Abstract: A device for lane determination includes a processor configured to detect a vehicle region representing a target vehicle traveling in an area around a host vehicle from an image of the area around the host vehicle generated by a camera mounted on the host vehicle, and determine that the target vehicle is traveling on an adjacent lane next to a lane on which the host vehicle is traveling, in the case where the vehicle region touches a left or right edge of the image and where a bottom position of the vehicle region is within a predetermined vertical range of the image.

Abstract: Disclosed are methods, systems, and one or more computer-readable mediums for performing, by one or more processors located off-board a vehicle, operations including receiving, by the fog based application framework before transit of the vehicle, vehicle operation data from a cloud based database of a cloud based computing system; receiving, by the fog based application framework before and/or in real-time during transit of the vehicle, edge-based vehicle data from one or more edge computing devices of the vehicle; and generating, by the fog based application framework during transit of the vehicle, a plurality of vehicle operation insights based on the vehicle operation data and the edge-based vehicle data.

Abstract: This application provides a road structure detection method and apparatus. The method includes: determining boundary information of a host lane and boundary information of an adjacent lane, and determining road structure information based on the boundary information of the host lane and the boundary information of the adjacent lane. The boundary information of the host lane is used to represent a location of a boundary of the current lane. The boundary information of the adjacent lane is used to represent a location of a boundary of the adjacent lane. The boundary information includes lane line information and/or location information of a lane boundary. The road structure information includes location information of a merge point (A) of the host lane and the adjacent lane and/or a split point (B) of the host lane and the adjacent lane.

Abstract: A system may detect a sound associated with a vehicle. The sound may be detected using a set of one or more microphones. The system may use a machine learning model to detect at least one of a squeak or a rattle based on the sound. The machine learning model may be trained using a plurality of sounds emitted in relation to one or more vehicles. The system may determine, based on detecting at least one of the squeak or the rattle, a location of the vehicle associated with at least one of the squeak or the rattle. In some implementations, the location may be determined based on detecting different sound levels between a first microphone and a second microphone, or detecting a time difference between the first and the second microphone, or by correlating the sound to a sound signature associated with a part of the vehicle.

Abstract: When accelerating a vehicle toward a set speed after the vehicle travels on a curved road at a vehicle speed equal to or lower than a speed limit based on the curved road, a driving support method and a driving support device accelerate the vehicle by a first acceleration in a case of acquiring a curve information related to the curved road, and accelerate the vehicle by a second acceleration smaller than the first acceleration in a case of not acquiring the curve information.

Abstract: A system selecting a parking spot using reinforcement learning includes a first monitor evaluating available parking spots in a parking lot. Reinforcement learning (RL) is used to pick a parking spot based on user preferences. A computer computes a probability of a future parking spot availability from the available parking spots. An information source wherein the computer retrieves information including time of day, weather and location from the information source to assist in computing the probability of the future parking spot availability. An update module receives the future parking spot availability from the computer and updates a belief probability, the belief probability including a belief defined as a data structure in which a probability of the available individual parking spots within the parking lot is stored. An RL model is updated for the parking lot after a park maneuver is completed for a host vehicle.

Abstract: Techniques for determining a response of a simulated vehicle to a simulated object in a simulation are discussed herein. Log data captured by a physical vehicle in an environment can be received. Object data representing an object in the log data can be used to instantiate a simulated object in a simulation to determine a response of a simulated vehicle to the simulated object. Additionally, one or more trajectory segments in a trajectory library representing the log data can be determined and instantiated as a trajectory of the simulated object in order to increase the accuracy and realism of the simulation.

Abstract: A dock area control system includes a vehicle proximity detection system (PDSC). The PDSC includes a vehicle low frequency magnetic field generator (MFG) that generates a vehicle pulsed magnetic field that is sensed by a dock area controller electronics module (DEM).

Abstract: An electric vehicle control method including using a first motor and a second motor as travel drive sources, performing drive control on the first motor by transmitting a first torque command value to a first inverter, and performing drive control on the second motor by transmitting a second torque command value to a second inverter, and performing switching control of switching, based on a required drive force, the drive control on the second motor by the second inverter between an ON state in which the drive control is performed and an OFF state in which the drive control is stopped, wherein a torque fluctuation amount generated in the second motor during the switching control is calculated based on a rotation speed of the second motor, and the first torque command value is corrected based on the torque fluctuation amount.

Abstract: The subject disclosure relates to estimating a grade of a road and calibrating sensors of an autonomous vehicle based on the grade. A process of the disclosed technology can include effectuating an autonomous vehicle to perform one or more maneuvers that cause the autonomous vehicle to face different directions along a road, obtaining a first set of sensor measurements of an autonomous vehicle in a first pose, wherein the first set of sensor measurements includes a first measured specific force, obtaining a second set of sensor measurements of the autonomous vehicle in a second pose, wherein the second set of sensor measurements includes a second measured specific force, determining a direction of gravity based on the first measured specific force and the second measured specific force, and calibrating at least one sensor of the autonomous vehicle based on the determined direction of gravity.

