Abstract: Technology is disclosed for systems, devices, and methods relating to vehicle positioning. A system for vehicle positioning can comprise a passive resonator configured to be embedded in a roadway, and at least one antenna configured to be attached to a vehicle. The at least one antenna can be configured to transmit a first signal to the passive resonator and receive a second signal from the passive resonator at a harmonic frequency of the first signal. Diodes are used to stimulate a resonant circuit to create the second signal. The passive resonator can be configured to receive the first signal from the at least one antenna and transmit a second signal to the at least one antenna. The system can further comprise a processor configured to: calculate a relative position between the vehicle and the passive resonator based on a phase difference observed between the first signal and a reference signal.

Abstract: For tracking a target, a method receives a combined signal comprising a target signal reflected by a target and a transmitter signal not reflected by the target, wherein the transmitter signal is comprised of a plurality of orthogonal frequency division multiplexing (OFDM) subcarrier signals. The method calculates a signal Fourier transform for the combined signal to obtain the complex symbols. The method estimates a sequence of channel state information. The method estimates CSI over for non-pilot OFDM subcarriers of the combined signal to obtain CSI for a sequence of M OFDM symbols. The method computes a CSI Fourier transform for the sequence of CSI for a plurality of OFDM subcarriers. The method estimates a CSI Doppler frequency by matching a Fourier transform template to the CSI Fourier transform. The method computes each of a target position and a target velocity vector for the target.

Abstract: For tracking a target, method detects, by use of a processor, that the target is present. The method estimates an initial target position. The method further tracks the target position from channel state information Doppler frequency measurements using at least one of an extended Kalman filter, a Viterbi algorithm, and a particle filter.

Abstract: For tracking a target, a method receives a combined signal comprising a target signal reflected by a target and a transmitter signal not reflected by the target, wherein the transmitter signal is comprised of a plurality of orthogonal frequency division multiplexing (OFDM) subcarrier signals. The method calculates a signal Fourier transform for the combined signal to obtain the complex symbols. The method estimates a sequence of channel state information. The method estimates CSI over for non-pilot OFDM subcarriers of the combined signal to obtain CSI for a sequence of M OFDM symbols. The method computes a CSI Fourier transform for the sequence of CSI for a plurality of OFDM subcarriers. The method estimates a CSI Doppler frequency by matching a Fourier transform template to the CSI Fourier transform. The method computes each of a target position and a target velocity vector for the target.

Abstract: Technology is disclosed for systems, devices, and methods relating to vehicle positioning. A system for vehicle positioning can comprise a passive resonator configured to be embedded in a roadway, and at least one antenna configured to be attached to a vehicle. The at least one antenna can be configured to transmit a first signal to the passive resonator and receive a second signal from the passive resonator at a harmonic frequency of the first signal. Diodes are used to stimulate a resonant circuit to create the second signal. The passive resonator can be configured to receive the first signal from the at least one antenna and transmit a second signal to the at least one antenna. The system can further comprise a processor configured to: calculate a relative position between the vehicle and the passive resonator based on a phase difference observed between the first signal and a reference signal.

Abstract: For tracking a target, a method receives a first target signal reflected by a target for a first transmitter/receiver pair. The method receives a second target signal reflected by the target for a second transmitter/receiver pair or transmitter signal characteristics for a transmitter of the first transmitter/receiver pair. The method determines Doppler frequencies based on the first target signal and the second target signal or the transmitter signal characteristics. The method determines a target position and a target velocity vector for the target based on the Doppler frequencies.

Abstract: Environmental recognition systems may improve recognition accuracy by leveraging local and nonlocal features in a recognition target. A local decoder may be used to analyze local features, and a nonlocal decoder may be used to analyze nonlocal features. Local and nonlocal estimates may then be exchanged to improve the accuracy of the local and nonlocal decoders. Additional iterations of analysis and exchange may be performed until a predetermined threshold is reached. In some embodiments, the system may comprise extrinsic information extractors to prevent positive feedback loops from causing the system to adhere to erroneous previous decisions.

Abstract: Environmental recognition systems may improve recognition accuracy by leveraging local and nonlocal features in a recognition target. A local decoder may be used to analyze local features, and a nonlocal decoder may be used to analyze nonlocal features. Local and nonlocal estimates may then be exchanged to improve the accuracy of the local and nonlocal decoders. Additional iterations of analysis and exchange may be performed until a predetermined threshold is reached. In some embodiments, the system may comprise extrinsic information extractors to prevent positive feedback loops from causing the system to adhere to erroneous previous decisions.

Abstract: Adaptive learning of a multichannel prefilter response processes multiple audio signals prior to emitting them from a set of loudspeakers. The signals are filtered and mixed in such a way that the emitted signals will be reconstructed at pre-specified points in a room. This is done in a user selective way so that, at each location, only one of the source signals is reconstructed and the other signals vanish. A gradient descent adaptive filtering method is applied.