An odometer comprises a housing having a vehicle mounting device attached thereto. In an embodiment, the vehicle mounting device configured to be connectable to and removable from the non-odometer equipped vehicle. The housing further comprises a doppler radar module disposed in the housing. A processor is disposed in the housing and operatively connected to the doppler radar module and memory. In turn, the memory comprises executable instructions that, when executed by the processor, cause the processor to receive, from the doppler radar module, velocity-indicative data relative to a surface traveled by the non-odometer equipped vehicle. Thereafter, the processor operates to determine a distance traveled by the non-odometer equipped vehicle based on the velocity-indicative data.

Perception sensors of a vehicle can be used for various operating functions of the vehicle. A computing device may receive sensor data from the perception sensors, and may calibrate the perception sensors using the sensor data, to enable effective operation of the vehicle. To calibrate the sensors, the computing device may project the sensor data into a voxel space, and determine a voxel score comprising an occupancy score and a residual value for each voxel. The computing device may then adjust an estimated position and/or orientation of the sensors, and associated sensor data, from at least one perception sensor to minimize the voxel score. The computing device may calibrate the sensor using the adjustments corresponding to the minimized voxel score. Additionally, the computing device may be configured to calculate an error in a position associated with the vehicle by calibrating data corresponding to a same point captured at different times.

A device is configured for performing localization using a set of sensors that are transportable with the device. The device includes at least one processor operationally connected to the set of sensors, and at least one memory that stores program code. The program code configures the at least one processor to determine a first set of device poses where a first sensor satisfies a localization performance rule, and to determine a second set of device poses where a second sensor satisfies the localization performance rule. The at least one processor is further configured to activate the second sensor while the first sensor is active based on a pose of the device transitioning from not being within to being within the second set of device poses.

Described herein are embodiments of a method and system that uses a vertical or upward facing imaging sensor to compute vehicle attitude, orientation, or heading and combines the computed vehicle attitude, orientation, or heading with range bearing measurements from an imaging sensor, LiDAR, sonar, etc., to features in the vicinity of the vehicle to compute accurate position and map estimates.

A sensor data processing system for an autonomous vehicle receives inertial measurement unit (IMU) data from one or more IMUs of the autonomous vehicle. Based at least in part on the IMU data, the system identifies an IMU data offset from a deficient IMU of the one or more IMUs, and generates an offset compensation transform to compensate for the IMU data offset from the deficient IMU. The system dynamically executes the offset compensation transform on the IMU data from the deficient IMU to dynamically compensate for the IMU data offset.

Obstacle detection and characterisation method, including the steps of: acquiring a first distance measurement obtained from at least one inertial measurement produced by at least one inertial sensor of a mobile terminal, and a second distance measurement obtained from at least one time of flight measurement; evaluating a distance error representative of a difference between the second distance measurement and the first distance measurement; from the distance error, detecting the presence of an obstacle between the mobile terminal and the reference equipment, and determining one or more characteristics of said obstacle.

A host vehicle position estimation device includes an observation position estimation unit configured to estimate an observation position of the vehicle based on a result of recognition of the target object performed, a prediction position calculation unit configured to calculate a prediction position of the vehicle from a result of estimation of the host vehicle position in the past based on a result of measurement performed by an internal sensor, a host vehicle position estimation unit configured to estimate the host vehicle position based on the observation position and the prediction position. The host vehicle position estimation unit is configured to give more weighting to the prediction position in the estimation of the host vehicle position such that the host vehicle position is estimated to be close to the prediction position if it is determined that a result of estimation of the host vehicle position is unsteady.

A method for locating an object of interest using offset. The object may be a mobile platform, or portion of same, associated with a vehicle, or a pavement segment or feature of or on a pavement segment on which the mobile platform is located. The vehicle includes first and second fixed points having a known offset from each other. An image sensor whose field of view includes the second fixed point and a portion of the mobile platform provides image data which is used with the known offset to calculate the precise location of the object of interest.

In one embodiment, a system and method for point cloud registration of LIDAR poses of an autonomous driving vehicle (ADV) is disclosed. The method selects poses of the point clouds that possess higher confidence level during the data capture phase as fixed anchor poses. The fixed anchor points are used to estimate and optimize the poses of non-anchor poses during point cloud registration. The method may partition the points clouds into blocks to perform the ICP algorithm for each block in parallel by minimizing the cost function of the bundle adjustment equation updated with a regularity term. The regularity term may measure the difference between current estimates of the poses and previous or the initial estimates. The method may also minimize the bundle adjustment equation updated with a regularity term when solving the pose graph problem to merge the optimized poses from the blocks to make connections between the blocks.

The presently disclosed subject matter includes a system and a method of navigating an unmanned ground vehicle (UGV) vehicle comprising a scanning device and an Inertial Navigation System (INS) being operatively connected to at least one processor. Operating the scanning device for scanning an area surrounding the UGV, and generate scanning output data; Generating, based on the scanning output data, a map representing at least a part of the area, the map being relative to a location of the UGV and comprising cells, each cell is classified to a class selected from at least two classes, comprising traversable and non-traversable, and characterized by dimensions larger than an accumulated drift value of the INS over a predefined distance; receiving INS data indicative of a current location of the UGV and updating a location of the UGV relative to cells in the map based on the INS data.