Abstract: There is provided a control apparatus that identifies an area for which an analysis is not required based on information of an image captured from a position of a movable object, identifies a first time period that is a time period for the movable object to reach the identified area, calculates a second time period that is an arrival time period to reach a movement area of the movable object from a position in the identified area, sets, in the identified area, a risk area where an object approaching the movable object may be present based on the first time period and the second time period and on the identified area, and controls transmission of risk area information.

Abstract: System, methods, and other embodiments described herein relate to coordinating and optimizing prediction by a model using intermediate data and vehicle-to-vehicle (V2V) communications that improves bandwidth utilization. In one embodiment, a method includes processing acquired data, by a subject vehicle using a prediction model, to execute a vehicle task associated with navigating a driving scene. The method also includes extracting processed data according to the acquired data from intermediate activations of layers within the prediction model according to a cooperation model. The method also includes quantifying relevancy of the processed data, for a target vehicle, to select a subset using the cooperation model. The method also includes communicating the subset to a selected vehicle having the prediction model for additional prediction according to the relevancy and available resources to transmit the subset.

Abstract: A motor control device is provided which achieves redundancy while suppressing an increase in the number of parts and connection signal lines. The device includes angle sensors for detecting a rotation angle of a motor, a first microcomputer unit for controlling the motor based on a stroke sensor and receiving the detected value of the angle sensor, a second microcomputer unit for controlling the motor based on the stroke sensor and receiving the detected value of the angle sensor, and communication units for transmitting and receiving signals between the microcomputer units. The first microcomputer unit includes an angle sensor failure detecting unit for detecting a failure of the angle sensors, according to the detected value of the angle sensors, and a control angle of the motor created in response to the stroke sensor.

Abstract: A vehicle controller detects a travel lane on which a vehicle is traveling, and determines whether the position of the detected travel lane relative to an edge of a road may differ from an actual position. The vehicle controller further identifies first control of the vehicle required on the travel lane and second control of the vehicle required on an adjoining lane. The vehicle controller transfers control of the vehicle to a driver in the case where the position of the detected travel lane may differ from the actual position and where both the first control and the second control may compromise safety of the vehicle or prevent completion of a predetermined action to be completed before reaching a predetermined distance.

Abstract: A processor performs a mediation process of mediating remote support of at least one vehicle when receiving a request for remote support from the at least one vehicle. In the mediation process, at least two vehicles are organized into at least one group based on map information and position and traveling direction information of the at least two vehicles when requests for remote support from the at least two vehicles have been received in the same time period. The support order of the vehicles in the at least one group is determined for each group based on the map information and the position and traveling direction information of the at least two vehicles. The surrounding image information of the corresponding vehicle is transmitted to at least one support device that performs remote support of the vehicles organized into the at least one group in the support order.

Abstract: A crane control system for actuating positioners of a crane is configured to receive target position data which describe a predefined target position of at least one positioner, in particular at least one crane superstructure positioner; receive clearance data which describe a user input for clearing a movement of the at least one positioner into the predefined target position; and output control data which describe control signals to be output to the at least one positioner in order to move the at least one positioner into the predefined target position.

Abstract: The present disclosure relates to a vehicle collision prevention system and a collision prevention method by using the same, and may include a first light source positioned on a left side of a vehicle, a second light source positioned on a right side of the vehicle, a camera positioned at a center of the vehicle and providing a shape, which is displayed when rays emitted from the first light source and the second light source irradiate an object, as image data, an image processing device that generating braking information based on the image data, and a braking device that performing a braking operation of decreasing a speed of the vehicle or stopping the vehicle based on the braking information.

Abstract: Techniques for generating testing data for an autonomous vehicle (AV) are described herein. A system can obtain sensor data descriptive of a traffic scenario. The traffic scenario can include a subject vehicle and actors in an environment. Additionally, the system can generate a perturbed trajectory for a first actor in the environment based on perturbation values. Moreover, the system can generate simulated sensor data. The simulated sensor data can include data descriptive of the perturbed trajectory for the first actor in the environment. Furthermore, the system can provide the simulated sensor data as input to an AV control system. The AV control system can be configured to process the simulated sensor data to generate an updated trajectory for the subject vehicle in the environment. Subsequently, the system can evaluate an adversarial loss function based on the updated trajectory for the subject vehicle to generate an adversarial loss value.

Abstract: Systems and methods are described for measuring velocity of an object detected by a light detection and ranging (lidar) system. According to some aspects a method may include receiving a lidar dataset generated by the lidar system, transforming the lidar dataset into a first layer dataset and a second layer dataset, and converting the first layer dataset into a first image and the second layer dataset into a second image. The method may also include performing a feature detection operation that identifies at least one feature in the first image and the same feature in the second image, locating a first location of the feature in the first image and a second location of the feature in the second image, and generating a velocity estimate of the feature based on a difference between the first location and the second location and a difference between the different time intervals.

Abstract: A shovel includes a lower traveling body, an upper turning body turnably mounted on the lower traveling body, a boom attached to the upper turning body, an arm attached to the boom, an end attachment attached to the arm, a sensor configured to output detection information about an orientation of a work part of the end attachment, and a processor configured to control operation of the work part to cause the work part to perform compaction of ground by pressing the work part against the ground, wherein the processor is configured to control an operation of the arm and the end attachment according to a lowering operation of the boom to cause an end portion of the work part to perform the compaction of the ground on the basis of the detection information of the sensor.