Abstract: A scalable solution to robot behavioral navigation following natural language instructions is presented. An example of the solution includes: receiving, by a pre-trained sequential prediction model, a navigation graph of the task environment, instructions in natural language and an initial location of the robot in the navigation graph, wherein the navigation graph comprises nodes indicating locations in the task environment, coordinates of the nodes, and edges indicating connectivity between the locations; and predicting sequentially, by the pre-trained sequential prediction model, a sequence of single-step behaviors executable by the robot to navigate the robot from the initial location to a destination.

Abstract: The present invention relates to a method for estimating the value of the angle of the direction of motion or of the walk of a person who carries a device capable of measuring the basic quantities related to his/her own inertia such as a common smartphone. The device is capable of measuring for example acceleration and angular rotation and to determine its orientation relative to Magnetic North. The estimation method in question is particularly suitable for estimating the direction angle of the individual's motion regardless of how the individual carries the device able to measure the main inertial quantities and consequently this method solves the problem of the determination of the relative attitude between the reference system of the carried device and the user reference system that moves within a generic absolute reference system.

Abstract: Technologies for determining a user's location by a mobile computing device include detecting, based on sensed inertial characteristics of the mobile computing device, that a user of the mobile computing device has taken a physical step in a direction. The mobile computing device determines a directional heading of the mobile computing device in the direction and a variation of an orientation of the mobile computing device relative to a previous orientation of the mobile computing device at a previous physical step of the user based on the sensed inertial characteristics. The mobile computing device further applies a Kalman filter to determine a heading of the user based on the determined directional heading of the mobile computing device and the variation of the orientation and determines an estimated location of the user based on the user's determined heading, an estimated step length of the user, and a previous location of the user at the previous physical step.

Abstract: A system and method for efficiently determining trajectory and/or location of a device (or user thereof). In a non-limiting example, rotation matrix coefficients may be analyzed in conjunction with stepping information to determine device trajectory and/or location. The system and method may, for example, be implemented in a MEMS sensor system, for example comprising a MEMS gyroscope, MEMS accelerometer, MEMS compass and/or MEMS pressure sensor.

Abstract: Technologies for determining a user's location include a mobile computing device (100) to determine, based on sensed inertial characteristics of the device, a walking gait of a user. The walking gait is one of a first gait indicative of the user holding the device to the user's side or a second gait indicative of the user swinging the device along the user's side. The device further detects that the user has taken a physical step based on the inertial characteristics and the determined walking gait of the user, and determines a raw directional heading of the device indicative of a direction of the physical step. The device determines an estimated location of the user based on the determined raw directional heading, an estimated step length, and the user's previous location.

Abstract: A system and method for efficiently determining trajectory and/or location of a device (or user thereof). In a non-limiting example, rotation matrix coefficients may be analyzed in conjunction with stepping information to determine device trajectory and/or location. The system and method may, for example, be implemented in a MEMS sensor system, for example comprising a MEMS gyroscope, MEMS accelerometer, MEMS compass and/or MEMS pressure sensor.

Abstract: This disclosure is directed to a detection and avoidance apparatus for an unmanned aerial vehicle (“UAV”) and systems, devices, and techniques pertaining to automated object detection and avoidance during UAV flight. The system may detect objects within the UAV's airspace through acoustic, visual, infrared, multispectral, hyperspectral, or object detectable signal emitted or reflected from an object. The system may identify the source of the object detectable signal by comparing features of the received signal with known sources signals in a database. The features may be, for example, a light arrangement or number of lights associated with the object. Furthermore, a trajectory envelope for the object may be determined based on characteristic performance parameters for the object such as cursing speed, maneuverability, etc. The UAV may determine an optimized flight plan based on the trajectory envelopes of detected objects within the UAV's airspace to avoid the detected objects.

Abstract: Techniques provided herein are directed toward resolving a direction of travel of a mobile device based on MEMS sensor data by identifying a type of motion the mobile device is subject to and offsetting vertical acceleration data with horizontal acceleration data by a predetermined time offset based on the identified type of motion. The offset vertical and horizontal acceleration data can then be used to resolve, with an increased accuracy, a direction of travel of the mobile device.

Abstract: A data fusion architecture with a plurality of sensors, optionally position measuring equipment (PMEs), is described. Each sensor supplies measurement data x1, x2 . . . xM and is associated with accuracy data H1, H2 . . . HM indicative of the accuracy of the supplied measurement data. Sub-processing units derives first estimates sf1, sf2 . . . sfM and second estimates Hn1, Hn2 . . . HnM of the variability of the measurement data supplied by the respective sensor. The first estimates are derived by processing the measurement data x1, x2 . . . xM and the second estimates are derived by processing the accuracy data H1, H2 . . . HM. The first and second estimates are combined in a multiplier to derive overall estimates ?1, ?2 . . . ?M of the variability of the measurement data supplied by the respective sensor. Data fusion means such as a Kalman filter combines the measurement data supplied by each sensor and the overall estimates ?1, ?2 . . . ?M for each sensor.

