Abstract: A first sensor performance level is used during driving where a vehicle is allowed to drive with a first maximum allowed speed, and while utilizing the first sensor performance level, simultaneously monitoring a rate of false positive object detections for a second sensor performance level which is associated with a second maximum allowed speed which is higher than the first maximum allowed speed and which is a less restrictive sensor performance level. When the rate of false positive object detections for the second sensor performance level is below a first false positive error threshold, a sensor performance level that is less restrictive than the first sensor performance level is used, and is associated with a higher maximum allowed speed equal to or lower than the second maximum allowed speed.

Abstract: A system receives scene data from a plurality of multi-access edge computing (MEC) nodes, the scene data for each MEC node indicating data about a scene covered by sensors of a given one of the MEC nodes. The system determines one or more areas of interest included in at least one of the scenes and, for at least one of the one or more areas of interest that includes indicated data from at least two of the MEC nodes, determines whether at least one of the at least two MEC nodes has preferential data. Additionally, the system utilizes the data from the at least two MEC nodes to execute a vehicle maneuver autonomously, in accordance with parameters defined for data utilization that dictate utilization based on the preferential data determination.

Abstract: A collision avoidance system is provided for an aircraft that includes a fuselage and a plurality of aircraft surfaces coupled to and extending from the fuselage. The collision avoidance system includes a light engine that is mounted on at least one of the aircraft surfaces and is configured, upon being energized, to emit a light beam in one or more directions. The light engine is further configured such that, when the light beam is emitted, it creates a light plane that is disposed at a predetermined angle relative to a ground surface on which the aircraft is located and extends, from the aircraft surface, along the ground surface thereby producing an elongated light pattern on the ground surface and on any obstacle that the light plane encounters.

Abstract: Described are example systems and methods generally directed to systems and methods for determining and managing flight planning and operations for unmanned vehicles, such as unmanned aerial vehicles (UAVs). The described systems and methods can facilitate generation of a risk-weighted model of an environment in which vehicles may operate to facilitate determination of a total cumulative risk associated with certain flight paths between an origin and a destination in the environment. The total cumulative risk associated with a flight path can include a risk associated risks present on the ground along the flight path, as well as risks associated with the vehicle performing the flight. The total cumulative risk for a given flight path can be used to identify flight paths presenting the lowest relative risk and can also be compared against a risk threshold to determine whether the total cumulative risk associated with the flight path is within an acceptable range.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for intervention behavior prediction. A method includes receiving data characterizing a scene that includes a first agent and a second agent and receiving intervention data specifying a planned intervention to be performed by the second agent. A conditional behavior prediction output that assigns, to each of a plurality of possible future behaviors, (i) a respective conditional likelihood that the first agent performs the possible future behavior given that the second agent performs the planned intervention and (ii) a predicted value of a confounder variable for the possible future behavior is-generated using a conditional behavior prediction model.

Abstract: When the driving mode is the automatic driving mode, the vehicle control device executes the first hard protection control according to the component-related parameter representing the state or the operating environment of the in-vehicle component, and when the driving mode is the manual driving mode, the vehicle control device executes the second hard protection control having a higher protection performance of the in-vehicle component than the first hard protection control according to the component-related parameter.

Abstract: Provided are a method for discharging a first battery and a second battery included in a mobile robot, the method including determining that the mobile robot is to begin driving, determining which of a plurality of predetermined intervals a charge amount of the first battery and a charge amount of the second battery at a time point of the determination fall within, respectively, determining an interval to discharge the first battery based on which intervals the charge amount of the first battery and the charge amount of the second battery fall within, and performing a switching operation to begin discharging of the second battery after the first battery has completed discharging in the determined interval, a mobile robot performing the method, and a computer-readable recording medium having a computer program for executing the method stored thereon.

Abstract: A driving handover control device includes a memory and a processor coupled to the memory. In a case in which driving is handed over from a first state in which a vehicle travels in accordance with instruction from a first remote operator of the vehicle to a second state in which the vehicle travels in accordance with instruction from a second remote operator who is different from the first remote operator, the processor implements a transition from the first state to a third state in which the vehicle travels autonomously without instruction from the first remote operator or the second remote operator, and, after the transition from the first state to the third state, implements a transition from the third state to the second state.

Abstract: Systems and methods are directed to generating behavioral predictions in reaction to autonomous vehicle movement. In one example, a computer-implemented method includes obtaining, by a computing system, local scene data associated with an environment external to an autonomous vehicle, the local scene data including actor data for an actor in the environment external to the autonomous vehicle. The method includes extracting, by the computing system and from the local scene data, one or more actor prediction parameters for the actor using a machine-learned parameter extraction model. The method includes determining, by the computing system, a candidate motion plan for the autonomous vehicle. The method includes generating, by the computing system and using a machine-learned prediction model, a reactive prediction for the actor based at least in part on the one or more actor prediction parameters and the candidate motion plan.

Abstract: Aspects of the present invention relate to a control system and method for controlling a state of charge of energy storage means of a hybrid electric vehicle, the control system comprising one or more electronic controllers, the one or more electronic controllers configured to: receive destination data; determine a route to be travelled by the vehicle, the route comprising one or more characteristics, in dependence on the received destination data; and control the state of charge of the energy storage means in dependence on the route to allow the vehicle to travel an end portion of the route in an electric-only mode.

