Abstract: Methods and systems for vehicle fault detection include collecting operational data from sensors in a vehicle. The sensors are associated with vehicle sub-systems. The operational data is processed with a neural network to generate a fault score, which represents a similarity to fault state training scenarios, and an anomaly score, which represents a dissimilarity to normal state training scenarios. The fault score is determined to be above a fault score threshold and the anomaly score is determined to be above an anomaly score threshold to detect a fault. A corrective action is performed responsive the fault, based on a sub-system associated with the fault.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a road condition reporter are disclosed. In one aspect, a method includes the actions of receiving, from a computing device, data that reflects characteristics of a vehicle. The actions further include, based on the data that reflects the characteristics of the vehicle, determining a characteristic of a road traveled by the vehicle. The actions further include, based on the characteristic of the road traveled by the vehicle, generating an instruction to perform an action. The actions further include providing, for output, the instruction to perform the action.

Abstract: A system includes a work vehicle, user interface, and controller. The work vehicle includes a frame, boom, implement, perception sensor, and ground speed sensor. The perception sensor senses an approaching environment. The user interface includes controls and indicators. The controller is coupled to the controls, indicators, perception sensor, and ground speed sensor. The controller receives a command to move the work vehicle, drives the work vehicle, determines a distance to the container, determines the ground speed, determines a boom raising start distance from the container, receives a command to raise the boom, and activates one of the indicators if the user command to raise the boom occurs prior to the work vehicle reaching the boom raising start distance from the container.

Abstract: Various disclosed embodiments include illustrative drive unit controllers, drive units, and vehicles. In an illustrative embodiment, a drive unit controller includes a processor having computer-readable media configured to store computer-executable instructions configured to cause the processor to receive free-wheel tow mode activation information, activate a hold mode based on the received free-wheel tow mode activation information, generate a zero-speed command in response to the hold mode being activated, and send the generated zero-speed command to a stabilizing system of the associated vehicle.

Abstract: A processing apparatus is a processing apparatus for a vehicle provided with a control processing unit that executes control processing for controlling an operation of an electronic device by executing a first program, and includes: an update determination unit that determines whether or not to update the first program; and a stop determination unit that determines whether or not running of the vehicle is stopped if the update determination unit makes a determination to update the first program, and, if the stop determination unit determines that running of the vehicle is stopped, the control processing unit executes the control processing by executing a second program, and a data amount of the second program is smaller than a data amount of the first program.

Abstract: An automated driving method for a vehicle includes: determining whether or not a traffic jam is detected ahead of a host vehicle by a distance equal to or more than a predetermined distance on a travel route of the host vehicle during travel by automated driving that brings a vehicle speed close to a target vehicle speed; and in a traffic jam detection time when the traffic jam is detected, reducing the vehicle speed VSP to be lower than a target vehicle speed VSPt0 for the automated driving in a normal time other than the traffic jam detection time.

Abstract: Method and device for processing LIDAR sensor data are disclosed. The method includes: receiving a first dataset and a second dataset having pluralities of data points; matching at least some of the plurality of first points with at least some of the plurality of second points, thereby determining a plurality of pairs; for the given one of the plurality of pairs, determining a pair-specific filtering parameter by calculating neighbour beam distances between the given first data point and respective ones the set of neighboring points, a given neighbour beam distance being representative of a linear distance between the given first data point and a respective one of the set of neighbouring points; in response to the pair-specific parameter being positive, excluding the given one of the plurality of pairs from further processing; and processing the reduced plurality of pairs for merging the first dataset and the second dataset.

Abstract: Systems and methods for controlling a vehicle may include receiving sensor data from a plurality of sensors, the sensor data including vehicle parameter information for the vehicle; using the sensor data to determine a vehicle state for a vehicle negotiating a corner, wherein the vehicle state comprises information regarding a magnitude of an effective understeer gradient for the vehicle; computing a yaw moment required to correct the effective understeer gradient based on the magnitude of the effective understeer gradient; and applying a brake torque to a single wheel of the vehicle, wherein an amount of brake torque applied is sufficient to lock up the single wheel to create a yaw moment on the vehicle to achieve the computed yaw moment required to correct the effective understeer gradient.

Abstract: A controller may obtain, from one or more first devices of a first machine, first information regarding a load associated with a first portion of an object. The first portion, of the object, may be carried by an implement of the first machine and a second portion, of the object, may be carried by an implement of a second machine. The controller may obtain, from one or more second devices of the first machine, second information regarding an orientation of the first machine. The controller may determine, based on the first information and a threshold derived based on the second information, that a load drop condition is satisfied; perform a first action associated with dropping the load; and transmit, to the second machine, information regarding the first action to cause the second machine to perform a second action.

Abstract: A work machine includes a work machine actuator, a position sensor configured to sense a geographic position of the work machine on a worksite and a control system configured to receive an indication of a thematic map of the worksite that maps variable values to different geographic locations on the worksite, generate a set of clusters based on the variable values and a geospatial control zone constraint, identify, based on the set of clusters, a plurality of control zones that are correlated to the worksite and have associated setting values, and generate control signals to control the work machine actuator based on the geographic position of the work machine relative to the plurality of control zones and the setting values associated with the control zones.

