Abstract: Among other things, techniques are described for improving the trajectory estimates for an object in an environment. The technique includes receiving, by at least one processor, information indicating a presence of an object operating in an environment; determining, by the at least one processor, a trajectory of the object, the trajectory including at least a position, a speed, and a direction of travel of the object; determining, by the at least one processor, an expected route of the object, wherein the expected route is pre-planned and includes an expected future position of the object at a future time; comparing the trajectory of the object to the expected route of the object; and in accordance with the comparison that the trajectory of the object is consistent with the expected route of the object, updating the trajectory of the object based on the expected route of the object.

Abstract: A method for assisting with the navigation of a fleet of vehicles including a main vehicle and a secondary vehicle that is mobile in relation to the main vehicle, the method including receiving relative movement data, acquired by one or more sensors, between the main vehicle and the secondary vehicle, estimating a navigation status of the fleet of vehicles by an invariant Kalman filter using the received data as observations, the navigation status including first variables representing a first rigid transformation linking a location mark associated with the main vehicle to a reference point, and second variables representing a second rigid transformation linking a location mark associated with the main vehicle to a location mark associated with the secondary vehicle, the invariant Kalman filter using, as an internal composition law, a law including a term-by term composition of the first rigid transformation and the second rigid transformation.

Abstract: Methods and devices for optimizing the climb of an aircraft or drone are provided. After an optimal continuous climb strategy has been determined, a lateral path is determined, in particular in terms of speeds and turn radii, based on vertical predictions computed in the previous step. Subsequently, computation results are displayed on one or more human-machine interfaces and the climb strategy is actually flown. Embodiments describe the use of altitude and speed constraints and/or settings in respect of speed and/or thrust and/or level-flight avoidance and/or gradient-variation minimization, and iteratively fitting parameters in order to make the profile of the current path coincide with the constrained profile in real time depending on the selected flight dynamics (e.g. energy sharing, constraint on climb gradient, constraint on the vertical climb rate). System (e.g. FMS) and software aspects are described.

Abstract: A controller causes a calculation device to perform calculation that determines an operation of a moving object and generates digital signals that define the operations of actuators. The generated digital signals are output to a digital signal transmission path by a signal bus control IC. ICs attached to the actuators obtain digital signals that define the operations of the actuators from the digital signal transmission path and generate control signals for the actuators based on the operations defined by the digital signals.

Abstract: A method for having a vehicle follow a desired curvature path is provided. The vehicle has at least one differential with a differential lock connected to at least one driven wheel axle of the vehicle. The method includes providing information regarding state of the differential lock, the state being either that the differential lock is activated or unlocked, and when the differential lock is activated, calculating a yaw moment of the vehicle caused by the differential lock; and compensating for a deviation from the desired curvature path caused by the yaw moment such that a resulting steering angle is equal to or less than a maximum allowed steering angle of the vehicle. The compensation is a feed forward compensation.

Abstract: A method and device for controlling an autonomous driving vehicle, and an autonomous driving vehicle. Wherein the method comprises: detecting error information of different components in a vehicle, wherein the different components comprise at least one of the following: a power supply, a sensor, a navigation device, a log memory and a processing device; if the error information of any component is detected, feeding back the detected error information to a processor; restarting the vehicle’ automatic driving function based on a feedback result, wherein the feedback result is feedback by the processor according the detected error information. The present invention solves the technical problem that the autonomous driving vehicle in the related art cannot perform error information detection on the components in the vehicle which leads to the low reliability of the autonomous driving vehicle.

Abstract: The present invention relates to an aerospace vehicle navigation and control system comprising a terrestrial illumination matching module for determining spacecraft position and attitude. The method permits aerospace vehicle position and attitude determinations using terrestrial lights using an Earth-pointing camera without the need of a dedicated sensor to track stars, the sun, or the horizon. Thus, a module for making such determinations can easily and inexpensively be made onboard an aerospace vehicle if an Earth-pointing sensor, such as a camera, is present.

Abstract: An example operation includes one or more of detecting, by a transport, an environment via a first sensor, determining, by the transport, an event related to the environment is imminent, powering, by the transport, a second sensor associated with the imminent event, and detecting, by the transport, the event as it is occurring via the second sensor.

Abstract: A method for assisting the navigation of a fleet of vehicles including main vehicle and a secondary vehicle movable relative to the main vehicle includes receiving data acquired by one or more sensors, the received data including relative kinematic data between the main vehicle and the secondary vehicle, and estimating a navigation state of the fleet of vehicles by an invariant Kalman filter using the received data as observations. The navigation state includes first variables representative of a first rigid transformation linking a frame attached to the main vehicle to a reference frame, and second variables representative of a second rigid transformation linking the frame attached to the main vehicle to a frame attached to the secondary vehicle. The invariant Kalman filter uses as binary operation an operation including a term-by-term composition of the first rigid transformation and of the second rigid transformation.

