Abstract: The technology relates to determining a future heading of an object. In order to do so, sensor data, including information identifying a bounding box representing an object in a vehicle's environment and locations of sensor data points corresponding to the object, may be received. Based on dimensions of the bounding box, an area corresponding to a wheel of the object may be identified. An orientation of the wheel may then be estimated based on the sensor data points having locations within the area. The estimation may then be used to determine a future heading of the object.

Abstract: When a first driver setting mode indicates an “OFF mode” or an “AUTO mode,” a VP accepts a light operation mode request from an ADK. When an operation is performed by a user, the VP changes an operation mode of a headlight in accordance with the operation by the user. When the operation by the user has not been performed, the VP changes the operation mode of the headlight in accordance with the light operation mode request.

Abstract: A mobile vehicle and a method of controlling the mobile vehicle are provided. The method of controlling the mobile vehicle includes defining a first line between the mobile vehicle and the user, determining a position and a size of each of at least one obstacle having a predetermined relationship with the first line, defining a second line based on the first line, the position of the at least one obstacle, and the size of the at least one obstacle, and controlling the mobile vehicle according to a direction and a size of an external force on the second line.

Abstract: Systems and methods for including overstay and human behavior in the pricing structure of a plug-in electric vehicle (PEV) charging station, in order to maximize operating revenue, and manage overstay duration. A mathematical framework with discrete choice models (DCM) is incorporated to operate a PEV charging station with an optimal pricing policy and charge control. The framework determines the probability of a PEV driver selecting various charging options, including overstay price. The pricing options are charging-flexibility, which allows a controller to manage charging costs over a parking duration, charging-asap, which charges the electric vehicle immediately and continuously until the vehicle departs, the battery is fully charged, or a desired level of charge has been reached, and leaving, which is an opportunity cost to the charging station.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reserving airspace for UAV operations. In some implementations, a flight planning system can reserve and allocate airspace for unmanned aerial vehicle (UAV) operations. For example, a UAV operator device can submit a flight plan to the flight planning system. The flight planning system can submit a flight authorization request to an airspace management system to reserve airspace necessary for the flight plan. The flight planning system can receive approval and/or a reservation of the airspace for the flight plan from the airspace management system, generate a flight data package, and send the flight data package to the operator's device.

Abstract: Systems, methods, and vehicles for taking a vehicle out-of-service are provided. In one example embodiment, a method includes obtaining, by one or more computing devices on-board an autonomous vehicle, data indicative of one or more parameters associated with the autonomous vehicle. The autonomous vehicle is configured to provide a vehicle service to one or more users of the vehicle service. The method includes determining, by the computing devices, an existence of a fault associated with the autonomous vehicle based at least in part on the one or more parameters associated with the autonomous vehicle. The method includes determining, by the computing devices, one or more actions to be performed by the autonomous vehicle based at least in part on the existence of the fault. The method includes performing, by the computing devices, one or more of the actions to take the autonomous vehicle out-of-service based at least in part on the fault.

Abstract: An apparatus including an interface and a processor. The interface may be configured to receive pixel data of an area external to a vehicle. The processor may be configured to generate video frames from the pixel data, perform computer vision operations on the video frames to detect objects in the video frames and determine characteristics of the objects, analyze the characteristics of the objects to determine a visually observable status of the objects, perform a comparison of the visually observable status to a remote command and send the remote command if the comparison determines that the visually observable status does not match the remote command. The remote command may be configured to control the visually observable status of the objects.

Abstract: A driver assistance system according to an embodiment of present disclosure includes: a camera disposed on the vehicle to have an external field of view of a vehicle and configured to obtain image data; a radar disposed on the vehicle to have a field of sensing outside the vehicle and configured to obtain radar data; and a controller including a processor configured to process the image data and the radar data, and the controller is configured to determine whether a rear vehicle changes direction based on the image data obtained by the camera, determine whether there is a risk of collision with the rear vehicle based on the radar data when the rear vehicle does not change direction and control at least one of a steering system or a vehicle velocity control system of the vehicle to avoid the rear vehicle when it is determined that there is a risk of collision with the rear vehicle.

Abstract: A method, apparatus, and system for filtering a point cloud generated by a LIDAR device in an autonomous vehicle is disclosed. A point cloud comprising a plurality of points is generated based on outputs of the LIDAR device. The point cloud is filtered to remove a first set of points in the plurality of points that correspond to noise based on one or more of: point intensity measurements, distances between points, or a combination thereof. Perception data is generated based on the filtered point cloud. Operations of the autonomous vehicle are controlled based on the perception data.

Abstract: A system and method for providing a virtual approach signal restriction upgrade between physical signaling components is presented. In one embodiment, in a CTC type of operation, the use of a virtual signal with signal type functionality to split a block into two or more sections can allow a train currently governed by an approach indication to accelerate on a clear indication if the advance signal indication upgrades. The addition of audio frequency type circuits with the advance signal indication can allow a train to upgrade from a restricting indication to an approach or clear indication, while protecting open HT switches, broken rail, hazards, and follow up moves. The present invention provides a system for allowing trains to upgrade from a “restricting” indication to an “approach” or “clear and accelerate” indication with an upgraded PTC track line for the segment.

