Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine six degree of freedom (DoF) data for a first object in a first video image and generate a synthetic video image corresponding to the first video image including a synthetic object and a synthetic object label based on the six DoF data. The instructions can include further instructions to train a generative adversarial network (GAN) based on a paired first video image and a synthetic video image to generate a modified synthetic image and train a deep neural network to locate the synthetic object in the modified synthetic video image based on the synthetic object. The instructions can include further instructions to download the trained deep neural network to a computing device in a vehicle.

Abstract: A communication system includes a data manager unit, a private interface, and an open interface. The data manager unit is configured to be disposed onboard a vehicle and to manage a transmission of data from a control system of the vehicle to a plurality of applications. The private interface is configured to communicably couple the data manager unit to the control system of the vehicle, and to limit communication with the control system via a connection protocol, wherein the connection protocol is configured to prevent direct communication between the data manager unit and an application that does not use the connection protocol. The open interface is configured to communicably couple the data manager unit and the plurality of applications.

Abstract: A steering control device includes an electronic control unit. The electronic control unit controls operation of a steering-side motor so as to apply a steering reaction force that resists a steering operation input to the steering wheel. The electronic control unit computes an obstruction strike reaction force for regulating a steering operation that steers a steered wheel toward an obstruction. The electronic control unit generates determination information indicating that the steered wheel is struck by an obstruction. The determination information includes first determination information indicating that the left side of the steered wheel is struck by an obstruction, and second determination information indicating that the right side of the steered wheel is struck by an obstruction. The electronic control unit sets a direction in which the obstruction strike reaction force is applied based on the generated determination information.

Abstract: A method for operating a motor vehicle, wherein the motor vehicle has a steering system for steering at least one wheel of the motor vehicle by means of a drive. In doing so, it is provided that a time span is determined for at least one countermeasure limiting a hazard to a vehicle occupant upon an at least partial failure of the steering system, within which time span the countermeasure deploys an effect, and that a state variable (T) influencing the operating capacity of the steering system is determined and extrapolated over time and a point in time (t1) is calculated in which the state variable (T) exceeds a limit value (T1), wherein the countermeasure is introduced when the point in time (t1) is less than the time span in the future.

Abstract: The present disclosure relates to an apparatus and a method for controlling a steer-by-wire system. In more details, the present disclosure relates to an apparatus and method for determining whether a catch-up is occurred due to a counter electromotive force in a rack drive motor in a steer-by-wire system and reflecting torque information that has not been output due to the catch-up on a steering reaction force motor, and thus providing an accurate steering sense for a driver.

Abstract: Sensor data obtained from a plurality of sensors mounted on an ADV driving on a route is collected. A set of features from the sensor data are extracted, where the set of features including an acceleration and a speed of the ADV driving on the route. A first similarity between the ADV and a first driving behavior associated with a first type of drivers driving on the route is determined based on the set of features. A second similarity between the ADV and a second driving behavior associated with a second type of drivers driving on the route is determined based on the set of features. A comfort score of the ADV based on the first similarity and the second similarity is determined to evaluate a motion planning and control of the ADV.

Abstract: Various aspects of a system, a method, and a computer program product for generation of roadwork extension data of a roadwork zone are disclosed herein. In accordance with an embodiment, the system includes a memory and a processor. The processor may be configured to obtain speed funnel data of one or more speed funnels. The processor may be configured to determine a plurality of candidate roadwork links, based on the speed funnel data. The processor may be configured to obtain vehicular trajectory data corresponding to the plurality of candidate roadwork links. The processor may be further configured to determine at least one qualified roadwork link from the plurality of candidate roadwork links, based on the vehicular trajectory data and speed threshold data of the plurality of candidate roadwork links. The processor may be further configured to generate the roadwork extension data based on the at least one qualified roadwork link.

Abstract: A shovel control method includes performing a plane position control or a height control of an end attachment by an operation of one lever. The plane position control is performed while maintaining a height of the end attachment. The height control is performed while maintaining a plane position of the end attachment.

Abstract: Example methods, apparatus, systems, and machine-readable mediums for an artificial intelligence platform for mobile charging of rechargeable vehicles and robotic devices are disclosed. An example method may include determining that a mobile vehicle is operating within a region and determining that the mobile vehicle requires charging of a battery for the mobile device while operating within the region. The method may further comprise identifying a charging station available within the region for charging of the battery at a time and a location within the region and navigating at least one of the mobile vehicle or the charging station to the location at the time for charging the battery of the mobile vehicle.

Abstract: The present application provides a method, apparatus and system for controlling transportation between warehouses. The method includes: receiving, from the source RCS, first transportation information which includes information of a first to-be-transported object; transporting the first to-be-transported object to a handover area; transferring control over the AGV from the source RCS to the target RCS; receiving a location of a first target storage space from the target RCS; transporting the first to-be-transported object from the handover area to the first target storage space. In the present application, the AGV transfers the control over itself from the source RCS to the target RCS after moving the to-be-transported object to the handover area, such that the target RCS could take over the AGV and control the AGV to transport the first to-be-transported object from the handover area to the first target storage space.

