plurality of wheels rotatable to move the cart along an inner surface of the spherical shell; a sensor coupled to the cart, the sensor configured to provide an inertial measurement of the cart; a motion encoder configured to measure an angular velocity of each wheel of the plurality of wheels; and a localizer configured to determine a location of the robot, based on the angular velocities of the plurality of wheels and the inertial measurement of the cart.

Abstract: The Intelligent Car Seat Camera Monitor is an alarm system. The Intelligent Car Seat Camera Monitor is constructed for use with a child car seat. Intelligent Car Seat Camera Monitor: a) detects when a child occupies the car seat; b) detects the driver side door opening; c) and deploys an audible alarm. The Intelligent Car Seat Camera Monitor comprises of a CPU, camera module, display, speaker, door sensor, and control buttons. The speaker activates a loud audible alarm when the camera has detected a child and the driver's door has been opened. The Intelligent Car Seat Camera Monitor utilizes real-time machine learning and model training to detect the child in the car seat, and it can be retrained to improve accuracy.

Abstract: A lanyard device (10) having a flexible neck cord (12) and at least one strain sensor (30) arranged for sensing strain in the flexible neck cord; and a personal lanyard monitoring system including the lanyard device (10). A position recognition unit (52) is configured for comparing strain data obtained from the at least one strain sensor (30) to predetermined strain data, and recognizing a position of the flexible neck cord (12) in dependence on a result of the comparison.

Abstract: A method and apparatus that perform threat zone assessment in a host vehicle are provided. The method includes detecting a target vehicle in a nonadjacent lane with respect to the host vehicle, determining dimensions of the detected target vehicle, a type of the detected target vehicle, and geometry of a road on which the detected target vehicle and the host vehicle are traveling, calculating the threat zone based on the dimensions of the detected target vehicle, the type of the detected target vehicle, or the geometry of the road on which the detected target vehicle and the host vehicle are traveling, and controlling the host vehicle to avoid the calculated threat zone by accelerating the host vehicle, decelerating the host vehicle, or aborting a lane change by the host vehicle.

Abstract: An apparatus comprising a transceiver, an antenna and a processor. The transceiver may be configured to send/receive data messages to/from a plurality of vehicles. The antenna may be configured to receive signals from GNSS satellites. The processor may be configured to (i) determine a first region based on relative coordinates calculated using the data messages, (ii) determine a second region calculated using the signals received from the GNSS satellites, (iii) determine whether a pre-determined amount of the first region to the second region overlap and (iv) increase a confidence level of a positional accuracy of the plurality of vehicles if the pre-determined amount of the first region and the second region overlap. One of the vehicles implements one or more automatic responses based on the confidence level of the positional accuracy.

Abstract: An electric brake device to be mounted on a vehicle includes a rotating body, a friction member, an electric motor, a piston, an operation conversion mechanism, an actuator, and a controller. The operation conversion mechanism is configured to include a rotating member and a linear motion member. The controller is configured to selectively execute a standby control of causing the linear motion member to stand by at a standby position where a clearance between the friction member and the rotating body is not larger than a backlash between a male screw and a female screw, and a backward movement control of moving the linear motion member backward to a backward movement position where the clearance is allowed to be equal to or more than the backlash, in a case where there is no braking force request for the electric brake device.

Abstract: A grass mower includes a frame that extends in a front/rear direction of a machine body, a mower deck supported to/under the frame, the mower deck extending in a transverse direction of the machine body, a side edge of the mower deck protruding laterally from the machine body, a tilt detector for detecting a rolling angle of the machine body, a display device for displaying the rolling angle, a first informing device for effecting a first informing for calling attention to grass scraping by the side edge when a rolling angle detected by the tilt detector exceeds a first tilt angle and a second informing device for effecting a second informing for calling attention to traveling danger when the rolling angle detected by the tilt detector exceeds a second tilt angle.

Abstract: An alignment system comprises a first diffractive optical element comprising an image and a laser source. The image is visible when the laser source is viewed from a desired field of view through the diffractive optical element. The laser source may be configured to produce a beam of light that will extend through at least a portion of the first diffractive optical element, thereby illuminating the image. The first diffractive optical element and the laser source may be disposed in a vehicle.

