A navigational system for a host vehicle may comprise at least one processing device. The processing device may be programmed to receive a first output and a second output associated with a host vehicle, wherein at least one of the outputs is received from a sensor onboard the host vehicle. The processing device may identify a target object in the first output and determine whether a characteristic of the target object triggers a navigational constraint by verifying the identification of the target object based on the first output; and, if the navigational constraint is not verified based on the first output, then verifying the identification of the target object based on a combination of the first output and the second output. In response to the verification, the processing device may cause at least one navigational change to the host vehicle.

Example implementations may relate to sun-aware vehicle routing. In particular, a computing system of a vehicle may determine an expected position of the sun relative to a geographic area. Based on the expected position, the computing system may make a determination that travel of the vehicle through certain location(s) within the geographic area is expected to result in the sun being proximate to an object within a field of view of the vehicle's image capture device. Responsively, the computing system may generate a route for the vehicle in the geographic area based at least on the route avoiding travel of the vehicle through these certain location(s), and may then operate the vehicle to travel in accordance with the generated route. Ultimately, this may help reduce or prevent situations where quality of image(s) degrades due to sunlight, which may allow for use of these image(s) as basis for operating the vehicle.

A controller of a vehicle obtains lane identifier information indicative of identifiers that define a lane of a road along which the vehicle will travel, determines distances between the lane identifiers at a plurality of different points along the lane based on the lane identifier information to obtain lane width information, determines a depth or distance from the vehicle to each of the plurality of different points along the lane using the lane width information and a known or assumed lane width to obtain an uncorrected lane topology profile, transforms the uncorrected lane topology profile to an inertial frame of reference of the vehicle based on a monitored orientation of the vehicle by a set of sensors to obtain a corrected lane topology profile, and controls an autonomous driving feature of the vehicle based on the corrected lane topology profile to proactively compensate for an upcoming road topology variation.

Techniques and methods for performing collision monitoring using error models. For instance, a vehicle may generate sensor data using one or more sensors. The vehicle may then analyze the sensor data using systems in order to determine parameters associated with the vehicle and parameters associated with another object. Additionally, the vehicle may process the parameters associated with the vehicle using error models associated with the systems in order to determine a distribution of estimated locations associated with the vehicle. The vehicle may also process the parameters associated with the object using the error models in order to determine a distribution of estimated locations associated with the object. Using the distributions of estimated locations, the vehicle may determine the probability of collision between the vehicle and the object.

Techniques and methods for performing collision monitoring using system data. For instance, a vehicle may generate sensor data using one or more sensors. The vehicle may then analyze the sensor data using systems in order to determine parameters associated with the vehicle and parameters associated with another object. Additionally, the vehicle may determine uncertainties associated with the parameters and then process the parameters using the uncertainties. Based at least in part on the processing, the vehicle may determine a distribution of estimated locations associated with the vehicle and a distribution of estimated locations associated with the object. Using the distributions of estimated locations, the vehicle may determine the probability of collision between the vehicle and the object.

Examples relating to vehicle velocity calculation using radar technology are described. An example method performed by a computing system may involve, while a vehicle is moving on a road, receiving, from two or more radar sensors mounted at different locations on the vehicle, radar data representative of an environment of the vehicle. The method may involve, based on the data, detecting at least one scatterer in the environment. The method may involve making a determination of a likelihood that the at least one scatterer is stationary with respect to the vehicle. The method may involve, based on the determination being that the likelihood is at least equal to a predefined confidence threshold, calculating a velocity of the vehicle based on the data from the sensors. The calculated velocity may include an angular and linear velocity. Further, the method may involve controlling the vehicle based on the calculated velocity.

Aspects of the disclosure relate to detecting unmapped drivable road surfaces. In one instance, sensor data captured by a sensor of an autonomous vehicle may be projected onto a grid having a plurality of cells. The plurality of cells may be classified by generating a label for each of the plurality of cells. Each label may identifies whether or not a corresponding cell contains a drivable surface. Ones of the plurality of cells may be clustered based on the labels to form a cluster of cells. An area of the cluster of cells may be compared to a map. Whether the area of the cluster of cells is an unmapped drivable road surface may be determined based on the comparison.

Example implementations may relate to sun-aware vehicle routing. In particular, a computing system of a vehicle may determine an expected position of the sun relative to a geographic area. Based on the expected position, the computing system may make a determination that travel of the vehicle through certain location(s) within the geographic area is expected to result in the sun being proximate to an object within a field of view of the vehicle's image capture device. Responsively, the computing system may generate a route for the vehicle in the geographic area based at least on the route avoiding travel of the vehicle through these certain location(s), and may then operate the vehicle to travel in accordance with the generated route. Ultimately, this may help reduce or prevent situations where quality of image(s) degrades due to sunlight, which may allow for use of these image(s) as basis for operating the vehicle.

Some embodiments of the invention include a method for updating an occlusion probability map. An occlusion probability map represents the probability that a given portion of the sensor field is occluded from one or more sensors. In some embodiments, a method may include receiving field of view data from a sensor system; producing a probabilistic model of the sensor field of view; and updating an occlusion probability map using the probabilistic model and field of view data.

An illustrative example embodiment of a system for controlling a vehicle includes at least one sensor configured to detect at least one localization reference and at least one processor configured to determine a location of the vehicle with a first precision based on an indication from the at least one sensor while the vehicle is traveling in a first lane of a roadway. The processor is configured to determine that at least one characteristic of the first precision is below a threshold and, based on the at least one characteristic being below the threshold, maneuver the vehicle to a second lane of the roadway.