Abstract: Systems and methods for predicting actions of an actor before entering a conflicted area are disclosed. The methods may include detecting the presence of an actor in an environment of an autonomous vehicle while the autonomous vehicle and the actor are approaching the conflicted area, determining whether the autonomous vehicle has precedence over the actor for traversing the conflicted area, assigning a kinematic target to the moving object that requires the moving object to come to a stop at an yield point before entering the conflicted area if the autonomous vehicle has precedence over the actor, determining whether a plurality of forecasted trajectories for the actor need to be generated, and controlling movement of the autonomous vehicle to traverse the conflicted area accordingly.

Abstract: A method, apparatus and computer program product are provided for automatically identify wrong-way driven vehicles in real-time on a roadway. Methods may include: receiving an image from at least one image sensor captured at a location; processing the image using a computer vision model to detect features within the image; identifying, using the computer vision model, a wrong-way driven vehicle in the image; incrementing a confidence value for detection of the wrong-way driven vehicle; and generating an alert indicating the presence of the wrong-way driven vehicle at the location in response to the confidence value satisfying a predetermined value.

Abstract: A method and apparatus for providing distributed fleet communications between aircraft including decentralized location tracking, weather data, and fleet health is used to determine actual aircraft position, better weather data from multiple sources, and health data to help with logistical calculations and increase efficiencies. The communication is a distributed communication network using blockchains wherein the block includes a data, a hash and a prior hash, determining, by a processor, a validity of the block in response to a blockchain register stored on a memory, the hash and the prior hash, determining, by the processor. The processor is configured to generate a record to be added to the local copy of the blockchain ledger stored in the memory, then send an update to the fleet blockchain to be added as a valid record to be stored and used by the fleet or other trusted individual operators.

Abstract: The present disclosure is directed to a novel system for a self-constructing deep neural network. The system may comprise a hybrid logic library which contains the building structures needed to construct the neural network, which may include both traditional logic and memory structures as well as learning structures. In constructing the neural network from library structures, the system may use an algorithm to iteratively improve the performance of the neural network. In this way, the system may provide a way to generate complex neural networks that become increasingly optimized over time.

Abstract: Vertical resolution and/or vertical accuracy of terrain elevation data near an aircraft runway is adjusted by obtaining local terrain data, yielding a first elevation value for a query location. A processor receptive of the first elevation value computes plane equations based on a predetermined standard model adapted to geometrically conform to the aircraft runway, yielding a second elevation value for the query location. The processor selectively uses the first and second elevation values to generate an adjusted elevation value that is supplied to a terrain avoidance and warning system.

Abstract: The present disclosure relates to an image processing method and apparatus based on a super network, and a computer storage medium. The method can include that a pretrained backbone network is merged with a rear end of a target detection network to obtain a merged super network, the merged super network is trained, Neural Architecture Search (NAS) is performed based on the trained super network to obtain a target detection neural architecture, and an image to be processed is processed by using the target detection neural architecture to obtain an image processing result.

Abstract: The invention relates to a method of controlling a heavy-duty vehicle in a slope when the vehicle has come to a standstill due to service brakes of the vehicle having applied a service brake force, the method comprising determining a total brake force required for maintaining the vehicle at standstill, activating at least one park brake for providing a park brake force, gradually increasing the park brake force, and, while the park brake force is gradually increased, gradually reducing the service brake force while maintaining the sum of the service brake force and the park brake force at least equal to the determined total brake force.

Abstract: A method may determine transformation parameters for a transformation of a position of a vehicle between a first coordinate system and a second coordinate system. In the method, a trajectory may be traveled with the vehicle in a step. In another step, the positions of the vehicle while traveling the trajectory may be acquired in the first coordinate system with a first position detection system, and in the second coordinate system with a second position detection system. In a further step, transformation parameters between the coordinate systems may be derived based on the positions of the vehicle acquired in the coordinate systems, and based on at least one geometric parameter of the trajectory.

Abstract: A method of optimizing flights of a fleet of aircraft is provided. The method includes accessing flight plans for flights of a fleet of aircraft through an air transportation network, and applying the flight plans to a reinforcement learning model configured to determine maneuvers for each aircraft on a respective flight that achieves a respective maximum cumulative value of an operational efficiency metric across the flights of the fleet of aircraft, one or more of the maneuvers constituting a deviation from a respective flight plan. A comparison of respective maximum cumulative values of the operational efficiency metric is performed for the aircraft of the fleet of aircraft, one of the aircraft is selected based on the comparison, and a notification of the deviation from the respective flight plan is sent to the one of the aircraft.

Abstract: A method for the predictive assessment of a current driving situation of a vehicle, in particular utility vehicle, includes determining currently present driving situation information, wherein the driving situation information characterizes the current driving situation of the vehicle. The method includes specifying the driving situation information to a neural algorithm, wherein the neural algorithm assigns, in the manner of a trained neural network, a driving situation category to the currently present driving situation information. The respective driving situation category is based on a predicted driving situation. The neural algorithm determines the predicted driving situation in accordance with the current driving situation and the predicted driving situation indicates a driving situation of the vehicle which will develop in future from the current driving situation. The method includes outputting an output value characterizing the driving situation category, as an assessment result.

