Abstract: This document describes techniques, apparatuses, and systems for standard-definition (SD) to high-definition (HD) navigation route determination. An example route builder receives a navigation route generated for a host vehicle. The navigation route includes a list of waypoints generated by an SD map database. The route builder matches the list of waypoints to lane geometry data maintained in an HD map database and outputs HD navigation route to a vehicle controller. The HD navigation route includes the list of waypoints, additional waypoints, and lane geometry data. The vehicle controller can then operate the host vehicle in a roadway environment along the HD navigation route. In this way, the described techniques and systems can provide HD navigation routes required by some assisted-driving and autonomous-driving systems based on SD navigation routes.

Abstract: This document describes vehicle localization using map and vision data. For example, this document describes a localization system that obtains a map centerline point and a vision centerline point of a lane of a roadway. The localization system also obtains the position of the vehicle. The localization system can then compare the map centerline point and the vision centerline point to generate a lateral and a longitudinal correction relative to the vehicle's position. The lateral and longitudinal corrections are used to generate a corrected position. In this way, the described localization system can provide accurate vehicle localization that addresses potential drift caused by lapsed or inaccurate positioning data and allows for the operation of assisted-driving and autonomous-driving systems at higher speeds and on roadways with tighter curves.

Abstract: Methods and systems are described that enable radar detection prioritization based on downstream feedback. As a vehicle is traveling in a travel corridor, radar detections are received by a processor and feedback related to a downstream function is received from another processor that is executing the downstream function. For the radar detections that are determined to be within the travel corridor, respective priorities are assigned based on locations of the radar detections and the feedback related to the downstream function. The radar detections with the assigned priorities are then stored in a detection buffer along with indications of their respective assigned priorities. In this way, the detection buffer may be optimized for the downstream function by filtering out certain detections and prioritizing others. Consequently, computational loads on the downstream function are reduced while ensuring that important detections are received by the downstream function early.

Abstract: This document describes vehicle localization using map and vision data. For example, this document describes a localization system that obtains a map centerline point and a vision centerline point of a lane of a roadway. The localization system also obtains the position of the vehicle. The localization system can then compare the map centerline point and the vision centerline point to generate a lateral and a longitudinal correction relative to the vehicle's position. The lateral and longitudinal corrections are used to generate a corrected position. In this way, the described localization system can provide accurate vehicle localization that addresses potential drift caused by lapsed or inaccurate positioning data and allows for the operation of assisted-driving and autonomous-driving systems at higher speeds and on roadways with tighter curves.

Abstract: This document describes techniques, apparatuses, and systems for standard-definition (SD) to high-definition (HD) navigation route determination. An example route builder receives a navigation route generated for a host vehicle. The navigation route includes a list of waypoints generated by an SD map database. The route builder matches the list of waypoints to lane geometry data maintained in an HD map database and outputs HD navigation route to a vehicle controller. The HD navigation route includes the list of waypoints, additional waypoints, and lane geometry data. The vehicle controller can then operate the host vehicle in a roadway environment along the HD navigation route. In this way, the described techniques and systems can provide HD navigation routes required by some assisted-driving and autonomous-driving systems based on SD navigation routes.

Abstract: The techniques of this disclosure relate to a system for adjusting a focus of an image. A system includes a phased metalens configured to adjust a focus of an image detected by an imaging substrate of an image sensor to compensate for warpage of the imaging substrate. The phased metalens can achieve a near-diffraction-limited focusing over incoming light wavelengths using precisely defined nanoscale subwavelength resolution structures.

Abstract: This document describes techniques for localizing a vehicle to map data, for example, to enable assisted driving and automated driving within a road. A road model builder is described that uses vehicle location data to determine its position relative to map data obtained from a provider, which can be different than the location data's source. Using the vehicle position, the road model builder maintains a current lane segment for the vehicle and its relative position within the current lane segment. Based on its relative position, the road model builder determines whether a transition to another lane segment is appropriate before setting the current lane segment to be the other lane segment. The current lane segment, when provided as an input to an assisted-driving or automated-driving system, can enable safer operation of the vehicle and use fewer computing resources than other systems.

Abstract: The techniques of this disclosure relate to a system for adjusting a focus of an image. A system includes a phased metalens configured to adjust a focus of an image detected by an imaging substrate of an image sensor to compensate for warpage of the imaging substrate. The phased metalens can achieve a near-diffraction-limited focusing over incoming light wavelengths using precisely defined nanoscale subwavelength resolution structures.

Abstract: The techniques of this disclosure relate to a system for adjusting a focus of an image. A system includes a phased metalens configured to adjust a focus of an image detected by an imaging substrate of an image sensor to compensate for warpage of the imaging substrate. The phased metalens can achieve a near-diffraction-limited focusing over incoming light wavelengths using precisely defined nanoscale subwavelength resolution structures.

Abstract: Methods and systems are described that enable radar detection prioritization based on downstream feedback. As a vehicle is traveling in a travel corridor, radar detections are received by a processor and feedback related to a downstream function is received from another processor that is executing the downstream function. For the radar detections that are determined to be within the travel corridor, respective priorities are assigned based on locations of the radar detections and the feedback related to the downstream function. The radar detections with the assigned priorities are then stored in a detection buffer along with indications of their respective assigned priorities. In this way, the detection buffer may be optimized for the downstream function by filtering out certain detections and prioritizing others. Consequently, computational loads on the downstream function are reduced while ensuring that important detections are received by the downstream function early.

Abstract: The techniques of this disclosure relate to a system for adjusting a focus of an image. A system includes a phased metalens configured to adjust a focus of an image detected by an imaging substrate of an image sensor to compensate for warpage of the imaging substrate. The phased metalens can achieve a near-diffraction-limited focusing over incoming light wavelengths using precisely defined nanoscale subwavelength resolution structures.

Abstract: The techniques of this disclosure relate to a system for adjusting a focus of an image. A system includes a phased metalens configured to adjust a focus of an image detected by an imaging substrate of an image sensor. The phased metalens is further configured to adjust a property of light that reaches the imaging substrate based on a change in a flatness of the imaging substrate. The property of the light that reaches the imaging substrate includes a phase of all the light that reaches the imaging substrate at a same time. The phased metalens accomplishes this by achieving near-diffraction-limited focusing over the incoming light wavelengths using precisely defined nanoscale subwavelength resolution structures.