Abstract: A system for detecting seatbelt routing includes: a state module configured to, based on a series of images over a period of time from a camera of a vehicle facing a seat, determine and output a routing state of a seatbelt of the seat; and a remediation module configured to, based on the routing state of the seatbelt of the seat, selectively perform at least one remedial action.

Abstract: An instant traffic condition warning method comprises the following steps. A controller receives a vehicle distance value and a vehicle velocity value, and the controller determines whether the vehicle distance value is less than a distance threshold. When the vehicle distance value is less than the distance threshold, the controller determines whether the vehicle velocity value is larger than a velocity threshold. When the vehicle velocity value is larger than the velocity threshold, a warning element generates a warning signal.

Abstract: A method, computer system, and a computer program product for adjusting a plurality of environmental conditions of a vehicle based on a plurality of environmental conditions of an expected destination is provided. The present invention may include monitoring the plurality of environmental conditions of a vehicle by utilizing at least one vehicle device sensor. The present invention may then include retrieving the plurality of environmental conditions of an expected destination of the vehicle. The present invention may also include determining a delta between the monitored plurality of environmental conditions of the vehicle and the retrieved plurality of environmental conditions of the expected destination of the vehicle. The present invention may further include adjusting, over a gradual period of time, the monitored plurality of environmental conditions of the vehicle.

Abstract: The present invention relates to a device, system and method for CO2 monitoring. To enable continuous monitoring at low cost and in a simple manner, the device comprises a signal input (10) for obtaining one or more monitoring signals (20) of a monitored area, a breathing monitor (11) for determining one or more breathing parameters (21) of one or more subjects present in the monitored area from the obtained one or more monitoring signals, and a CO2 estimation unit (12) for estimating the CO2 level (22) in the monitored area based on the determined one or more breathing parameters.

Abstract: An apparatus includes a capture device and a processor. The capture device may be configured to generate a plurality of video frames corresponding to an area outside of a vehicle. The processor may be configured to perform operations to detect objects in the video frames, determine whether a potential collision is unavoidable based on the objects detected in the video frames and generate a signal if the potential collision is unavoidable. The signal may be configured to move a position of a seat in the vehicle. The position of the seat may be moved before an impact corresponding to the potential collision occurs.

Abstract: A driver condition estimation device includes an estimation unit configured to trigger an event that a webbing of a seat belt device is retracted, and to estimate a condition of a driver based on an amount of retraction of the webbing in the event.

Abstract: An indoor monitoring device includes: an image obtainment unit obtaining a captured image obtained by imaging an inside of a cabin of a vehicle by an imaging unit; and a position detection unit determining whether or not an occupant's head is present in the captured image, detecting a size of the head, a head position of the head, and a key point position of a key point other than the head of the occupant in the captured image in a case where the head is present in the captured image, and detecting a seating position of the occupant in the cabin based on the size of the head, the head position, and the key point position.

Abstract: Systems and methods are disclosed for determining whether or not a crash involving a vehicle has occurred. A computing device may receive acceleration measurement(s) measured by one or more accelerometers during a time window. The computing device may determine, for one or more acceleration measurements, a corresponding acceleration magnitude. Based on the corresponding acceleration magnitude(s), the computing device may identify, from the acceleration measurement(s), an acceleration measurement and/or may determine whether the acceleration magnitude exceeds a threshold acceleration magnitude. The computing device may corroborate whether a vehicle associated with the mobile computing device was involved in a crash. Data associated with the acceleration magnitude and/or an event, such as a crash event, may be transmitted to a server.

Abstract: A method for controlling an actuatable restraining device includes sensing a plurality of crash event indications in response to a crash event. The method also includes classifying the crash event in response to comparing the sensed crash event indications against one another to identify an oblique moving deformable barrier crash event. The method further includes controlling deployment timing of the actuatable restraining device in response to the classification of the crash event.

Abstract: A system for video processing includes a ranging system hardware interface, a vehicle bus interface, and a processor. The ranging system hardware interface is configured to receive ranging system data and/or ranging system metadata. The a vehicle bus interface is configured to receive vehicle bus data and vehicle bus metadata sent from a ranging system. The processor is configured to determine video data of interest based at least in part on the ranging system data and the ranging system metadata. The ranging system data and/or the ranging system metadata data includes information not included in the vehicle bus data and vehicle bus metadata sent from the ranging system via the vehicle bus interface.