Abstract: The present invention may provide a method of managing, by a vehicle, a sensor. Herein, a method of managing, by a vehicle, a sensor may include: monitoring state information of a first sensor of a first vehicle; when the first sensor is abnormal, determining whether or not a second sensor performs the function of the first sensor; when the second sensor performs the function of the first sensor, reporting information representing that second sensor performs the function of the first sensor; and receiving sensing data from the second sensor.

Abstract: Examples of systems and methods for locating movable objects such as carts (e.g., shopping carts) are disclosed. Such systems and methods can use dead reckoning techniques to estimate the current position of the movable object. Various techniques for improving accuracy of position estimates are disclosed, including compensation for various error sources involving the use of magnetometer and accelerometer, and using vibration analysis to derive wheel rotation rates. Also disclosed are various techniques to utilize characteristics of the operating environment in conjunction with or in lieu of dead reckoning techniques, including characteristic of environment such as ground texture, availability of signals from radio frequency (RF) transmitters including precision fix sources. Such systems and methods can be applied in both indoor and outdoor settings and in retail or warehouse settings.

Abstract: The present disclosure relates to a hybrid vehicle control device, a system including the same, and a method thereof. The hybrid vehicle control device according to an embodiment of the present disclosure includes a processor and storage. The processor sets a target engine speed and determines presence or absence of a kick down shift based on the vehicle driving situation, and performs engine clutch engagement control according to a result of the kick down shift. The storage stores the vehicle driving situation and a result of the determination of the presence or absence of the kick down shift.

Abstract: A method for assisting a driver of a host vehicle in avoiding a collision, the method including: detecting a target in the vicinity of the vehicle; determining that the host vehicle is travelling on a collision course with the target; detecting a set of road markers on a side of the target; detecting a free space on the side of the road markers opposite the target side of the road markers, and when a collision with the target is predicted to occur within a predetermined time period and no driver initiated steering action for avoiding the collision course has been detected, providing a steering guidance to the driver of the host vehicle including altering of a steering wheel angular orientation for momentarily steering the host vehicle towards the road markers to indicate an evasive steering action to the driver.

Abstract: The disclosure relates to methods, systems, and apparatuses for autonomous driving vehicles or driving assistance systems and more particularly relates to vehicle radar perception and location. The vehicle driving system disclosed may include a storage media, a radar system, a location component and a driver controller. The storage media stores a map of roadways. The radar system is configured to generate perception information from a region near the vehicle. The location component is configured to determine a location of the vehicle on the map based on the radar perception information and other navigation related data. The drive controller is configured to control driving of the vehicle based on the map and the determined location.

Abstract: Systems and methods are disclosed for identifying time-latency and subsystem control actuation dynamic delay due to second order dynamics that are neglected in control systems of the prior art. Embodiments identify time-latency and subsystem control actuation delays by developing a discrete-time dynamic model having parameters and estimating the parameters using a least-squares method over selected crowd-driving data. After estimating the model parameters, the model can be used to identify dynamic actuation delay metrics such as time-latency, rise time, settling time, overshoot, bandwidth, and resonant peak of the control subsystem. Control subsystems can include steering, braking, and throttling.

Abstract: A vehicle control apparatus and method are provided. The vehicle control apparatus comprises a surrounding detection part, detecting a surrounding status of a host vehicle; and a control part, performing a moving control of the host vehicle according to the surrounding status. In a road system including a first road and a second road intersected with the first road that includes a first lane, a second lane that is an opposite lane of the first lane and a specified area arranged between the first and the second lanes, when the host vehicle enters the first lane, the control part make a determined result whether the host vehicle can enter the specified area or not according to a traffic situation of the second lane, and performs the moving control according to the determined result.

Abstract: A flight-time variable associated with an aircraft is determined including by determining the flight-time variable while the aircraft is flying. It is determined whether the aircraft is airworthy based at least in part on the flight-time variable. In response to determining that the aircraft is not airworthy, the aircraft is automatically landed.

Abstract: Electric vehicle predictive range estimating systems and methods are provided herein. An example method includes determining an initial state of charge (SOC) for an energy source of a vehicle at a first point in time; determining one or more boundary conditions for the vehicle during a time frame extending from the first point in time to a second point in time, the one or more boundary conditions causing a loss in the energy source during the time frame; determining a predicted future SOC for the energy source based on the one or more boundary conditions and the initial SOC; and predicting an availability of a vehicle operating condition based on the predicted future SOC for the energy source.

Abstract: A RLP system for a host vehicle includes a memory and levels. The memory stores a RLP algorithm, which is a multi-agent collaborative DQN with PER algorithm. A first level includes a data processing module that provides sensor data, object location data, and state information of the host vehicle and other vehicles. A second level includes a coordinate location module that, based on the sensor data, the object location data, the state information, and a refined policy provided by the third level, generates an updated policy and a set of future coordinate locations implemented via the first level. A third level includes evaluation and target neural networks and a processor that executes instructions of the RLP algorithm for collaborative action planning between the host and other vehicles based on outputs of the evaluation and target networks and to generate the refined policy based on reward values associated with events.