Techniques involve releasing and/or capturing a fixed-wing aircraft using an aerial vehicle with VTOL capabilities while the fixed-wing aircraft is in flight. For example, the VTOL aerial vehicle may take off vertically while carrying the fixed-wing aircraft and then fly horizontally before releasing the fixed-wing aircraft. Upon release, the fixed-wing aircraft flies independently to perform a mission (e.g., surveillance, payload delivery, combinations thereof, etc.). After the fixed-wing aircraft has completed its mission, the VTOL aerial vehicle may capture the fixed-wing aircraft while both are in flight, and then land together vertically. Such operation enables the fixed-wing aircraft to vertically take off and/or land while avoiding certain drawbacks associated with a conventional VTOL kit such as being burdened by weight and drag from the VTOL kit's rotors/propellers, mounting hardware, etc. during a mission which otherwise would limit the fixed-wing aircraft's maximum airspeed, ceiling, payload capacity, endurance, and so on.

An approach is provided for biasing machine learning models towards potential risks for controlling vehicles/robots. The approach involves, for example, determining an occluded space that is occluded in sensor data collected from one or more sensors of a vehicle or a robot. The approach also involves generating a sensor space completion that represents the occluded space based on biasing a generation of one or more potential risks to the vehicle or the robot originating from the occluded space. The approach further involves providing the sensor space completion to a system of the vehicle or the robot for generating a control decision, a warning, or a combination thereof.

Disclosed are an anti-collision system and method for an aircraft and an aircraft including the anti-collision system. The anti-collision system includes: a sensor data processing unit configured to process data received from a plurality of sensors to detect objects around the aircraft, and output a result about detected objects; a safeguarding box building unit configured to generate, based on an aircraft geometry database, a three-dimensional safeguarding box for the aircraft; and a risk assessment unit configured to calculate relative distances between detected objects and the aircraft, and determine whether there is a collision risk between the aircraft and an object, among the detected objects, located in the safeguarding box or to be entering into the safeguarding box, wherein the system is configured to output an alarm or a warning when there is the collision risk.

Disclosed are an anti-collision system and method for an aircraft and an aircraft including the anti-collision system. The anti-collision system includes: a sensor data processing unit configured to process data received from a plurality of sensors to detect objects around the aircraft, and output a result about detected objects; a safeguarding box building unit configured to generate, based on an aircraft geometry database, a three-dimensional safeguarding box for the aircraft; and a risk assessment unit configured to calculate relative distances between detected objects and the aircraft, and determine whether there is a collision risk between the aircraft and an object, among the detected objects, located in the safeguarding box or to be entering into the safeguarding box, wherein the system is configured to output an alarm or a warning when there is the collision risk.

An imaging system including a transmitter configured to transmit a signal in a direction of a scene of interest. The transmitted signal is spatially and temporally incoherent at a point where the transmitted signal reaches the scene of interest. The system includes a receiver set including at least a first receiver and a second receiver. The first receiver and the second receiver are configured to receive a reflected signal. The reflected signal is a reflection of the transmitted signal from the scene of interest. The system further includes an active incoherent millimeter-wave image processor configured to obtain the reflected signal and reconstruct a scene based on the reflected signal. The system also includes a display device configured to display the scene.

The present invention relates to a method for assisting the landing of an aircraft on a landing runway, the method comprising: detecting, by a radar, characteristic elements of the landing runway, determining the angular offset between the axis of the radar and the runway axis as a function of the coordinates of the characteristic elements detected, and determining, as a function of the angular offset determined and the coordinates of the characteristic elements detected: the distance of the orthogonal projection onto the runway axis from the horizontal projection of the radar, and the distance of the orthogonal projection onto the straight line passing through the runway threshold from the horizontal projection of the radar.

The present invention relates to a method for assisting the landing of an aircraft on a landing runway, the method comprising: detecting, by a radar, characteristic elements of the landing runway, determining the angular offset between the axis of the radar and the runway axis as a function of the coordinates of the characteristic elements detected, and determining, as a function of the angular offset determined and the coordinates of the characteristic elements detected: the distance of the orthogonal projection onto the runway axis from the horizontal projection of the radar, and the distance of the orthogonal projection onto the straight line passing through the runway threshold from the horizontal projection of the radar.

In an example, a method is described. The method includes causing one or more sensors arranged on an aircraft to acquire, over a window of time, first data associated with a first object that is within an environment of the aircraft, where the one or more sensors include one or more of a light detection and ranging (LIDAR) sensor, a radar sensor, or a camera, causing an array of microphones arranged on the aircraft to acquire, over approximately the same window of time as the first data is acquired, first acoustic data associated with the first object, and training a machine learning model by using the first acoustic data as an input value to the machine learning model and by using an azimuth, a range, an elevation, and a type of the first object identified from the first data as ground truth output labels for the machine learning model.

A radar imaging method using an active antenna comprising N transmission channels and M reception channels, transmitting in bursts of pointing cycles, is disclosed. The antenna covers a given angular range during a detection time unit of duration T, said time unit corresponds to a burst in which the N transmission channels are focused successively in a number D.sub.e of pointing directions (di) such that: the pointing direction on transmission (di) is modified from recurrence to recurrence; each time unit of duration T comprising a periodic repetition of a number C of identical pointing cycles, each of these cycles comprising a number P of recurrences, the set of these P recurrences covers the D.sub.e pointing directions (di); at least one beam is formed in reception on each recurrence in a direction included in the angular range focused on transmission in the pointing direction corresponding to said recurrence.

Aspects and implementations of the present disclosure address challenges of the existing technology by enabling lidar-assisted identification and characterization of visibility-reducing media (VRM) such as fog, rain, snow, dust in autonomous vehicle applications, using lidar sensing. VRM can be identified and characterized using a variety of techniques, including analyzing a spatial distribution of low-intensity lidar returns, detecting pulse elongation of VRM-returns associated with reflection from VRM, determining intensity of VRM-returns, determining reduction of intensity of returns from various reference objects, and other techniques.