Abstract: A vehicle having one or more cameras, configured to record one or more images of a driver of the vehicle. The camera(s) can be configured to send biometric image data derived from the image(s). The vehicle can include a computing system configured to receive the biometric data and to determine a risk score of the driver based on the received biometric data and an AI technique, such as an ANN or a decision tree. The received biometric data or a derivative thereof can be input for the AI technique. The computing system can also be configured to transmit the risk score of the driver to the customer so that the customer can decide whether to book the vehicle for a ride.

Abstract: A method for adapting a triggering algorithm of a personal restraint device of a vehicle is described. The method includes at least one step of reading in and a step of outputting. In the step of reading in, an object signal is read in that represents a recognition of a mobile object situated in the area of a person in the vehicle during a trip. In the step of outputting, a control signal is outputted that is designed to modify the triggering algorithm of the personal restraint device using the object signal.

Abstract: A video image output apparatus includes a video image data acquisition unit, a motion detection unit, a state determination unit and a video image control unit. The video image data acquisition unit acquires an occupant image obtained by picking up an occupant in a vehicle. The motion detection unit detects a movement of the occupant based on the acquired occupant image. The video image control unit generates a display image such that at least a part of the display image is displayed in a predetermined form when the state determination unit determines that a motion amount of the occupant is equal to or greater to than a reference value, and generates the display image such that the occupant image is displayed only for a predetermined time when the state determination unit determines that the motion amount of the occupant is less than the reference value.

Abstract: Systems and methods are disclosed for determining whether or not a crash involving a vehicle has occurred. The acceleration of the vehicle may be measured using, for example, an accelerometer of a mobile device, which may be located inside the vehicle. The system may determine the magnitude of each accelerometer measurement and whether the magnitude exceeds one or more acceleration magnitude thresholds. The system may also determine the number of accelerometer events within a time window and whether the number exceeds one or more count thresholds. The system may determine whether a crash involving the vehicle has occurred based on the magnitudes of acceleration, number of acceleration events, and various thresholds. In some examples, the system may confirm that a crash has occurred based on, for example, the location of the mobile device.

Abstract: A vehicle-initiated cadenced operator interaction system introduces an operational concept to a vehicle operator via a machine-initiated interaction. Thereafter, interaction is initiated by the industrial vehicle according to a cadence that provides a gap between interactions so that the operator can demonstrate the behavior associated with the introduced concept. The vehicle controller actively analyzes industrial vehicle data associated with the content of the interaction(s), and evaluates the data against pre-defined operational criteria to determine whether the operator is demonstrating the appropriate skill/behavior associated with the interaction(s). Responsive to the operator's demonstrated ability, the system can modify operation of the vehicle to tune the industrial vehicle to the operator. The system can also extend to the operating environment, by interacting with electronic devices, vehicles, machines, etc., in the operating environment to tune the environment to the operator.

Abstract: A method for controlling at least one occupant protection device for a vehicle in the case of a collision, including determining input data which represent an ignition time of an airbag of the vehicle, an angular frequency of the collision, an available displacement path of a vehicle occupant relative to the vehicle, a mass of the vehicle occupant of the vehicle, a distance of the vehicle occupant from the airbag, and an inflation time duration of the airbag; ascertaining a restraint force using the input data. The restraint force represents a force that can be provided by the at least one occupant protection device and that is suitable to minimize an occupant energy of the vehicle occupant up until the end of the collision; and providing a control signal for controlling the at least one occupant protection device, the control signal being produced using the restraint force.

Abstract: A computer-implemented process for controlling a vehicle interior includes detecting a previously defined situation that relates to an undesirable environmental condition of the vehicle interior, and assessing both a risk level and an urgency level, based on a vehicle sensor input. The process also includes generating a vehicle command based upon the detected previously defined situation, the assessed risk level, and assessed urgency level, and executing the generated vehicle command to control at least one of an engine, a window, and a heating, ventilation and air conditioning (HVAC) unit to modify an environmental condition of the vehicle interior.

