Abstract: A system for controlling an unmanned aerial vehicle (UAV) includes smart glasses and a remote controller. The smart glasses are configured to establish a first channel directly with the UAV, receive first person view (FPV) image data directly from the UAV through the first channel, and display the FPV image data. The remote controller is configured to establish a second channel directly with the UAV, and send a flight control instruction directly to the UAV through the second channel.

Abstract: A vehicular communication apparatus is configured to be mounted on a movable body and to receive movement data related to movements of other movable bodies. The apparatus includes an acquiring unit, a memory, and a data managing unit. The acquiring unit is configured to acquire the movement data on the other movable bodies. The memory is configured to store and record therein the movement data acquired by the acquiring unit. The data managing unit is configured to manage the record of the movement data in the memory. The data managing unit is configured to acquire a virtual speed of each movable body that is obtained from the movement data recorded in the memory, and invalidate or delete the movement data recorded in the memory on a movable-body by movable-body basis, in accordance with the acquired virtual speed of each movable body.

Abstract: Embodiments of the present disclosure relate generally to generating and utilizing three-dimensional terrain maps for vehicular control. Other embodiments may be described and/or claimed.

Abstract: A system, comprising a computer that includes a processor and a memory, the memory storing instructions executable by the processor to detect and locate an object by processing video camera data with a capsule network, wherein training the capsule network includes determining routing coefficients with a scale-invariant normalization function. The computer can be further programmed to receive the detected and located object.

Abstract: This vehicle control system is provided with an input monitoring unit and a determination time changing unit. When a state in which first target data is not input to a second control unit continues for a first determination time or longer, the input monitoring unit determines the first target data to be in a non-input state. When a state in which second target data is not input to the second control unit continues for a second determination time or longer, the input monitoring unit determines the second target data to be in a non-input state. When the first target data is determined to be in a non-input state, the determination time changing unit shortens the second determination time.

Abstract: A method for an autonomous vehicle includes: receiving first object data from a first sensor module; receiving second object data from a second sensor module; comparing the first object data to the second object data; determining, based on comparing the first object data to the second object data, whether the first object data corresponds to the second object data; and in response to determining that the first object data does not correspond to the second object data, performing an action for the autonomous vehicle.

Abstract: Embodiments of the present disclosure relate generally to generating and utilizing three-dimensional terrain maps for vehicular control. Other embodiments may be described and/or claimed.

Abstract: Smart car operations are detailed. The system uses neural network and population statistics to determine whether a vehicle operation is reasonably safe operation of the autonomous vehicle to guide the operation of cars as a group.

Abstract: Improved control of cruise control for a vehicle, in particular an automated activation of cruise control. For this purpose, the speed of the vehicle is monitored. If the speed of the vehicle and/or a distance between the vehicle and a further vehicle in front of the vehicle is within a predetermined range for a specific period of time it is indicated to a user that cruise control can be activated. Accordingly, cruise control can be automatically activated after providing the indication to the user, or a user may respond to this indication by providing a specific activity such as a release of the acceleration pedal.

Abstract: At an application executing in a device in a vehicle, a phrase is detected in a conversation occurring between two users. A determination is made that the phrase is usable in providing a navigation directive. Using NLP, a deep parsing the conversation is performed to extract a context applicable to the phrase. the context is evaluated to determine whether the context is related to a navigation of the vehicle. At the device, from the conversation, a future location is computed of the vehicle during the navigation. Using data from a data source, a suboptimal driving condition is identified on a route between a present location of the vehicle and the future location. A user in the vehicle is alerted about the suboptimal driving condition on the route.

Abstract: Example systems and methods are disclosed for implementing vehicle operation limits to prevent vehicle load failure during vehicle teleoperation. The method may include receiving sensor data from sensors on a vehicle that carries a load. The vehicle may be controlled by a remote control system. The load weight and dimensions may be determined based on the sensor data. In order to prevent a vehicle load failure, a forward velocity limit and an angular velocity limit may be calculated. Vehicle load failures may include the vehicle tipping over, the load tipping over, the load sliding off of the vehicle, or collisions. The vehicle carrying the load may be restricted from exceeding the forward velocity limit and/or the angular velocity limit during vehicle operation. The remote control system may display a user interface indicating to a remote operator the forward velocity limit and the angular velocity limit.

