Abstract: Disclosed are a neural network training method, a neural network training device and an electronic device. The neural network training method includes: training a first neural network to be trained by using sample data; determining an indicator parameter of the first neural network in a current training process; determining an update manner corresponding to a preset condition if the indicator parameter meets the preset condition; and updating a parameter of a batch normalization layer in the first neural network based on the update manner. In this way, sparsing of a feature map output by a neural network is implemented, thereby reducing an amount of data to be transmitted and improving computation speed of a chip.

Abstract: A system and method including receiving an indication of an occurrence of an event associated with the operation of an autonomous vehicle; determining at least one action to be performed, the at least one action including a data request for a specified subset of stored data associated with the operation of the autonomous vehicle from a memory; generating an output including the specified subset of data; and transmitting the specified subset of data to a remote monitoring system.

Abstract: A method, non-transitory computer readable medium, and system for receiving sensor data from one or more sensors disposed on an autonomous vehicle, determining whether a potentially dangerous event is detected in the environment around the autonomous vehicle, and providing automatically at least a portion of the sensor data to a user associated with the autonomous vehicle. The sensor data may comprise measurements associated with an environment around the autonomous vehicle. The determination of the potentially dangerous event may be based on the sensor data. The portion of the sensor data may be provided automatically in response to determining that the potentially dangerous event is detected.

Abstract: Transportation systems have artificial intelligence including neural networks for recognition and classification of objects and behavior including natural language processing and computer vision systems. The transportation systems involve sets of complex chemical processes, mechanical systems, and interactions with behaviors of operators. System-level interactions and behaviors are classified, predicted and optimized using neural networks and other artificial intelligence systems through selective deployment, as well as hybrids and combinations of the artificial intelligence systems, neural networks, expert systems, cognitive systems, genetic algorithms and deep learning.

Abstract: A vehicle includes an ADK attachable to and removable from a vehicle main body, the ADK issuing an instruction for autonomous driving, a VP including a plurality of functional units that perform a plurality of prescribed functions of the vehicle main body, and a VCIB that issues a control instruction to the functional units in accordance with an instruction from the ADK. One of the plurality of functional units is a steering system that steers the vehicle main body. The steering system specifies a limit value of a steering rate in accordance with a prescribed reference and transmits the specified limit value to the ADK through the VCIB. The ADK calculates a target steering angle to satisfy the limit value received from the steering system and transmits an instruction for the calculated steering angle to the steering system through the VCIB.

Abstract: A machine learning method performs training of values of model parameters forming a machine learning model, and is performed in a machine learning system including a vehicle having the machine learning model and a server able to communicate with the vehicle. The machine learning method includes: detecting, by the server, a current processing load of the server; determining, by the server, processing amounts of training respectively performed by the server and the vehicle, based on the processing load; performing, by the server, training of the values of the model parameters in accordance with the determined processing amount in the server; and performing, by the vehicle, training of the values of the model parameters in accordance with the determined processing amount in the vehicle. The server decreases a processing amount at the server when the processing load is relatively high compared to when it is relatively low.

Abstract: A method may include obtaining sensor data that include a plurality of sensor returns from an environment of an autonomous vehicle. A first set of features may be extracted from the sensor data. The first set of features may be processed with a machine learning model to generate, for at least a subset of the plurality of sensor returns, a first output that classifies a respective sensor return as corresponding to an object or non-object and a second output that indicates a property of the object. The sensor returns classified as corresponding to objects may be compared to a plurality of pre-classified objects to generate one or more generic object classifications. The autonomous vehicle may be controlled based at least in part on the one or more generic object classifications.

Abstract: A controller in a vehicle includes an obtaining unit that obtains facility information on a charging facility that can charge a power storage mounted on the vehicle, the facility information including position information and utility information in association with each other, the position information indicating a position of the charging facility, the utility information indicating an electric utility that manages the charging facility. The controller further includes at least one of a first notification unit and a second notification unit. The first notification unit causes a notification apparatus to give first information that indicates an electric utility, by using the facility information obtained by the obtaining unit. The second notification unit causes the notification apparatus to give second information that indicates a position of a charging facility, by using the facility information obtained by the obtaining unit.

Abstract: Systems and methods for route management are disclosed. A system for use with a communication network includes an electronic logging device, a global positioning device, and a server. The server communicates via a communication network and to access vehicle data and global positioning data via the communication network. The server includes a processor(s) and a non-transitory computer-readable medium storing instructions thereon, that when executed by the one or more processors, cause the processor(s) to: analyze the vehicle data to identify start-and-stop events of the vehicle; analyze each of the start-and-stop events with respect to criteria to identify which of the start-and-stop events is associated with an actual visit event; identify the locations and the times from the global positioning data that correspond to the actual visit events; and correlate the locations and the times of the vehicle with the respective ones of the actual visit events.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for unmanned aerial vehicle authorization and geofence envelope determination. One of the methods includes determining, by an electronic system in an Unmanned Aerial Vehicle (UAV), an estimated fuel remaining in the UAV. An estimated fuel consumption of the UAV is determined. Estimated information associated with wind affecting the UAV is determined using information obtained from sensors included in the UAV. Estimated flights times remaining for a current path, and one or more alternative flight paths, are determined using the determined estimated fuel remaining, determined estimated fuel consumption, determined information associated wind, and information describing each flight path. In response to the electronic system determining that the estimated fuel remaining, after completion of the current flight path, would be below a first threshold, an alternative flight path is selected.

