Abstract: Thrust values for motors in an aircraft are generated where each flight controller in a plurality of flight controllers generates a thrust value for each motor in a plurality of motors using an optimization problem with a single solution. Each flight controller in the plurality of flight controllers passes one of the generated thrust values to a corresponding motor in the plurality of motors, where other generated thrust values for that flight controller terminate at that flight controller. The plurality of motors perform the passed thrust values.

Abstract: The invention discloses an unmanned surface vessel (USV) formation path-following method based on deep reinforcement learning, which includes USV navigation environment exploration, reward function design, formation pattern keeping, a random braking mechanism and path following, wherein the USV navigation environment exploration is realized adopting simultaneous exploration by multiple underactuated USVs to extract environmental information, the reward function design includes the design of a formation pattern composition and a path following error, the path following controls USVs to move along a preset path by a leader-follower formation control strategy, and path following of all USVs in a formation is realized by constantly updating positions of the USVs.

Abstract: In a target track generation apparatus, a subject vehicle reference preceding vehicle position calculator calculates a point group of subject vehicle reference preceding vehicle positions representing a history of a relative position of a preceding vehicle in a coordinate system using a current position of a subject vehicle as a reference. A target track generator generates a target track of the subject vehicle, based on the point group of the subject vehicle reference preceding vehicle positions. A correction target track generator generates a correction target track obtained by correcting the target track, based on the point group of the subject vehicle reference preceding vehicle positions or the target track, when it is determined that correction of the target track is necessary.

Abstract: Embodiments of the present disclosure set forth a computer-implemented method comprising receiving, from at least one sensor, sensor data associated with an environment, generating, based on the sensor data, a set of lane change data values associated with positions of at least two vehicles relative to a first lane position in the environment, determining, based on the set of lane change data values, a collision risk value associated with the at least two vehicles attempting to occupy the first lane position, and generating, based on the collision risk value, an output signal to a first vehicle included in the at least two vehicles.

Abstract: An in-vehicle stable platform system employing active suspension and a control method thereof is provided. The system includes a vehicle body, an in-vehicle stable platform, an inertial measurement device, an electronic control device, a servo controller set, multiple wheels, and suspension servo actuation cylinders and displacement sensors respectively corresponding to the wheels. The wheels are divided into three groups, which form three support points. The heights of the three support points are controlled to control orientation of the vehicle body. An amount of extension/retraction of the suspension servo actuation cylinders required to cause the in-vehicle stable platform to return to a horizontal level is calculated according to a measured pitch angle and a roll angle of the in-vehicle stable platform, and when a vehicle travels on an uneven road, the extension/retraction of each suspension servo actuation cylinder is controlled to cause the in-vehicle stable platform to be horizontal.

Abstract: The disclosure relates to a method for actuating an electrical drive of a trailer vehicle with a towing vehicle. According to an embodiment, the method include the steps of: determining a current mass of the towing vehicle; determining a current drive force of the towing vehicle; determining an acceleration demand in dependence upon the current mass and the current drive force; and, actuating the electric drive via an actuating signal in dependence upon the acceleration demand. The disclosure also relates to a control device for executing the method, a towing vehicle, a trailer vehicle and a semi-trailer truck.

Abstract: The invention relates to a payload frame for deploying a payload underwater. The payload frame includes at least three lead screws, each lead screw connected near a top end of the lead screw to the payload by a corresponding spherical bearing; at least three motors, each motor connected to a bottom end of one of the lead screws, the motor to rotate the lead screw through the corresponding spherical bearing; at least three feet, each foot attached to one of the motors, the feet to support and secure the payload frame on a water body bed; an accelerometer attached to the payload, the accelerometer to measure gravity vectors of the payload; and a microcontroller connected to the accelerometer and the motors. The microcontroller to receive the gravity vectors from the accelerometer and control each of the motors based on the gravity vectors to position the payload in a target orientation.

Abstract: A method for controlling propulsion of a marine vessel powered by a marine propulsion system including a plurality of propulsion devices includes operating at least one proximity sensor to determine a relative position of the marine vessel with respect to an object, the at least one proximity sensor having a field of view (FOV), identifying a trigger condition for expanding the FOV of the at least one proximity sensor, and determining whether the object will be sufficiently captured based on recent vessel angle data of the marine vessel. Upon determining that the object will not be sufficiently captured, thrust and/or steering position of at least one of the plurality of propulsion devices is controlled to expand the FOV of the at least one proximity sensor by inducing a roll movement or a pitch movement of the marine vessel.

Abstract: A method of solving a graph simultaneous localization and mapping (graph SLAM) for HD maps using a computing system includes partitioning a graph into a plurality of subgraphs, each of the subgraphs having all of the vertices of the graph and a subset of the edges of the graph. Constrained and non-constrained vertices are defined for the subgraphs. An alternating direction method of multipliers (ADMM) formulation for Graph SLAM is defined using the partitioned graph. A distributed Graph SLAM algorithm is then defined in terms of the constrained and non-constrained vertices based on the ADMM formulation. The distributed Graph SLAM algorithm is then used to solve the Graph SLAM problem for HD maps.