Abstract: The present disclosure relates to systems and methods for distributing service requests for an on-demand service. The systems may perform the methods to obtain the service request; determine first information related to the service request, wherein the first information comprises at least one of a start location, a destination, or a start time; determine reference information based at least in part on the first information related to the service request; generate a modified service request based on the service request and the reference information; and send the modified service request to the at least one provider terminal.

Abstract: Aspects described herein provide a computer-implemented method and system for grouping topographic data based on the context of said data without the operator needing to make any assumptions. For each vector feature, its context, that is, information about the adjacent features, is incorporated in to the associated attribution data. In doing this, the system is able to characterise all of the vector features in a geographical area based on its context, from which patterns emerge. These patterns indicate features that have similar contexts, enabling the system to group the vector features according to their contexts based on their characteristics and attributes. Conversely, features that are anomalous within the region, that is, they do not fit the pattern of the surrounding features, are also identified. This is particularly important for identifying and resolving errors in the underlying topographic data.

Abstract: A method for control of a rear-axle steering of a motor vehicle. A steering angle of wheels of a rear axle is set. Upon reaching a predetermined lateral acceleration of the motor vehicle, the steering angle and/or the gradient of the steering angle of the wheels of the rear axle is limited as a function of a coefficient of friction of a roadway surface on which the motor vehicle is moving.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle and, for only those agents which are high priority agents, generating data characterizing the agents using a first prediction model. In a first aspect, a system identifies multiple agents in an environment in a vicinity of a vehicle. The system generates a respective importance score for each of the agents by processing a feature representation of each agent using an importance scoring model. The importance score for an agent characterizes an estimated impact of the agent on planning decisions generated by a planning system of the vehicle which plans a future trajectory of the vehicle. The system identifies, as high-priority agents, a proper subset of the plurality of agents with the highest importance scores.

Abstract: The disclosure includes embodiments for managing a flow of traffic through an intersection. In some embodiments, a method for a roadside device proximate to the intersection of a roadway includes retrieving twin data describing one or more digital behavioral twins of a vehicle present in a vicinity of the intersection. The method includes retrieving sensor data describing a driving context of the vehicle. The method includes modifying an operation of an Advanced Driver Assistance System (ADAS) of the vehicle to achieve managing the flow of traffic including the vehicle through the intersection based on the driving context and the one or more digital behavioral twins of the vehicle to improve safety and traffic efficiency within an intersection range.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. In one aspect, a method comprises processing an input that characterizes a trajectory of the vehicle in an environment using an importance scoring model to generate an output that defines a respective importance score for each of a plurality of agents in the environment in the vicinity of the vehicle. The importance score for an agent characterizes an estimated impact of the agent on planning decisions generated by a planning system of the vehicle which plans a future trajectory of the vehicle. The high-priority agents are identified as a proper subset of the plurality of agents with the highest importance scores.

Abstract: A redundant sensor fabric in an autonomous vehicle may include receiving, by a processing unit, sensor data from a first sensor of a plurality of sensors associated with a same sensing space of the autonomous vehicle; detecting a fault associated with the first sensor; establishing, via a switched fabric, a communications path between the processing unit and a second sensor of the plurality of sensors; and receiving, by the processing unit, sensor data from the second sensor instead of the first sensor.

Abstract: A construction machine system comprises a self-propelled construction machine and a total station. The construction machine possesses a machine frame, a drive means and a working means for altering the terrain. A position-determination means determines the position of a reference point on the machine in a first coordinate system independent of the machine. The position-determination means receives satellite signals from a global navigation satellite system (GNSS), wherein in normal operation the machine is controlled using the GNSS such that a reference point on the machine moves along a set target travel path. In a total station control mode, the machine is controlled without the GNSS and only using the total station based on a position of the standpoint and orientation of the total station ascertained in the GNSS control mode, and the position-determination of the construction machine occurs in a second coordinate system based on the total station.

Abstract: Systems, methods, and devices of the various embodiments enable dynamic configuration of a number of display regions of interest (ROIs) associated with safety critical content presented on a display, such as a vehicle display. Various embodiments may enable verification of data integrity for ROIs on a display. Various embodiments may enable the selection of different sets of display ROIs from a plurality of independent sets of display ROIs each associated with its own set of stored integrity check values (ICVs). Various embodiments may enable stored ICVs to be used to verify the data integrity of ROIs on a display. Various embodiments may enable the set of display ROIs and the associated ICVs for each display ROI to be changed after a number of frames have been displayed.