Abstract: A vehicle control apparatus to be applied to a vehicle includes a first traveling motor, a second traveling motor, and a control system. The control system estimates a first friction coefficient between a first wheel and a road surface and a second friction coefficient between a second wheel and a road surface. When the vehicle starts in a situation in which any of the first and second friction coefficients is less than a first threshold and a difference between the first and second friction coefficients is greater than a second threshold, the control system increases a power running torque of the first traveling motor after elapse of a first delay time after increasing a power running torque of the second traveling motor, if the first friction coefficient is smaller than the second friction coefficient. The first delay time is set on the basis of the first friction coefficient.

Abstract: A system includes a processor and a memory. The memory stores instructions executable by the processor to determine an action for a vehicle based on an identified risk condition, to determine a minimum time for performing the action, and based on data including a vehicle battery state of charge, an outdoor temperature, and a vehicle mode of operation, to determine an available electrical power for performing the action. The instructions further include instructions to determine maximum permissible electrical energy discharge rate based on the minimum time for performing the action and the determined available electrical power, to determine a load control plan for a plurality of electrical devices in the vehicle based on the maximum permissible electrical energy discharge rate, an electrical load status of the vehicle, and load priority data; and to execute the determined load control plan.

Abstract: A parking control method executes a control instruction for moving a vehicle along a parking route. The parking route is calculated based on an operation command acquired from an operator located outside the vehicle. The parking control method includes detecting a relative altitude between a first height position of the operator and a second height position of the vehicle and when determining that the relative altitude is not less than a first predetermined value, changing a first speed to a second speed lower than the first speed. The first speed is preliminarily set in the control instruction. The parking control method further includes moving the vehicle in accordance with the control instruction changed.

Abstract: An electrical resistance of a lamp in communication with a computer is determined. A respective classification for each of the electrical resistance, a vehicle length, and a trailer length is determined. Each classification is associated to a respective range of values of one of the electrical resistance, the vehicle length, or the trailer length. Based on the classifications a trailer that is attached to a vehicle is detected. One or more components of the vehicle are actuated to move the trailer.

Abstract: Systems, methods and apparatus of recordation of vehicle data associated with errant vehicle behavior. For example, a vehicle includes: sensors configured to generate sensor data; control elements configured to generate control signals to be applied to the vehicle in response to user interactions with the control elements; electronic control units configured to provide status data in operations of the electronic control units; and a data storage device. The data storage device is configured to receive input data including the sensor data, the control signals and the status data, store the input data in a cyclic way in an input partition over time, generate a classification of errant behavior based on the input data and using an artificial neural network, and preserve a portion of the input data associated with the classification of errant behavior.

Abstract: Among other things, techniques are described for steering angle calibration. An autonomous vehicle receives a steering angle measurement and a yaw rate measurement, and estimates a steering angle offset using the steering angle measurement, the yaw rate measurement, and a wheel base of the autonomous vehicle. An estimated yaw rate is determined based on a yaw rate model, the steering angle measurement and the estimated steering angle offset. The yaw rate measurement and the estimated yaw rate are compared and an action is initiated on the autonomous vehicle in response to the comparing.

Abstract: A steering control device includes: an absolute steering angle detecting unit configured to detect an absolute steering angle; and a current command value calculating unit configured to calculate a current command value corresponding to a target value of the motor torque output from the motor. The current command value calculating unit is configured to perform partial release control for decreasing a correction value of the current command value due to execution of the end contact relaxation control when a vehicle is tried to be turned at the time of execution of the end contact relaxation control. The current command value calculating unit is configured to stop the partial release control when the current command value which is calculated at the time of execution of the partial release control is a value which is not affected by decreasing the correction value based on execution of the partial release control.

Abstract: An apparatus and method for controlling lane following include acquiring front image information through a camera installed at an ego-vehicle during travel of the ego-vehicle; setting a target trajectory of the ego-vehicle using line information and travel information of a preceding vehicle extracted based on the image information; and calculating a steering torque to control steering of the ego-vehicle along the set target trajectory.

Abstract: A vehicle control system includes a plurality of driving assistance devices configured to sequentially send request signals including requests to an actuator in the vehicle and identifiers of the driving assistance devices to an in-vehicle network, a movement manager device configured to acquire the request signals from the in-vehicle network, select one of the identifiers respectively included in the acquired request signals based on a predetermined rule, and sequentially send a control signal including at least the selected identifier to the in-vehicle network, and an actuator control device configured to sequentially acquire the request signal and the control signal from the in-vehicle network, when the control signal is acquired, select a latest request signal including the identifier included in the acquired latest control signal among the acquired request signals, and decide a control value of the actuator based on the request included in the selected request signal.

Abstract: Cargo aerial delivery systems for delivering one or more delivery items and related methods. A cargo aerial delivery system may include a cargo container configured to carry the delivery item(s) and an unmanned aerial vehicle (UAV) configured to carry the cargo container to delivery destinations of the delivery items. The cargo container may include a programmable device that stores manifest information regarding the delivery item(s) and a local communication mode configured to convey delivery information from the cargo container to the UAV. A method of utilizing a cargo aerial delivery system may include loading delivery item(s) into a container body of a cargo container, entering manifest information into a programmable device, operatively engaging the cargo container with a UAV, generating a delivery itinerary, transporting the cargo container with the UAV according to the delivery itinerary, and unloading each delivery item at the respective delivery destination.