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 control system includes first and second traveling control units for performing traveling control of controlling driving, braking, and/or steering of a vehicle without depending on a driving operation of a driver. In a case in which control instructions concerning the same actuator conflict between the first traveling control unit and the second traveling control unit, the first traveling control unit arbitrate the control instructions.

In various embodiments, a driver sensing subsystem computes a characterization of a driver based on physiological attribute(s) of the driver that are measured as the driver operates a vehicle. Subsequently, a driver assessment application uses a confidence level model to estimate a confidence level of the driver based on the characterization of the driver. The driver assessment application then causes driver assistance application(s) to modify at least one functionality of the vehicle based on the confidence level. Advantageously, by enabling the driver assistance application(s) to take into account the confidence level of the driver, the driver assessment application can improve driving safety relative to conventional techniques for implementing driver assistance applications that disregard the confidence levels of drivers.

A vehicle learning system includes a first execution device mounted on a vehicle, a second execution device outside the vehicle, and a storage device. The storage device stores mapping data including data, which is learned by machine learning and defines mapping that receives input data based on a detection value of an in-vehicle sensor and outputs an output value. The first execution device and the second execution device execute, in cooperation with each other, an acquisition process of acquiring input data, a calculation process of calculating an output value with the input data as an input of the mapping, and a relationship evaluation process of evaluating a relationship between a predetermined variable different from a variable corresponding to the output value and accuracy of the output value. The first execution device executes at least the acquisition process, and the second execution device executes at least the relationship evaluation process.

A vehicle hitch detection system is provided. The vehicle hitch detection system includes a camera arranged to capture images of a vehicle hitch and a controller processing the images to detect a powered hitch ornament connected to the hitch based on the processed images when an electrical hitch connection is detected. The controller may further control a driver assistance system based on the detected hitch ornament to enable or disable the system.

A vehicle control system includes: an automated driving controller configured to execute one driving mode from out of a plurality of driving modes including an automated driving mode and a manual driving mode; a vehicle information collection section configured to collect information related to control history of one or both out of speed control and steering control performed based on operation by the occupant of the vehicle while the manual driving mode is being executed; and a driving characteristics derivation section configured to derive driving characteristics for each occupant of the vehicle based on information collected by the vehicle information collection section. The automated driving controller executes the automated driving mode by reflecting the driving characteristics for each occupant of the vehicle to the automated driving.

A method during which a current position of a pilot control is determined, an equivalent position is determined that the pilot control needs to reach following a control transition in order to avoid modifying the actuator, and at least one mismatch is determined between the equivalent position and the current position. As from a transition, a target is determined for controlling the actuator by giving a corrected value to at least one position variable in a post-transition piloting relationship, the corrected value being determined as a function of the mismatch and of the current position of the pilot control. So long as the mismatch is not zero, the value of the mismatch in the relationship is reduced in proportion to the movement of the pilot control as the pilot control comes closer to the equivalent position.

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.

The present invention obtains a rider-assistance system capable of appropriately assisting with driving by a rider of a straddle-type vehicle and a control method for such a rider-assistance system.

The rider-assistance system that assists with driving by the rider of the straddle-type vehicle includes: a peripheral environment detector that is mounted to the straddle-type vehicle and detects peripheral environment of the straddle-type vehicle; an input device that is mounted to the straddle-type vehicle and is operated by the rider of the straddle-type vehicle; and a controller that governs operation of the rider-assistance system. The controller includes: an acquisition section that acquires pitch angle correction target information that is target information on pitch angle correction of the peripheral environment detector; and a correction operation performing section that performs correction operation for detection of the peripheral environment by the peripheral environment detector on the basis of the pitch angle correction target information acquired by the acquisition section.

Included are: a learning history data acquiring unit for acquiring, as learning history data, driving history data obtained when a learning mobile object is operated in a risk-free environment; an imitation learning unit for performing learning for imitating driving of the learning mobile object in the risk-free environment using the learning history data as training data and generating an imitation learning model; a training history data acquiring unit for acquiring, as training history data, driving history data obtained when a mobile object for generating training data is operated in the same environment as the environment in which the learning history data has been acquired; a training data generating unit for estimating whether the training history data matches the learning history data using the training history data as input to the imitation learning model and assigning a label related to risks; and a cognitive learning unit for learning a model for inferring a result for controlling a mobile object to be controlled using at least the label related to risks as training data, on the basis of sensor information of the mobile object to be controlled.