Abstract: The invention relates to a method for authenticating a vehicle user. In the method, movement data of a sensor identification circuit are detected by sensors. The detected movement data are supplied to a self-learning system. The self-learning system ascertains a movement profile based on the supplied movement data and assigns this to a vehicle user. Upon approach of the vehicle by a vehicle user, it is checked whether movement data detected at the point in time of the approach corresponds to a movement profile, which is assigned to a vehicle user authorized to use the vehicle. In the event of a match, the vehicle user approaching the vehicle is authorized to use the vehicle.

Abstract: The invention relates to a driver-assistance device for assisting with driving a motor vehicle (1) following a road (2), this device comprising: a sensor suitable for acquiring a signal representative of the presence of an obstacle in the interior of a detection field (110) of this sensor, and a control module that is programmed to control a driver-assistance function for assisting with driving the motor vehicle, depending on the signal acquired by said sensor, and: a) to detect, on the basis of a position of the motor vehicle and of characteristics of said road, a section (20) of this road located outside of the detection field of said sensor, and b) in case of detection of this road section, to control said driver-assistance function while taking into account the potential presence of an obstacle on said road section. An associated driver-assistance method is also described.

Abstract: A system for localizing an object of interest in a monitored space includes a plurality of capacitive sensors for sensing changes in the status of a space, adapted to electrically interact in a contactless way with a ground surface so as to provide a capacitance varying on the basis of such changes, and adapted to detect at least a time evolution of the capacitance and to produce a capacitance-depending signal, a filtering unit configured for reducing the noise level in the time evolution of such capacitance by filtering the capacitance-depending signal provided by the capacitive sensors, so that corresponding filtered signals are produced, and a central device in signal communication with the capacitive sensors.

Abstract: A system and method for using human driving patterns to detect and correct abnormal driving behaviors of autonomous vehicles are disclosed. A particular embodiment includes: generating data corresponding to a normal driving behavior safe zone; receiving a proposed vehicle control command; comparing the proposed vehicle control command with the normal driving behavior safe zone; and issuing a warning alert if the proposed vehicle control command is outside of the normal driving behavior safe zone. Another embodiment includes modifying the proposed vehicle control command to produce a modified and validated vehicle control command if the proposed vehicle control command is outside of the normal driving behavior safe zone.

Abstract: Apparatus, systems, and methods generally including detecting, using a sensor, an impact at a vehicle; before, during, or after detecting the impact, storing a first data set associated with the vehicle in a first memory; in response to detecting the impact, retrieving the first data set from the first memory; transmitting, using a first short range communication device, the first data set via a first wireless signal; receiving, using a second short range communication device, the first data set via the first wireless signal; and storing the first data set in a second memory; and after storing the first data set in the second memory, retrieving the first data set from the second memory; wherein the first short range communication device is part of the vehicle; and wherein the second short range communication device is part of an infrastructure.

Abstract: Devices for simulating a transportation emergency are disclosed. The devices have a base with a framework of interconnected supports extending therefrom as a skeletal portion of a simulated transportation device and defining a chamber configured to receive a human or a medical-training manikin. Within the chamber a seat for receiving the human or the medical-training manikin is disposed. The framework defines one or more openings representative of access openings into the simulated transportation device such that a first responder in-training can receive instructions on how to assist a victim positioned in the simulated transportation device. The framework also defines one or more open frames representative of structural features of the simulated transportation device that block access to the victim such that realistic training occurs. The device may include one or more props such as a telescoping steering column, a prying simulator, a foot pedal unit, and a side impact bar.

Abstract: A driving assistance device includes a driving state detection portion that detects a driving state of a vehicle by a driver; an environment detection portion that detects an environment in which the vehicle travels; an emotion detection portion that detects the driver's emotion or change in emotion; a characteristic estimation portion that estimates the drivers characteristic with respect to the vehicle on the basis of the driving state of the driver in the environment detected by the environment detection portion, and the driver's emotion or change in emotion during the driving; and a change portion that changes setting of various control in the vehicle on the basis of the driver's characteristic estimated by the characteristic estimation portion.

Abstract: An occupant detection device includes: a face area detecting unit for executing a process of detecting a plurality of face areas corresponding to a plurality of faces in an image captured by a camera for capturing an image of a vehicle interior; a first determination unit for determining whether or not, among a plurality of seat areas corresponding to a plurality of seats in the captured image, there is a seat area including two or more face areas; a second determination unit for determining whether or not a duration time of a state where there is a seat area including two or more face areas has exceeded a reference time; and a warning output control unit for executing control for outputting a warning when the duration time exceeds the reference time.