Abstract: Display rotation management is described. A device may include sensors disposed within a housing that produce an output usable to determine an orientation of a display device disposed on a surface of the housing. A rotation manager module disposed within the housing may process the output of the sensors to determine the orientation of the display device. The rotation manager module may calculate an average orientation of the display device over a time interval and a variance of the orientation. Based on the variance of the orientation in relation to a threshold amount, the rotation manager module can set a screen orientation of the display device.

Abstract: There is provided a mobile object including an input detection unit configured to detect an input from an outside, an acquisition unit configured to acquire environmental information detected by a sensor in a remote location, in accordance with a content of detection performed by the input detection unit, and a control unit configured to control an actuator other than a driving actuator in accordance with the environmental information acquired by the acquisition unit, the driving actuator relating to movement of the mobile object.

Abstract: A method for time-space-position-information (TSPI) for at least one air-based platform in a flight test includes providing a system having components to collect TSPI. The system, which includes an air-based platform, is initialized and a flight test is started. The system is remotely monitored to determine system diagnostics and, when system problems are diagnosed, they are fixed by remote configuration or manual repair. TSPI data is received with ground-based receiver nodes through a wireless data link signal transmitted from a dedicated on board transmitter on the air-based platform. The dedicated on board transmitter uses a known transmitter signal waveform. The ground-based receiver nodes match an internally generated signal waveform to the known transmitter signal waveform to measure time of arrival. The TSPI data is collected and sent to a ground processing station. The TSPI data is processed with the ground processing station. The system components and TSPI data are collected.

Abstract: A method and apparatus for determining a trajectory for a vehicle are disclosed, wherein, the method includes: identifying a starting position (p0) and a desired terminal position (P) for the vehicle; linearly approximating dynamics of the vehicle; and using the starting position (p0), desired terminal position (P), and linear approximation, determining the trajectory for the vehicle. The linear approximation can be constrained by requirements (e.g., specifications) that: (i) an acceleration applied to the vehicle at a point on the trajectory is relatively large when the acceleration acts in a direction that is substantially perpendicular to the velocity of the vehicle; and (ii) an acceleration applied to the vehicle at a point on the trajectory is relatively small when the acceleration acts in a direction that is substantially parallel to the velocity of the vehicle. The vehicle may have a curvature limit.

Abstract: A method for determining overbounds comprises the steps of determining conservative overbounds (qi) of at least one error (?i) in a first phase space, multiplying the conservative overbounds (qi) of errors (?i) in the first phase space by a first parameter (?(?x)·2) and a second parameter (?(x)·2), and determining an upper bound for the integrity risk at the alert limit (pw,int(AL)) in a second phase space using overbounds (qi) of errors (?i) in the first phase space by the first parameter (?(?x)·2) and the second parameter (?(x)·2).

Abstract: A method/system for estimating a state of a device and at least one target in an environment. The process involves computing a state vector using an error state form of the position of the device in a local coordinate reference frame.

Abstract: A user-heading determining system (10) for pedestrian use includes a multiple-axis accelerometer (110) having acceleration sensors; a device-heading sensor circuit (115) physically situated in a fixed relationship to the accelerometer (110); an electronic circuit (100) operable to generate signals representing components of acceleration sensed by the accelerometer (110) sensors, and to electronically process at least some part of the signals to produce an estimation of attitude of a user motion with respect to the accelerometer, and further to combine the attitude estimation (750, ?) with a device heading estimation (770, ?) responsive to the device-heading sensor circuit, to produce a user heading estimation (780); and an electronic display (190) responsive to the electronic circuit (100) to display information at least in part based on the user heading estimation. Other systems, circuits and processes are also disclosed.

Abstract: Computer-implemented systems and methods are disclosed for distance and congestion-aware resource deployment. In some embodiments, a method is provided to estimate a vehicle deployment region. The method includes constructing a graph data structure using at least in part a single invocation of a form of Dijkstra's algorithm. The method additionally includes partitioning an angular space centered on a vehicle location into a plurality of angular space regions, the vehicle location corresponding to a current or potential location of the vehicle.

Abstract: A signal processing module (50) comprises a difference signal generating module (60) for generating at least one difference signal (?) from a first and a second acceleration measurement vector signal (S1, S2), the first and the second acceleration measurement vector signal (S1, S2) respectively comprising a first and a second sequence of vector signal samples, the vector signal samples comprising at least a first and a second linearly independent acceleration measurement signal component, wherein the vector signal samples represent a measurement result of an acceleration sensor having a variable orientation as a function of time, wherein samples in the first sequence have a corresponding sample in the second sequence.

Abstract: Energy costs which are assigned to area segments are used when calculating the range and/or consumption for a vehicle.