Abstract: Methods and apparatus for matching portions of images are described as well as using depth information generated from the matching results. In various embodiments, lower portions of images of a scene area, which are more likely to include objects closer to a vehicle on which cameras are mounted, than are portions of images corresponding to an upper portion of the scene area, are processed and used for depth determination. In this way, depths to objects, which are likely to be closer to the vehicle than objects in the upper portion of the scene area, are determined first and used to control a vehicle reducing the risk of collision as compared to systems where the depth determination of an entire scene is completed before depth information is used for control purposes with the order of processing being such that nearer objects are likely to be detected prior to more distant objects.

Abstract: A system for controlling a vehicle includes at least one vehicle network on board the vehicle, first and second controllers coupled to the at least one vehicle network and configured to communicate with each other via the at least one vehicle network, and first and second sensor sets coupled to the at least one vehicle network, and configured to communicate with any of the first and second controllers via the at least one vehicle network. Each of the first and second controllers is configured to, based on data output from any of the first and second sensor sets, control a movement of the vehicle independently of the other of the first and second controllers. The first sensor set is located at a first location on the vehicle, the second sensor set is located at a second location on the vehicle, and the second location is different from the first location.

Abstract: A driver monitoring system configured to monitor the performance of a driver of a vehicle communicating wirelessly with the driver monitoring system. The system comprises a driver behavior module that receives from the vehicle event data captured by a plurality of sensors in the vehicle and identifies at least one of a plurality of driver behaviors. A behavior characterization module receives from the driver behavior module the at least one identified driver behavior and characterizes the at least one identified driver behavior into at least one of a plurality of behavior categories. A risk assessment module analyzes the at least one characterized driver behavior in the plurality of behavior categories and determines therefrom a driver profile that may include a risk assessment for the driver of the vehicle system.

Abstract: Methods and systems for improved simultaneous localization and mapping based on 3-D LIDAR image data are presented herein. In one aspect, LIDAR image frames are segmented and clustered before feature detection to improve computational efficiency while maintaining both mapping and localization accuracy. Segmentation involves removing redundant data before feature extraction. Clustering involves grouping pixels associated with similar objects together before feature extraction. In another aspect, features are extracted from LIDAR image frames based on a measured optical property associated with each measured point. The pools of feature points comprise a low resolution feature map associated with each image frame. Low resolution feature maps are aggregated over time to generate high resolution feature maps.

Abstract: A control device for a loading machine includes a measurement data acquisition unit that acquires measurement data of a measurement device mounted on the loading machine that includes working equipment, a target calculation unit that extracts, from the measurement data, loading target data being measurement data on a loading target on which excavated material excavated by the working equipment is loaded and calculates, based on the loading target data, height data indicating a height of an upper end portion of the loading target and distance data indicating a distance from the loading machine to the loading target, and a working equipment control unit that controls the working equipment based on the height data and the distance data.

Abstract: A system for cross-channel communication for effectors in an electric aircraft is presented. The system may include a flight component of an electric aircraft. The system may include a plurality of effectors, wherein the plurality of effectors may be configured to control the flight component. The system may include a plurality of flight controllers communicatively connected to the plurality of effectors, wherein the plurality of flight controllers may be configured to receive an input, generate a command as a function of the input and transmit the command to the plurality of effectors. The system may include a plurality of networks communicatively connected to the plurality of effectors and the plurality of flight controllers, wherein the plurality of networks may be configured to receive the command from the plurality of flight controllers and transmit the command to the plurality of effectors.

Abstract: A work implement's position is determined. Provided is a system including a work machine, the system comprising: a work machine body; a work implement attached to the work machine body; an imaging device that captures an image of the work implement; and a computer. The computer includes a trained position estimation model. The computer is programmed to obtain the image of the work implement captured by the imaging device and use the trained position estimation model to obtain a position of the work implement estimated from the captured image.

Abstract: A vehicle rescue device includes a communication unit that is communicable with an onboard communication device or a terminal device of a user of each of a plurality of electric vehicles; a receiving unit configured to store, in a storage unit, vehicle notification information received by the communication unit; a determination unit configured to determine, based on the vehicle notification information of an electric vehicle that has requested an electric power supply and the vehicle notification information of an electric vehicle that has accepted a rescue request, whether or not the electric vehicle that has accepted the rescue request can be dispatched to the electric vehicle that has requested the electric power supply; and a management unit configured to direct the electric vehicle that has accepted the rescue request to a location where electric power supply to the electric vehicle that has requested the electric power supply can be performed.

Abstract: A device performs operations including determining a probability that a vulnerable road user (VRU) will continue on a current path (e.g., in connection with controlling an autonomous vehicle). The device receives an image depicting a vulnerable road user (VRU). The device inputs at least a portion of the image into a model, and receives, as output from the model, a plurality of probabilities describing the VRU, each of the probabilities corresponding to a probability that the VRU is in a given state. The device determines, based on at least some of the plurality of probabilities, a probability that the VRU will exhibit a behavior, and outputs the probability that the VRU will exhibit the behavior to a control system.

Abstract: Provided is a control method which includes: obtaining battery information which is information regarding a battery; calculating a present residual value of the battery based on the battery information obtained; calculating a first residual value using a first model which has been trained, the first residual value being a residual value of the battery in a case where a user uses the battery with a tendency identical to a tendency of a plurality of other users; and issuing a token to the user according to an evaluation value calculated based on the present residual value and the first residual value calculated.