Metrotech Corporation

Horizon Robotics Inc.

Kun Li

James W Waite

Dimitar Gargov

Johan Överby

Johan D Overby

Jim Waite

Ruwan Welaratna

Paolo Salvagione

Yihan Hu

Pingyuan Liang

Disclosed are a method and an apparatus for predicting vehicle trajectory, and a method and an apparatus for training a neural network prediction model, relating to the field of intelligent driving technology. The method for predicting vehicle trajectory including: determining raster image data of a vehicle at a current time point based on ego-vehicle travelling data of the vehicle during travelling and environmental data of the vehicle; processing the raster image data based on a neural network prediction model, and predicting a trajectory of the vehicle in a future predetermined time period based on the multidimensional feature map, ego-vehicle size data and the environmental data.

Method and apparatus for predicting vehicle trajectory, and method and apparatus for training neural network prediction model

A system for determining the position of an underground sonde transmitter is disclosed. In some embodiments, the system measures a set of complex electromagnetic field magnitude and phase strengths at one or more positions while traversing a target sonde path at any angle using one or more electromagnetic coil sensors, models a set of expected complex electromagnetic strengths of a hypothetical sonde at the positions for one or more of the electromagnetic coil sensors, the set of expected electromagnetic field values corresponding to a model for the target sonde, and estimates parameters related to the target sonde based on the residual error between the measured set of complex electromagnetic field values and the modeled set of expected complex electromagnetic field strengths. A final estimated parameter set is determined after the residual error has converged to a minimum tolerance to indicate the sonde transmitter position.

System for determining a precise location and orientation of a concealed dipole transmitter

A method for determining the location of underground cables and pipes is disclosed. In some embodiments, the method includes measuring a set of electromagnetic field magnitudes and phases at a plurality of positions while traversing a target line parallelly using 3D electromagnetic coil sensors, the 3D electromagnetic coil sensors being orthogonally oriented to the target line, modeling a set of expected complex electromagnetic field magnitudes of a single underground conductor at each of the positions to form a set of values corresponding to a set of individual models for the target line, determining which of the set of individuals models is a best model, determining confidence information at each of the positions based on a comparison between the measured set of complex electromagnetic magnitudes and phases and the best model, and determining parameters at each of positions related to the target line from the best model.

Enhanced precise location

A line locator includes a signal detector to detect signals from an underground line; an error modeler that models a phase error in the signal from neighboring underground lines; and an enhanced electromagnetic field modeler that provides a location of the underground line based on the signal and a result from the error modeler.

A method for determining the location of an underground sonde transmitter is disclosed. In some embodiments, the method includes measuring a set of complex electromagnetic field magnitude and phase strengths at one or more of positions while traversing a target sonde path at any angle using one or more electromagnetic coil sensors, modeling a set of expected complex electromagnetic strengths of a hypothetical sonde at the one or more of positions for one or more of the electromagnetic coil sensors, the set of expected electromagnetic field values corresponding to a model for the target sonde, and estimating parameters related to the target sonde based on the residual error between the measured set of complex electromagnetic field values and the modeled set of expected complex electromagnetic field strengths, wherein a final estimated parameter set is determined after the residual error has converged to a minimum tolerance.

Growing community of inventors

Cupertino, CA, United States of America

Kun Li