A vehicle control system uses reliability of an input signal of an autonomous vehicle to safely travel through an intersection or a crossroad. The system includes a first calculating unit that calculates reliability for behavior information of a front vehicle and a second calculating unit calculates reliability for state information of a traffic light in the crossroad or the intersection based on a surrounding vehicle. A third calculating unit calculates reliability for brake light information of the front vehicle and a fourth calculating unit calculates reliability for flow information of the surrounding vehicle passing the crossroad or the intersection. A determining unit generates a vehicle control signal according to the calculated reliability.

A transmission includes an input shaft coupled to a prime mover, a countershaft, main shaft, and an output shaft, with gears between the countershaft and the main shaft. A shift actuator selectively couples the input shaft to the main shaft by rotatably coupling gears between the countershaft and the main shaft. The shift actuator is mounted on an exterior wall of a housing including the countershaft and the main shaft. An integrated actuator housing includes a single external power access for the shift actuator. A controller interprets a shaft displacement angle, determines if the transmission is in an imminent zero or zero torque region, and performs a transmission operation in response to the transmission in the imminent zero or zero torque region.

A sensor aiming device includes: a target positional relationship processing unit for outputting positional relationship information of first and second targets; a sensor observation information processing unit configured to convert the observation result of the first and second targets into a predetermined unified coordinate system according to a coordinate conversion parameter, perform time synchronization at a predetermined timing, and extract first target information indicating a position of the first target and second target information indicating a position of the second target; a position estimation unit configured to estimate a position of the second target using the first target information, the second target information, and the positional relationship information; and a sensor correction amount estimation unit configured to calculate a deviation amount of the second sensor using the second target information and an estimated position of the second target and estimate a correction amount.

Described are techniques and systems for secure camera based IMU calibration for stationary systems, including vehicles. Existing vehicle camera systems are employed, with enhanced security to prevent malicious attempts by hackers to try and cause a vehicle to enter IMU calibration mode. IMU calibration occurs when a calibration system determines the vehicle is parked in a controlled environment; calibration targets are positioned at different viewing angles to vehicle cameras to act as sources of optical patterns of encoded data. Features of the patterns are for security as well as for alignment functionality. Images of the calibration targets enable inference of a vehicle coordinate system, from which calculations for IMU mounting error compensations are performed. A relative rotation between the IMU and the vehicle coordinate system are applied to IMU data to compensate for relative rotations between the vehicle and the IMU, thereby improving vehicle slope and bank metrics.

This disclosure describes systems and methods for training a neural network with a training data set including data items labeled at different granularities. During training, each item within the training data set can be fed through the neural network. For items with labels of a higher granularity, weights of the network can be adjusted based on a comparison between the output of the network and the label of the item. For items with labels of a lower granularity, an output of the network can be fed through a conversion function that convers the output from the higher granularity to the lower granularity. The weights of the network can then be adjusted based on a comparison between the converted output and the label of the item.

Devices, systems, and methods for a vehicular safety system in autonomous vehicles are described. An example method for safely controlling a vehicle includes selecting, based on a first control command from a first vehicle control unit, an operating mode of the vehicle, and transmitting, based on the selecting, the operating mode to an autonomous driving system, wherein the first control command is generated based on input from a first plurality of sensors, and wherein the operating mode corresponds to one of (a) a default operating mode, (b) a minimal risk condition mode of a first type that configures the vehicle to pull over to a nearest pre-designated safety location, (c) a minimal risk condition mode of a second type that configures the vehicle to immediately stop in a current lane, or (d) a minimal risk condition mode of a third type that configures the vehicle to come to a gentle stop.

Provided is a vehicle control device configured to: recognize a surrounding situation of a vehicle; control steering and acceleration/deceleration of the vehicle; detect operation states of a plurality of external recognition sensors; determine a driving mode of the vehicle as any one of a plurality of driving modes including a first driving mode, a second driving mode, and a third driving mode; change the third driving mode to either one of the first driving mode and the second driving mode when determining that a failure has occurred in one of the plurality of external recognition sensors that implement: a function of causing the vehicle to follow a preceding vehicle; and a function of assisting the vehicle in keeping a lane; and change the third driving mode to the second driving mode when determining that degradation in performance has occurred in one of the plurality of external recognition sensors.

A vehicle control device includes: an acquiring unit that acquires vehicle height information from a link mechanism type vehicle height sensor that is connected to a lower arm of a suspension that connects a vehicle body and wheels of a vehicle; a storage unit that stores vehicle height error information, which is information representing a relationship between an acting force that is applied to the vehicle in a horizontal direction and an error that is contained in the vehicle height information that is output by the vehicle height sensor; and a correcting unit that corrects the vehicle height information that has been acquired by the acquiring unit, based on the acting force that acts when the vehicle height information is acquired and the vehicle height error information that is stored in the storage unit.

This drive assistance device comprises an ACC unit, an abnormality detection unit for detecting an abnormality from a detector used to perform ACC, and a vehicle stop control unit for performing control to stop an ego vehicle when an abnormality is detected by the abnormality detection unit and an inter-vehicle distance to a preceding vehicle satisfies a certain condition.

A vehicle includes receiving signals from a plurality of satellites; obtaining position information based on the received signal; detecting a driving speed and yaw rate; obtaining dead reckoning information based on position information about a position of a vehicle recognized in a previous cycle and the received detection information; predicting the position information based on the obtained dead reckoning information; obtaining a value of Euclidean distance based on the position information about the position of the vehicle recognized in the previous cycle and the obtained position information; generating a first outlier filter based on the value of the Euclidean distance; obtaining a value of Mahalanobis distance based on the obtained position information and the predicted position information; generating a second outlier filter based on the value of the Mahalanobis distance; recognizing a current position of the vehicle by fusing information passing through the first outlier filter and information passing through the second outlier filter; and outputting information about the current position of the recognized vehicle as an image or a sound.