A device and method therein for improving measurement result made by a radar unit are disclosed. The device comprises the radar unit and at least one motion sensor unit. The radar unit transmits at least one radar pulse in a frequency range and receives at least one radar pulse response associated to reflections of the at least one transmitted radar pulse. The radar unit determines at least one measurement based on the transmitted and received radar pulses. The radar unit further receives information on movement of the device from the at least one motion sensor unit during radar pulse transmission and reception and adjust the at least one measurement based on received information on movement of the device from the at least one motion sensor unit.

In some implementations, a user equipment (UE) may determine an angular motion using at least one gyroscope. The UE may adjust at least one measurement from at least one sensor that is associated with the UE and used to measure relative position, based at least in part on the angular motion. Additionally, in some implementations, the UE may determine at least one distance between the at least one sensor and an estimated grip associated with the UE, and determine at least one translation associated with the at least one sensor based at least in part on the angular motion and the at least one distance. Accordingly, the UE may adjust the at least one measurement by offsetting the at least one measurement based at least in part on the at least one translation.

A device and method therein for improving measurement result made by a radar unit are disclosed. The device comprises the radar unit and at least one motion sensor unit. The radar unit transmits at least one radar pulse in a frequency range and receives at least one radar pulse response associated to reflections of the at least one transmitted radar pulse. The radar unit determines at least one measurement based on the transmitted and received radar pulses. The radar unit further receives information on movement of the device from the at least one motion sensor unit during radar pulse transmission and reception and adjust the at least one measurement based on received information on movement of the device from the at least one motion sensor unit.

The present application discloses a new form of μ-STAP, referred to herein as post μ-STAP or Pμ-STAP, which overcomes the drawbacks associated with existing μ-STAP techniques. The Pμ-STAP techniques described herein facilitate the generation of additional training data and homogenization after pulse compression. For example, Pμ-STAP techniques may apply a plurality of homogenization filters to a pulse compressed datacube generated from an input radar waveform, which produces a plurality of new pulse compressed datacubes with improved characteristics. Unlike existing μ-STAP techniques described above, which require prepulse compressed data to operate, the Pμ-STAP techniques disclosed in the present application are designed to utilize pulse compressed data, and therefore may be readily applied to legacy radar systems.

A method for determining direction information for at least one target object in a radar system for a vehicle. The first detection information is provided by at least two receive antennas of the radar system, wherein the first detection information is specific for a first radar signal transmitted by a first transmit antenna of the radar system. The second detection information is provided by the at least two receive antennas of the radar system, wherein the second detection information is specific for a second radar signal transmitted by a second transmit antenna of the radar system. A first angle determination and a second angle determination are performed. At least one comparison of the first angle information with the second angle information is performed in order to detect an ambiguity in the first angle determination for the determination of the direction information.

According to an example aspect of the present invention, there is provided monitoring living facilities by a multichannel radar. A field of view within a frequency range from 1 to 1000 GHz, for example between 1 to 30 GHz, 10 to 30 GHz, 30 to 300 GHz or 300 to 1000 GHz, is scanned using a plurality of radar channels of the radar. Image units comprising at least amplitude and phase information are generated for a radar image on the basis of results of the scanning. Information indicating at least one error source of a physical movement of the radar and interrelated movements of targets within the field of view are determined on the basis of the image units. Results of the scanning are compensated on the basis of the determined error source. A radar image is generated on the basis of the compensated results.

A radar data compensation method for a mobile robot, comprising: obtaining a uniform time series, the time interval between any two adjacent time points of the uniform time series being equal (201); determining, according to the timestamp of obtaining data by a position sensor and position information obtained by the position sensor, position information corresponding to the uniform time series (201); determining, according to the timestamp of obtaining data by an angle sensor and angle information obtained by the angle sensor, angle information corresponding to the uniform time series (203); determining, according to the position information and angle information corresponding to the uniform time series, position information and angle information of a mobile robot at the moment when a radar sensor obtains data points (204); and compensating, according to the position information and angle information of the mobile robot at the moment when the radar sensor obtains the data points, each radar data point corresponding to the moment when the radar sensor obtains radar data, so as to obtain motion compensation points of the radar data points corresponding to the moment when the radar data is obtained (205). Also provided are a radar data compensation apparatus for a mobile robot, a device, and a storage medium.

In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Disclosed herein is a system for facilitating performing of motion analysis in a field of interest, in accordance with some embodiments. Accordingly, the system may include a passive sensor, an active sensor, a processing device, a gateway, and a remote monitoring center. Further, the passive sensor and the active sensor is disposed in the field of interest. Further, the passive sensor generates passive sensor data. Further, the active sensor produces second waves, receives transformed waves, and generates active sensor data. Further, the gateway is configured for transmitting the passive sensor data and the active sensor data to the remote monitoring center. Further, the remote monitoring center is configured for performing the motion analysis. Further, the remote monitoring center may include a remote processing device configured for combining the passive sensor data and the active sensor data and generating motion information based on the combining.

A machine-learned model is trained using human driving data to determine a desired vehicle speed based from a set of driving-environment characteristics. An autonomous-vehicle control system obtains, from cameras, sensors, services, and data sources, a variety of sensor data. The sensor data is used to determine a set of characteristics for the driving-environment for the autonomous vehicle. Using the machine-learned model, the autonomous-vehicle control system determines a human-like desired speed for the autonomous vehicle based at least in part on the determined characteristics of the driving-environment.