Abstract: A user-heading determining system (10) for pedestrian use includes a multiple-axis accelerometer (110) having acceleration sensors; a device-heading sensor circuit (115) physically situated in a fixed relationship to the accelerometer (110); an electronic circuit (100) operable to generate signals representing components of acceleration sensed by the accelerometer (110) sensors, and to electronically process at least some part of the signals to produce an estimation of attitude of a user motion with respect to the accelerometer, and further to combine the attitude estimation (750, ?) with a device heading estimation (770, ?) responsive to the device-heading sensor circuit, to produce a user heading estimation (780); and an electronic display (190) responsive to the electronic circuit (100) to display information at least in part based on the user heading estimation. Other systems, circuits and processes are also disclosed.

Abstract: A method determines a partial area of a map which is described by features, the partial area describing the remaining range of a motor vehicle. An energy-storage system supplies a drive system which acts on at least one wheel of the motor vehicle. The remaining range is determined as a function of energy stored in the energy-storage system using an algorithm which expands from a current position of the motor vehicle. The method uses divides the map into geometric, in particular rectangular, structures of equal size. Whenever, in the context of the expansion, a feature lying in a structure or corresponding to a structure is added, the structure is added to the partial area.

Abstract: A system and a method for commanding a spacecraft to perform a three-axis maneuver purely based on “position” (i.e., attitude) measurements. Using an “inertial gimbal concept”, a set of formulae are derived that can map a set of “inertial” motion to the spacecraft body frame based on position information so that the spacecraft can perform/follow according to the desired inertial position maneuvers commands. Also, the system and method disclosed herein employ an intrusion steering law to protect the spacecraft from acquisition failure when a long sensor intrusion occurs.

Abstract: Systems and methods for determining a position of a vehicle are described. The system includes at least one GNSS sensor mounted to the vehicle for receiving GNSS signals of a global positioning system and at least one physical sensor mounted to the vehicle for generating physical data indicative of a physical parameter of at least a part of the vehicle. The system also includes a recursive statistical estimator, such as a Kalman Filter, in communication with the GNSS sensor(s) for seeding the recursive statistical estimator with an output of the GNSS sensor(s) to determine an estimated position of the vehicle. A data fusion module combines the estimated position and velocity of the vehicle with the physical data thus generating combined data, which is used to seed the recursive statistical estimator to determine an updated estimated position of the vehicle.

Abstract: A method of estimating position and orientation of a vehicle using image data is provided. The method includes capturing an image of a region external to the vehicle using a camera mounted to the vehicle, and identifying in the image a set of feature points of the region. The method further includes subsequently capturing another image of the region from a different orientation of the camera, and identifying in the image the same set of feature points. A pose estimation of the vehicle is generated based upon the identified set of feature points and corresponding to the region. Each of the steps are repeated at with respect to a different region at least once so as to generate at least one succeeding pose estimation of the vehicle. The pose estimations are then propagated over a time interval by chaining the pose estimation and each succeeding pose estimation one with another according to a sequence in which each was generated.

Abstract: The present invention relates to a system and method for determining vehicle attitude and position from image data detected by sensors in a vehicle. The invention uses calculated differences between the locations of selected features in an image plane and the location of corresponding features in a terrain map to determine the attitude of the vehicle carrying the sensors with respect to a ground frame of reference.

Abstract: A user-heading determining system (10) for pedestrian use includes a multiple-axis accelerometer (110) having acceleration sensors; a device-heading sensor circuit (115) physically situated in a fixed relationship to the accelerometer (110); an electronic circuit (100) operable to generate signals representing components of acceleration sensed by the accelerometer (110) sensors, and to electronically process at least some part of the signals to produce an estimation of attitude of a user motion with respect to the accelerometer, and further to combine the attitude estimation (750, ?) with a device heading estimation (770, ?) responsive to the device-heading sensor circuit, to produce a user heading estimation (780); and an electronic display (190) responsive to the electronic circuit (100) to display information at least in part based on the user heading estimation. Other systems, circuits and processes are also disclosed.

Abstract: A cooperative engagement group-position determining system employs a group of at least three cooperative units, for example a group of unmanned aerial vehicles (UAV's), with each unit including a GPS system for determining a GPS-based position, an inter-distance measurement module for measuring a distance of the unit relative to at least one other unit, and a computer having a computer-readable storage medium encoded with a program algorithm for correcting the GPS-based position based on at least one relative distance between two units, providing an improved GPS-based position for the unit and for the group. The system can also include a ground controller, for example, for providing flight control for UAV's.

Abstract: A method of error compensation for an inertial measurement unit is provided. The method comprises providing a first object including an inertial measurement unit, providing a second object proximal to the first object, and determining an initial position and orientation of the first object. A motion update is triggered for the inertial measurement unit when the second object is stationary with respect to a ground surface. At least one position vector is measured between the first object and the second object when the first object is in motion and the second object is stationary. A distance, direction, and orientation of the second object with respect to the first object are calculated using the at least one position vector. An error correction is then determined for the inertial measurement unit from the calculated distance, direction, and orientation of the second object with respect to the first object.