Abstract: The present application discloses an improved transportation matching system, and corresponding methods and computer-readable media. According to disclosed embodiments, a transportation matching system trains a predictive request model to generate a metric predicted to trigger an increase in transportation provider activity within the geographic area for a given time period. Furthermore, the system determines a predicted gap between expected request activity and expected transportation provider activity for the geographic area during a future time period, utilizes the predictive request model and the predicted gap to generate a metric for the geographic area, and generates an interactive map associated with a customized schedule for the geographic area and the future time period based on the generated metric.

Abstract: Systems and methods for detecting and classifying objects proximate to an autonomous vehicle can include a sensor system and a vehicle computing system. The sensor system includes at least one LIDAR system configured to transmit ranging signals relative to the autonomous vehicle and to generate LIDAR data. The vehicle computing system receives the LIDAR data from the sensor system. The vehicle computing system also determines at least a range-view representation of the LIDAR data and a top-view representation of the LIDAR data, wherein the range-view representation contains a fewer number of total data points than the top-view representation. The vehicle computing system further detects objects of interest in the range-view representation of the LIDAR data and generates a bounding shape for each of the detected objects of interest in the top-view representation of the LIDAR data.

Abstract: The present application discloses is a scheduling method and system for fully autonomous waterborne inter terminal transportation, and belongs to the field of transportation. The method includes: establishing a dynamic scheduling model for waterborne Autonomous guided vessels (wAGVs); quickly inserting the dynamically arriving transportation tasks into all the existing wAGV paths, calculating the insertion cost and selecting the path and position with the lowest insertion cost to obtain updated initial paths; improving the initial path using a heuristic algorithm based on tabu search to obtain quasi-optimal wAGV paths; executing the scheduling wAGV paths.

Abstract: The invention provides systems and methods for an Intelligent Road Infrastructure System (IRIS), which facilitates vehicle operations and control for connected automated vehicle highway (CAVH) systems. IRIS systems and methods provide vehicles with individually customized information and real-time control instructions for vehicle to fulfill the driving tasks such as car following, lane changing, and route guidance. IRIS systems and methods also manage transportation operations and management services for both freeways and urban arterials. In some embodiments, the IRIS comprises or consists of one of more of the following physical subsystems: (1) Roadside unit (RSU) network, (2) Traffic Control Unit (TCU) and Traffic Control Center (TCC) network, (3) vehicle onboard unit (OBU), (4) traffic operations centers (TOCs), and (5) cloud information and computing services.

Abstract: A method for setting a working point of a slip controller for a wheel of a vehicle. Upon activating the slip controller, a torque at the wheel is controlled on the basis of the working point using a slip at the wheel, wherein the torque is monitored and a value of the working point is set to a previous value of the torque if the slip satisfies a condition.

Abstract: Hybrid electric propulsion systems includes a combustion engine and an electric motor. The hybrid electric propulsion systems may include or utilize a non-transitory computer-readable medium comprising computer-executable instructions, which when executed by a processor associated with the hybrid electric propulsion system, cause the processor to perform a method that includes determining an occurrence of a thrust asymmetry in the hybrid electric propulsion system, and controlling the electric motor to decrease an efficiency of the electric motor for a transient time period sufficient to reduce a torque output of the combustion engine to match an electrical load on the combustion engine.

Abstract: Embodiments discussed herein refer to systems and methods that compensate for debris and water obfuscation that affect operation of LiDAR systems. A debris management system can direct air and/or fluid over a portion of the LiDAR system to remove any debris or water.

Abstract: An apparatus, method, and computer readable medium related to determining the position of a device, for example determining the pose of a camera. Varying embodiments discuss the use of sensors and captured images to construct an environment property map, which provides reference information in the form of environment properties that are associated with positions, such as camera poses. Embodiments of the disclosure discuss using the environment property map online (e.g. in real time) in order to determine the position of a device. In some embodiments, the environment property map provides a coarse position that is used to refine or limit the necessary work for determining a more precise position.

Abstract: A vegetative health mapping system which creates two- or three-dimensional maps and associates moisture content, soil density, ambient light, surface temperature, and/or additional indications of vegetative health with the map. Moisture content is inferred using radar return signals of near-field and/or far-field radar. By tuning various parameters of the one or more radar (e.g. frequency, focus, power), additional data may be associated with the map from subterranean features (such as rocks, soil density, sprinklers, etc.). Additional sensors (camera(s), lidar, IMU, GPS, etc.) may be fused with radar returns to generate maps having associated moisture content, surface temperature, ambient light levels, additional indications of vegetative health (as may be determined by machine learned algorithms), etc. Such vegetative health maps may be provided to a user who, in turn, may indicate additional areas for the vegetative health device to scan or otherwise used to recommend and/or perform treatments.

Abstract: The technology relates to detecting and responding to processions. For instance, sensor data identifying two or more objects in an environment of a vehicle may be received. The two or more objects may be determined to be disobeying a predetermined rule in a same way. Based on the determination that the two or more objects are disobeying a predetermined rule, that the two or more objects are involved in a procession may be determined. The vehicle may then be controlled autonomously in order to respond to the procession based on the determination that the two or more objects are involved in a procession.

Abstract: A system and method for instance-level lane detection for autonomous vehicle control are disclosed.