A method and electronic device for determining relevant signals in radar signal processing. The electronic device includes a radar transceiver, a memory, and a processor. The processor is configured to cause the electronic device to obtain, via the radar transceiver of the electronic device, radar measurements for one or more modes in a set of modes; process the radar measurements to obtain a set of radar images; identify relevant signals in the set of radar images based on signal determination criteria for an application; and perform the application using only the relevant signals.

A method and electronic device for determining relevant signals in radar signal processing. The electronic device includes a radar transceiver, a memory, and a processor. The processor is configured to cause the electronic device to obtain, via the radar transceiver of the electronic device, radar measurements for one or more modes in a set of modes; process the radar measurements to obtain a set of radar images; identify relevant signals in the set of radar images based on signal determination criteria for an application; and perform the application using only the relevant signals.

A computer-implemented method and system for calibrating an occupancy grid mapping a vehicle environment are disclosed. An example method includes identifying a feature of an occupancy grid that maps a vehicle environment in which the occupancy grid provides a primary representation of the feature. The example method also includes determining a quality level of the primary representation of the feature and determining if the quality level satisfies a quality criterion. The example method further includes adjusting a calibration of the occupancy grid if the quality level fails to satisfy the quality criterion. The adjustment of the calibration of the occupancy grid can include adjusting at least one parameter used to generate the occupancy grid to cause the quality level to satisfy the quality criterion.

A computer-implemented method and system for calibrating an occupancy grid mapping a vehicle environment are disclosed. An example method includes identifying a feature of an occupancy grid that maps a vehicle environment in which the occupancy grid provides a primary representation of the feature. The example method also includes determining a quality level of the primary representation of the feature and determining if the quality level satisfies a quality criterion. The example method further includes adjusting a calibration of the occupancy grid if the quality level fails to satisfy the quality criterion. The adjustment of the calibration of the occupancy grid can include adjusting at least one parameter used to generate the occupancy grid to cause the quality level to satisfy the quality criterion.

A system and a method for generating a subterranean map with ground penetrating radar are described. The system includes multiple ground penetrating radar transmitters, multiple ground penetrating radar receivers, and a controller. A first subset of the transmitters radiate a first signal at a first frequency bandwidth, a second subset of the transmitters radiate a second signal at a second frequency bandwidth different than the first frequency bandwidth, and a third subset of the transmitters radiate a third signal at a third frequency bandwidth different than the first and second frequency bandwidths. The receivers receive a first return signal at the first frequency bandwidth, a second return signal at the second frequency bandwidth, and a third return signal at the third frequency bandwidth and transmit the return signals. The controller operates the ground penetrating radar transmitters, receives the return signals, and generates a subterranean map from the return signals.

The described aspects and implementations enable fast and accurate object identification in autonomous vehicle (AV) applications by combining radar data with camera images. In one implementation, disclosed is a method and a system to perform the method that includes obtaining a radar image of a first hypothetical object in an environment of the AV, obtaining a camera image of a second hypothetical object in the environment of the AV, and processing the radar image and the camera image using one or more machine-learning models MLMs to obtain a prediction measure representing a likelihood that the first hypothetical object and the second hypothetical object correspond to a same object in the environment of the AV.

A system for use in a vehicle for determining an indication of the type of terrain in the vicinity of the vehicle, the system comprising; means configured to receive sensor output data from at least one sensor on the vehicle; means configured to determine a plurality of parameters in dependence on the sensor output data; a neural network algorithm configured to receive the plurality of parameters; and means configured to execute the neural network algorithm to provide a plurality of outputs corresponding to a plurality of different terrain types, the neural network being further configured to associate the plurality of parameters with one of the plurality of outputs, so as to determine an indication of the terrain type.

A method of automatically detecting damage following a loss causing incident is disclosed. The method includes capturing image information about a group of physical objects in their initial states and comparing these with image information about the group of physical objects in their modified states following a loss causing incident. The method includes detecting discrepancies between the initial and modified states and automatically assesses the degree of damage and/or loss.

A method of automatically detecting damage following a loss causing incident is disclosed. The method includes capturing image information about a group of physical objects in their initial states and comparing these with image information about the group of physical objects in their modified states following a loss causing incident. The method includes detecting discrepancies between the initial and modified states and automatically assesses the degree of damage and/or loss.

A method comprising: obtaining pose data representative of a pose of a portable device during observation of an environment comprising an object; obtaining distance data representative of a distance between the object and a receiver during the observation of the environment, using at least one radio waveform reflected from the object and received by the receiver; and processing the pose data and the distance data to generate a topological model of the object.