Abstract: Techniques are described for an autonomous vehicle to provide the autonomous vehicle's health-related information, identification information, and/or inspection information to a device that may be used by law enforcement or a government agency or a third-party so that the autonomous vehicle can comply with government regulations and can continue to operate on the road.

Abstract: A flight control computer (FCC) for a rotorcraft includes a processor and a non-transitory computer-readable storage medium storing a program to be executed by the processor, with the program including instructions for providing main rotor overspeed protection. The instructions for providing the main rotor overspeed protection include instructions for monitoring sensor signals indicating a main rotor RPM, determining a target operating parameter, determining one or more flight parameters in response to a relationship between the main rotor RPM and the target operating parameter indicating a main rotor overspeed condition. Determining the one or more flight parameters includes determining a setting for a flight control device of the rotorcraft that changes the main rotor RPM, controlling positioning of a pilot control according to the flight parameters, and controlling the flight control device of the rotorcraft according to positioning of the pilot control.

Abstract: The work state identifying unit identifies a work state of a work machine disposed in a construction site at each time point and a work state of a transport vehicle traveling at the construction site at each time point. The time chart generation unit that generates a time chart representing the work state of the work machine at each time point and a time chart representing the work state of the transport vehicle at each time point on the basis of the identified work states. The output control unit that outputs the time charts on an identical screen with a time axis as a common axis.

Abstract: A method and a system determine a change of state of an autonomous device, such as an autonomous vehicle. A plurality of performance parameter values obtained by monitoring at least one performance parameter during the autonomous operation of the device is received. A performance quantity quantifying the quality of autonomous operation of the device, in particular the quality of driving of the autonomous vehicle, is determined based on the obtained performance parameter values and information associated with a flux of software and/or hardware related to the autonomous operation of the device. Further, a change of state value for the device is determined based on the performance quantity.

Abstract: A vehicle system includes a first vehicle and a second vehicle. The first vehicle includes an information storage configured to store vehicle characteristic information representing a vehicle characteristic, and an information output unit configured to output the stored vehicle characteristic information to a predetermined storage medium. The second vehicle includes an information input unit configured to input vehicle characteristic information from the storage medium, and a vehicle characteristic setter configured to set a vehicle characteristic represented by the input vehicle characteristic information in the second vehicle.

Abstract: A vehicle includes an ADK that creates a driving plan, a VP that carries out vehicle control in accordance with various commands from the ADK, and a vehicle control interface that interfaces between the VP and the ADK. A power supply structure for the ADK is provided independently of a power supply structure for the VP.

Abstract: Some embodiments provide a navigation application with a novel declutter navigation mode. In some embodiments, the navigation application has a declutter control that when selected, directs the navigation application to simplify a navigation presentation by removing or de-emphasizing non-essential items that are displayed in the navigation presentation. In some embodiments, the declutter control is a mode-selecting control that allows the navigation presentation to toggle between normal first navigation presentation and a simplified second navigation presentation, which below is also referred to as a decluttered navigation presentation. During normal mode operation, the navigation presentation of some embodiments provides (1) a representation of the navigated route, (2) representations of the roads along the navigated route, (3) representation of major and minor roads that intersect or are near the navigated route, and (4) representations of buildings and other objects in the navigated scene.

Abstract: Provided are methods for vehicle scenario mining for machine learning methods, which can include determining a set of attributes associated with an untested scenario for which a machine learning model of an autonomous vehicle is to make planned movements. The method includes searching a scenario database for the untested scenario based on the set of attributes. The scenario database includes a plurality of datasets representative of data received from an autonomous vehicle sensor system in which the plurality of datasets is marked with at least one attribute of the set of attributes. The method further includes obtaining the untested scenario from the scenario database for inputting into the machine learning model for training the machine learning model. The machine learning model is configured to make the planned movements for the autonomous vehicle. Systems and computer program products are also provided.

Abstract: A control device is provided for a wheel-monitoring system of a vehicle which is equipped with vehicle wheels. At least one of the vehicle wheels is equipped with an electronic wheel unit, arranged thereon, for detecting at least one wheel operating parameter of the respective vehicle wheel for transmitting wheel operating data to the control device. The control device makes available an abnormality message in the event of an abnormality which is determined on the basis of the transmitted wheel operating data. The control device also takes into account position data relating to a current position of the vehicle for the determination of the abnormality.

Abstract: According to various aspects, a controller includes one or more processors configured to: determine when a predicted event occurs, at which a velocity of a vehicle is changed; and provide an instruction for a reorientation of one or more seats of the vehicle based on when the predicted event occurs.