Abstract: A control system for a motor vehicle, for outputting a controlled variable, with the aid of which a directly controlled variable of a motor vehicle is adjustable via suitable control operations, in order to adapt the directly controlled variable to a reference variable of the control system. The control system includes a controller, which is configured to output a first output variable on the basis of the directly controlled variable of the motor vehicle, and on the basis of the reference variable of the control system. The control system further includes a predictive model, which may be trained to output a second output variable that reflects a deviation of a driving behavior of a driver of the motor vehicle from the first output variable of the controller. The controlled variable of the control system encompasses an addition of the first output variable and the second output variable.

Abstract: Techniques for a geofence generation feature are described herein. Geospatial vector data for a geographical area and seed points for delivery locations within the geographical area may be obtained. A plurality of polygons that represent the geographical area may be determined based on an algorithm that uses the seed points and the geospatial vector data. A boundary point for each polygon may be determined based on coordinates for the plurality of polygons where each boundary point corresponds to a single seed point. A geofence of a first size may be generated, for each polygon, based on the coordinates for the polygons, the seed point, and the boundary point. Historical scans of GPS data may be obtained from user devices during historical visits to the geographical area. The geofence may be modified to a second size or a different shape based on the historical scans of the GPS data.

Abstract: A method for simulating an obstacle in an unmanned simulation scene includes: for obstacle information in a three-dimensional scene map, determining Gaussian distribution information of obstacle position detected by using a perception algorithm to be tested based on actual perception performance of the perception algorithm; adjusting each position of the simulated obstacle in the initial motion trajectory sequence, such that a position deviation between each adjusted position point in the target motion trajectory sequence and the corresponding position point in the initial motion trajectory sequence follows a Gaussian distribution; and adding the target motion trajectory sequence of the simulated obstacle to the three-dimensional scene map.

Abstract: A vehicle program update system and a vehicle program update method are provided which update a vehicle program that is used to control a vehicle by an on-board control device mounted on the vehicle to an update program received by the vehicle from an external device separate from the vehicle via wireless communication. When the update of the vehicle program is completed, determination is made whether the updated vehicle program is normal. When determination is made that the updated vehicle program is not normal, control of the vehicle is switched from control that is performed by the on-board control device using the vehicle program to limp home control for performing a limp home operation in which the vehicle travels using a driving force from a vehicle driving force source without being controlled by the on-board control device.

Abstract: A computing system can input first relative location embedding data into an interaction transformer model and receive, as an output of the interaction transformer model, motion forecast data for actors relative to a vehicle. The computing system can input the motion forecast data into a prediction model to receive respective trajectories for the actors for a current time step and respective projected trajectories for the actors for a subsequent time step. The computing system can generate second relative location embedding data based on the respective projected trajectories from the second time step. The computing system can produce second motion forecast data using the interaction transformer model based on the second relative location embedding. The computing system can determine second respective trajectories for the actors using the prediction model based on the second forecast data.

Abstract: An autonomous cleaning robot includes a drive system to maneuver the autonomous cleaning robot across a floor surface; a cleaning assembly for cleaning the floor surface; and a sensor system disposed at a forward portion of the autonomous cleaning robot. The sensor system includes a movable element having (i) a first configuration in which the movable element extends beyond a bottom surface of the autonomous cleaning robot by a first amount, and (ii) a second configuration in which the movable element extends beyond the bottom surface of the autonomous cleaning robot by a second amount less than the first amount; a spring mechanically coupled to the movable element, the spring being biased to hold the movable element in the first configuration; and a sensor assembly configured to generate a signal based on the configuration of the movable element.

Abstract: A system for handling a driving while disconnected event. One example includes an electronic logging device configured to be connected to a vehicle and a mobile device. The mobile device includes an electronic processor configured to determine a connection status between the mobile device and the electronic logging device; determine movement of the mobile device; and determine whether the mobile device is connected to the electronic logging device based on the connection status. In response to determining the mobile device is not connected to the electronic logging device, the electronic processor generates driving information associated with a user of the mobile device and movement of the mobile device; transmits the driving information to an external device; and generates a user-perceivable notification to connect the mobile device to the electronic logging device.

Abstract: A method and a device for locating a vehicle, able to estimate a first position of a vehicle from data that are generated by sensors of the vehicle and that are applied to a first particle filter, to store in memory, in a history, for a plurality of times, sensor data that led to the best estimations of a current position ti, to receive at the time tn a corrected GNSS position of the vehicle at a time t0, and to estimate using a second particle filter FP2 a corrected position of the vehicle at a time ti by applying the second particle filter FP2 to the received corrected GNSS position, to the data stored in memory in association with the time ti and to the dynamic characteristics of the vehicle that are associated with the time ti?1.

Abstract: GPS-based position reporting suffers from probabilistic error. The system and methods discussed herein reduce uncertainty by mapping a geometric figure that encompasses a GPS-based reported location and that bounds corresponding predetermined-as-more-probable true locations (MPTL's) among possible locations for the source of the reported location. The mapped figure is overlaid on a relatively accurate mapping of substantially adjacent polygonal areas. Areas of overlap are used for picking among the areas, the polygonal area most likely to be occupied by the source. In one embodiment, the polygonal areas are closely packed parking spots in a parking lot, garage or other like structure, the source is a customer's mobile phone and an attendant is tasked with quickly delivering ordered goods to the customer's parking spot.