Abstract: A vehicle is a vehicle on which an ADK is mountable. The vehicle includes: a VP that controls the vehicle in accordance with an instruction from the ADK; and a VCIB that serves as an interface between the ADK and the VP. The VP outputs a brake pedal position signal in accordance with an amount of depression of a brake pedal by a driver, and outputs a brake pedal intervention signal, to the ADK through the VCIB. The brake pedal intervention signal indicates that the brake pedal is depressed, when the brake pedal position signal indicates that the amount of depression is larger than a threshold value, and indicates beyond autonomy deceleration of the vehicle, when a deceleration request in accordance with the amount of depression is higher than a system deceleration request.

Abstract: Sensors coupled to a first vehicle are used to measure sensor measurements. Based on the sensor measurements, the first vehicle identifies a risk to the first vehicle and/or to a second vehicle near the first vehicle, for example based on a distance between the first and second vehicle being unsafely low. The first vehicle generates an alert based on the risk and outputs the alert toward the second vehicle, for example visually through a screen and/or audibly using speakers, to warn an operator of the second vehicle about the risk.

Abstract: A vehicle safety system for helping to protect a vehicle occupant in the event of a frontal collision includes a controller, one or more crash sensors for sensing a frontal collision, and an active sensor for detecting objects in the path of the vehicle. The controller is configured to implement crash discrimination metrics that detect the occurrence of a frontal collision in response to signals received from the crash sensors. The crash discrimination metrics implement thresholds for determining whether the signals received from the crash sensors indicate the occurrence of a frontal collision. The controller is configured to implement an algorithm that uses information obtained from the active sensor to detect an object in the path of the vehicle and to select the thresholds implemented in the crash discrimination metrics in response to detecting the object.

Abstract: A method for operating a vehicle comprising at least one functional module, two or more drive modules, which are: autonomously operated, individually associated with a set of energy parameters, a pair of wheels, an electrical motor operating the wheels, and an interface releasably connected to an interface on the functional module, and wherein one drive module has a gear ratio different from any gear ratio of any other drive module. The method comprises: obtaining route information describing a planned route of the vehicle; determining a distribution of a requested driving torque between the respective at least one electrical motors of the two or more drive modules for operating the vehicle along the route based on the route information and the individual sets of energy parameters in order to meet energy criteria; and controlling the two or more drive modules to produce the requested driving torque, in accordance with the determined distribution.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that control devices in an aquaculture environment. One of the methods includes determining a particular objective for a robot that is operating in an aquaculture environment and determining one or more sensed conditions that are associated with the aquaculture environment. The particular objective is provided to an anti-fish-startling model evaluation engine that is configured to output actions, for a given objective, that accomplish the given objective while reducing a startling effect on nearby fish. Based on providing the particular objective to the anti-fish-startling model evaluation engine, one or more particular actions for accomplishing the particular objective are determined. The one or more particular actions are transmitted to another device.

Abstract: A method for machine learning includes extracting features from a training set of inputs, wherein each input generates a feature set and each the feature set forms a neural network key. The method includes arranging the keys in an in-memory computational layer such that the distance between any pair of keys corresponding to similar inputs is as close as possible while keys for a pair of dissimilar inputs have differing values as far apart as possible, wherein each of the keys has a fixed size. The method also includes searching through the dataset using an in-memory K-nearest neighbor unit to find K keys similar to a query key, the searching occurring in a constant amount of time as a function of the fixed size and irrespective of a size of the dataset.

Abstract: A system and method are provided for assisted positioning of a loading container of a transport vehicle with respect to a work machine during material loading operations. A target loading position is determined for at least the loading container relative to at least an undercarriage of the work machine. The target loading position may be based on user input, and/or automatically determined based on a selected swing angle or range for an implement (e.g., boom assembly), a distance from the work machine, etc. Output signals are generated corresponding to the target loading position, and optionally to a determined route of travel corresponding to a current position of the transport vehicle and the target loading position for at least the loading container.

Abstract: A control apparatus includes a communication unit configured to receive motion data indicating motion of at least one user outside a vehicle that moves along a route including at least one road, and a controller configured to make a boarding determination of determining whether the at least one user will board the vehicle based on the motion data received by the communication unit and execute, upon determining in the boarding determination that the at least one user will board the vehicle, control for opening a door of the vehicle.

Abstract: To provide an other vehicle behavior prediction apparatus, an other vehicle behavior prediction method, and an automatic driving system which can determine the presence absence of the lane change of the other vehicle with good accuracy, regardless of the change of road shape. An other vehicle behavior prediction apparatus, including: a periphery detector that detects other vehicle which exists around an own vehicle; a road shape detector that detects a road shape where the other vehicle is located; and a lane change predictor that predicts presence or absence of a lane change of the other vehicle based on a detection result of the other vehicle, and changes a determination value which is used when predicting the presence or absence of the lane change of the other vehicle, based on the road shape where the other vehicle is located.

Abstract: The present technology relates to a vehicle control apparatus and a vehicle control method that allow safer automated driving. The vehicle control apparatus includes a driver monitoring section and a penalty application section. The driver monitoring section detects a driving intervention level indicating an extent to which the driver intervenes in driving of a vehicle. The penalty application section applies a penalty disadvantageous to the driver in the case where the driving intervention level is insufficient. The present technology is applicable, for example, to a vehicle control apparatus that controls automated driving.