Abstract: The present disclosure extends to methods, systems, and computer program products for controlling climate in vehicle cabins. A person may provide climate related data to a vehicle climate control system prior to pick up and/or during a ride in the vehicle. The climate control system may adjust the climate in at least part of a vehicle cabin based at least in part on the climate related data and configuration of components in the climate control system. Climate control adjustments can be used to precondition part of a vehicle cabin for a person and/or in response to indicated thermal discomfort of the person. The climate control system can refer to an occupant comfort model and compute climate adjustments in accordance with the occupant comfort model.

Abstract: A method and device for generating a highly precise map, including a step of receiving surrounding-area data values, which represent a surrounding area of a vehicle, the surrounding area encompassing at least one static surrounding-area feature and at least one mobile surrounding-area feature; including a step of receiving movement data values, which represent a movement of the at least one mobile surrounding-area feature in the surrounding area of the vehicle; including a step of generating a highly precise map on the basis of the surrounding-area data values, using the at least one static surrounding-area feature, and excluding the at least one mobile surrounding-area feature, the exclusion occurring as a function of the movement; and including a step of providing the highly precise map.

Abstract: A knee airbag apparatus for an autonomous vehicle, wherein a first cushion and a second cushion are deployed toward the knees of a passenger and a third cushion is deployed toward the feet and shins of the passenger according to a collision mode (head-on collision, offset collision or oblique collision) and a position (normal position or relaxation position) of a seat.

Abstract: An impact motion tracking system for tracking an object in a three-dimensional space includes a motion tracking sensor that includes a housing, a magnetic measurement module, an inertial measurement module, and a transmitter module, which generates magnetic fields. The magnetic measurement module measures magnetic fields generated by the transmitter module and has a fixed orientation with the object. The inertial measurement module measures a linear acceleration or an angular acceleration and has a fixed positional relationship with the object. An electronic processor receives measured signals from the motion tracking sensor and derives an impact motion information for the object based on received measured signals from the inertial measurement module. The electronic processor derives a magnetic motion information for the object based on received measured signals from the magnetic measurement module and periodically calibrates impact motion information with magnetic motion information.

Abstract: A method of on-line diagnostic and prognostic assessment of an autonomous vehicle perception system includes detecting, via a sensor, a physical parameter of an object external to the vehicle. The method also includes communicating data representing the physical parameter via the sensor to an electronic controller. The method additionally includes comparing the data from the sensor to data representing the physical parameter generated by a geo-source model. The method also includes comparing results generated by a perception software during analysis of the data from the sensor to labels representing the physical parameter from the geo-source model. Furthermore, the method includes generating a prognostic assessment of a ground truth for the physical parameter of the object using the comparisons of the sensor data to the geo-source model data and of the software results to the geo-source model labels. A system for on-line assessment of the vehicle perception system is also disclosed.

Abstract: A seatbelt retractor device includes a pre-tensioner section, and a force limiter section that can change a magnitude of a load at which to start reducing tension of the retracted seatbelt. A seatbelt control ECU activates the pre-tensioner section when a deceleration G detected by a floor sensor exceeds a first threshold, and acquires a collision velocity from a radar device and sets a second threshold value to a lower value the greater the collision velocity. The seatbelt control ECU controls the starting load for tension reduction by the force limiter section to be a high load when the deceleration G has exceeded the second threshold within a determination time period after activation of the pre-tensioner section, and controls the starting load for tension reduction to be a low load when which the deceleration G has not exceeded the second threshold within the determination time period.

Abstract: A radar data processing device includes at least one analog-to-digital converter (ADC) configured to digitize a plurality of input signals, wherein each input signal includes radar chirp and radar chirp reflection information received at one of a plurality of receiver antennas. The radar data processing device also includes Fast Fourier Transform (FFT) logic configured to generate FFT output samples based on each digitized input signal, wherein at least some of the generated FFT output samples are across antenna FFT output samples associated with at least two of the plurality of receiver antennas. The radar data processing device also includes a processor configured to determine a plurality of object parameters based on at least some of the generated FFT output samples, wherein the processor uses a neural network classifier trained to provide a confidence metric for at least one of the plurality of object parameters.