Abstract: A method of calibrating an advanced driver assistance system (ADAS) for a vehicle comprises: receiving first information by a mobile device that has a camera and a light detection and ranging (LiDAR) device, the first information comprising a three-dimensional (3D) specification of physical dimensions for the vehicle having the ADAS; scanning, by the mobile device, the vehicle and a physical target for the ADAS, the scanning performed with the camera and the LiDAR device after receiving the first information, the scanning generating frame data; tracking, by the mobile device, the vehicle in the frame data using the first information; generating, by the mobile device, an output indicating whether the physical target is positioned at a target location for the ADAS; and initiating, after the output is generated, a calibration process of the ADAS that uses the physical target.

Abstract: Given that an intersection point of a straight line, which connects a relatively moving body and an eyeball reference position of a driver of a vehicle, and a virtual surface, which includes a virtual display region and is wider than the virtual display region, is defined as a first intersection point, and an intersection point between the virtual display region and a straight line, which connects the eyeball reference position and an AR image, is defined as a second intersection point, a position of the second intersection point is controlled such that a second distance, which is a distance between the first intersection point and the second intersection point, is longer when a first distance, which is a distance between the relatively moving body and the vehicle, is longer than a predetermined value, than when the first distance is the predetermined value.

Abstract: Techniques for identifying road segments associated with an object trajectory are discussed herein. A computing device can implement a model that extracts points from an object trajectory and identifies road segments along a path between the extracted points. The model can determine a set of road segments for the path based on searching a graph. The graph can comprise nodes to represent different road segments, and a graph search algorithm can output road segments representing a shortest path between the nodes associated with the extracted points. The road segments can be used by a vehicle computing device for predicting vehicle actions to control a vehicle.

Abstract: In an aspect, a method for monitoring recurrent aircraft faults is disclosed. The method comprises (a) retrieving a plurality of data entries from an aircraft. The plurality of data entries may comprise semantic information about a plurality of recurrent aircraft faults. The method also comprises (b) using a trained natural language processing algorithm, establishing a plurality of pairwise relations of the plurality of data entries, a pairwise relation corresponding to a recurrent fault of the plurality of recurrent aircraft faults. The method also comprises (c) generating one or more alerts from the plurality of pairwise relations. Finally, the method comprises (d) presenting the one or more alerts in a user interface.

Abstract: A vehicle includes an autonomous driving system and a vehicle platform that controls the vehicle according to commands from the automated driving system. The autonomous driving system is configured to send to the vehicle platform commands for autonomous driving, which is autonomous driving of the vehicle alone, and commands for remote driving, which is automatic driving based on signals from outside the vehicle. The vehicle is configured to be operable in an automatic mode, in which the vehicle platform is under control of an autonomous driving system, and in a manual mode, in which the vehicle is under control of a driver. When the vehicle is not in remote operation, switching to remote operation is allowed in manual mode and prohibited in automatic mode.

Abstract: The present invention provides a vehicle control apparatus (10) including: an acquisition unit (11) that acquires internal situation information indicating a situation inside a vehicle; a detection unit (12) that detects a person who satisfies a predetermined condition inside the vehicle, based on the internal situation information; a decision unit (13) that decides a driving mode of the vehicle, based on whether the person who satisfies the predetermined condition is detected; a processing unit (14) that performs processing of the decided driving mode; and a notification unit (15) that notifies an outside of the vehicle of the decided driving mode.

Abstract: A safety system for an autonomous electronic vehicle having a body and a platform. The safety system includes at least one mechanical connection unit and a safety control module. The mechanical connection unit connects the body to the platform, and is transitionable between a first state, in which the body is attached to the platform at the mechanical connection unit, and a second state, in which the body is released from the platform at the mechanical connection unit. The safety control module is programmed to prompt the mechanical connection unit to transition from the first state to the second state under circumstances of an imminent collision event. In some embodiments, the safety control module is programmed to determine a safety path for passengers within the body and/or others in the collision zone based on conditions surrounding the vehicle.

Abstract: Managing a vehicle body including computing an efficiency value of a monitoring target, the monitoring target being the power train or a part or a subsystem of the power train, on the basis of information about the vehicle body, the information being sensed by a sensor provided to the vehicle body. An output terminal that outputs the efficiency value of the monitoring target. Determining whether a load parameter is larger than a load determination value set in advance, and computing the efficiency value of the monitoring target on the basis of input energy and output energy of the monitoring target on condition that the load parameter be larger than the load determination value, and recording the computed efficiency value of the monitoring target.

Abstract: Systems and techniques for whether to associate predicted trajectories of objects detected in an environment with candidate vehicle trajectories are described. A vehicle traversing an environment may have several candidate actions that may be used to control the vehicle. Predicted object trajectories may be excluded from further processing based on a relevancy score determination. Various factors may be evaluated to determine the relevancy score associated with a predicted object trajectory and candidate vehicle action pair that indicated the impact of the predicted object trajectory and candidate vehicle action. A resultant trajectory may be determined using only those relevant predicted object trajectories.

Abstract: Systems and methods for terminal procedure prediction for flight planning include obtaining, at a processor, input data corresponding to an upcoming flight of an aircraft; obtaining, at the processor, predicted data corresponding to the upcoming flight; and processing, at the processor, the input data and the predicted data to obtain a terminal procedure prediction associated with the upcoming flight, the terminal procedure prediction at least partially based on flight plans of historical flights having conditions similar to the input data and the predicted data.