Abstract: The disclosed embodiments provide a highly accurate, low-latency pre-processing pipeline hardware architecture for RADAR images. In an embodiment, a method comprises: receiving a time-domain representation of a radar image of a scene, the representation including at least one object; determining a range to the at least one target based on a range frequency spectrum computed from the time-domain representation; determining a radial velocity of the at least one object based on a Doppler frequency spectrum computed from the time-domain representation; determining an azimuth angle of the at least one object based on the Doppler frequency spectrum; generating a data structure containing the range, radial velocity and azimuth angle; performing at least one machine learning process on contents of the data structure; and generating at least one control signal for controlling a vehicle based at least in part on a result of performing the machine learning process.

Abstract: Provided are methods for generation of representations of radar data. Some methods described include: receiving ADC raw data of a radar sensor of a vehicle; performing range FFT, Doppler FFT, and azimuth FFT on the ADC raw data; generating a 1D range heat map tensor representing the range FFT, a 2D RD heat map tensor representing a combination of the range FFT and the Doppler FFT, a 2D RA heat map tensor representing a combination of the range FFT and the azimuth FFT, or a 3D RAD matrix tensor representing a combination of the range FFT, the Doppler FFT, and the azimuth FFT; and inputting at least one of the 1D range heat map tensor, the 2D RD heat map tensor, the 2D RA heat map tensor, or the 3D RAD matrix tensor, to a machine learning model for detecting objects on a road network around the vehicle.

Abstract: Provided are methods for generation of representations of radar data. Some methods described include: receiving ADC raw data of a radar sensor of a vehicle; performing range FFT, Doppler FFT, and azimuth FFT on the ADC raw data; generating a 1D range heat map tensor representing the range FFT, a 2D RD heat map tensor representing a combination of the range FFT and the Doppler FFT, a 2D RA heat map tensor representing a combination of the range FFT and the azimuth FFT, or a 3D RAD matrix tensor representing a combination of the range FFT, the Doppler FFT, and the azimuth FFT; and inputting at least one of the 1D range heat map tensor, the 2D RD heat map tensor, the 2D RA heat map tensor, or the 3D RAD matrix tensor, to a machine learning model for detecting objects on a road network around the vehicle.

Abstract: Provided are methods for generation of representations of radar data. Some methods described include: receiving ADC raw data of a radar sensor of a vehicle; performing range FFT, Doppler FFT, and azimuth FFT on the ADC raw data; generating a 1D range heat map tensor representing the range FFT, a 2D RD heat map tensor representing a combination of the range FFT and the Doppler FFT, a 2D RA heat map tensor representing a combination of the range FFT and the azimuth FFT, or a 3D RAD matrix tensor representing a combination of the range FFT, the Doppler FFT, and the azimuth FFT; and inputting at least one of the 1D range heat map tensor, the 2D RD heat map tensor, the 2D RA heat map tensor, or the 3D RAD matrix tensor, to a machine learning model for detecting objects on a road network around the vehicle.

Abstract: In a virtualized desktop system an interfacing module is coupled to peripheral ports of a target device. The interfacing module is connected to a network. A digital user station is connected to the network. The digital user station is configured to be coupled to peripherals. The interfacing module and digital user station use respective hardware engines to communicate via said network.

Abstract: In a virtualized desktop system, a digital user station communicates with an interfacing module coupled to a target device via a network. The digital user station controls the power of the target device and the interfacing module by determining the power status of the interfacing module and sending a power control packet to the target device the interfacing module is coupled to.

Abstract: An interfacing module connected to a network. A target network device connected to the network. An interfacing module is associated with a target network device. An interfacing module is coupled to a peripheral port of a target network device. Interfacing module identification data is stored in a memory portion of the target network device. The network address of the target network device is determined. The network address of the interfacing module is determined. At a remote location the network address of the target network device is used to read the interfacing module identification data from the memory portion of the target device via the network.

Abstract: In a virtualized desktop system an interfacing module is coupled to peripheral ports of a target device. The interfacing module is connected to a network. A digital user station is connected to the network. The digital user station is configured to be coupled to peripherals. The interfacing module and digital user station use respective hardware engines to communicate via said network.

Abstract: In a virtualized desktop system, a digital user station communicates with an interfacing module coupled to a target device via a network. The digital user station controls the power of the target device and the interfacing module by determining the power status of the interfacing module and sending a power control packet to the target device the interfacing module is coupled to.

Abstract: An interfacing module connected to a network. A target network device connected to the network. An interfacing module is associated with a target network device. An interfacing module is coupled to a peripheral port of a target network device. Interfacing module identification data is stored in a memory portion of the target network device. The network address of the target network device is determined. The network address of the interfacing module is determined. At a remote location the network address of the target network device is used to read the interfacing module identification data from the memory portion of the target device via the network.