Abstract: An end-to-end system for data generation, map creation using the generated data, and localization to the created map is disclosed. Mapstreams—or streams of sensor data, perception outputs from deep neural networks (DNNs), and/or relative trajectory data—corresponding to any number of drives by any number of vehicles may be generated and uploaded to the cloud. The mapstreams may be used to generate map data—and ultimately a fused high definition (HD) map—that represents data generated over a plurality of drives. When localizing to the fused HD map, individual localization results may be generated based on comparisons of real-time data from a sensor modality to map data corresponding to the same sensor modality. This process may be repeated for any number of sensor modalities and the results may be fused together to determine a final fused localization result.

Abstract: Embodiments of the present disclosure relate to a system and method used to localize one or more systems using 2D map data. The method may include determining an image location of a representation of a portion of an object in an image corresponding to an environment. In some embodiments, the method may additionally include determining one or more predicted image locations corresponding to the image location of the representation of the portion of the object. The method may additionally include comparing one or more ground plane locations of the portion of the object with the one or more predicted image locations, and determining a cost based at least on the comparison between the one or more ground plane locations and the one or more predicted image locations. Further, the method may include localizing a system to the 2D map data based on the determined cost.

Abstract: An end-to-end system for data generation, map creation using the generated data, and localization to the created map is disclosed. Mapstreams—or streams of sensor data, perception outputs from deep neural networks (DNNs), and/or relative trajectory data—corresponding to any number of drives by any number of vehicles may be generated and uploaded to the cloud. The mapstreams may be used to generate map data—and ultimately a fused high definition (HD) map—that represents data generated over a plurality of drives. When localizing to the fused HD map, individual localization results may be generated based on comparisons of real-time data from a sensor modality to map data corresponding to the same sensor modality. This process may be repeated for any number of sensor modalities and the results may be fused together to determine a final fused localization result.

Abstract: One or more embodiments of the present disclosure relate to generating RADAR (RAdio Detection And Ranging) point clouds based on RADAR data obtained using one or more RADAR sensors disposed on one or more ego-machines. In these or other embodiments, the RADAR point clouds may be communicated to a distributed map system that is configured to generate map data based on the RADAR point clouds. In some embodiments of the present disclosure, certain compression operations may be performed on the RADAR point clouds to reduce the amount of data that is communicated from the ego-machines to the map system.

Abstract: In various examples, path-specific trackers may be initialized and used to localize a machine (e.g., an autonomous or semi-autonomous machine or vehicle) with respect to a specific path in an environment. For instance, when the machine passes through a junction of multiple road segments, a respective tracker may be initialized for each road segment, and the trackers may be placed at respective candidate locations along each of the road segments. The candidate locations may represent possible locations of the machine along the road segments. Using various input data, a determination may be made regarding which tracker—or candidate location—most closely corresponds to the actual location of the machine subsequent to the junction. In some examples, the tracker may be selected for tracking the location of the machine along the current road segment while the other trackers may be terminated or otherwise removed.

Abstract: In various examples, junction points corresponding to locations where disparate lanes deviate from one another may be determined and used to associate (e.g., match) perceived lanes with corresponding, mapped road segments. For instance, the systems and methods of the present disclosure may use perception data to determine locations of junction points where two or more lanes deviate from one another, as well as to determine lateral distances between adjacent lanes. Using the junction points and/or the lateral distances, the lanes may be sorted into various lane groups, where each lane group may correspond to a different road segment. In some examples, the systems may match individual lanes or lane groups to respective road segments of a map based on the junction points corresponding to mapped road junctions and/or lane geometry corresponding to mapped road topology.

Abstract: In various examples, probabilistic-based techniques may be used to predict intended paths of machines through an environment. For instance, various input data from perception systems, localization systems, mapping systems, and/or other sources of data may be used to determine occupant intent and compute scores associated with road segments in an environment. The scores may indicate a probability that certain road segments are part of the occupant's intended path for the machine, and the scores may be aggregated for each of the road segments across multiple instances of receiving an analyzing the input data. In some instances, a highest scoring road segment(s) may be selected as part of a predicted path of the machine. For instance, at a junction(s) where multiple road segments meet, the highest scoring road segment(s) may be selected as the predicted path.

Abstract: Embodiments of the present disclosure relate to performance by a machine of one or more planning, control, or navigation operations using a point cloud. The point cloud being generated using sensor data selected from a sensor data set obtained using one or more external sensors of the machine. The selected sensor data being selected for inclusion in the point cloud based at least on one or more criteria individually corresponding to generation of the point cloud.

Abstract: The present application relates to a microfluidic fully-automatic platelet detection method and a platelet analysis and homogenization system, where the microfluidic fully-automatic platelet detection method performs a detecting and sampling process of the platelet rich plasma and a detecting and sampling process of the platelet poor plasma on the same platelet analysis and homogenization device, the entire device is small in volume, neither require arrangement of any additional centrifuge device for preparing the platelet poor plasma, nor require arrangement of any additional magnetic stirring device for stirring, the detection steps are simplified, the cost is reduced, and the detection efficiency is improved.

Abstract: Embodiments of the present disclosure relate to generating RADAR (RAdio Detection And Ranging) point clouds based on RADAR data obtained from one or more RADAR sensors disposed on one or more ego-machines. In these or other embodiments, the RADAR point clouds may be used to generate map data. Additionally or alternatively, the RADAR point clouds may be used for performing localization.

Abstract: One or more embodiments of the present disclosure relate to generation of map data. In these or other embodiments, the generation of the map data may include determining whether objects indicated by the sensor data are static objects or dynamic objects. Additionally or alternatively, sensor data may be removed or included in the map data based on determinations as to whether it corresponds to static objects or dynamic objects.

Abstract: One or more embodiments of the present disclosure relate to generation of map data. In these or other embodiments, the generation of the map data may include determining whether objects indicated by the sensor data are static objects or dynamic objects. Additionally or alternatively, sensor data may be removed or included in the map data based on determinations as to whether it corresponds to static objects or dynamic objects.

Abstract: Embodiments of the present disclosure relate to a system and method used to localize one or more systems using 2D map data. The method may include determining an image location of a representation of a portion of an object in an image corresponding to an environment. In some embodiments, the method may additionally include determining one or more predicted image locations corresponding to the image location of the representation of the portion of the object. The method may additionally include comparing one or more ground plane locations of the portion of the object with the one or more predicted image locations, and determining a cost based at least on the comparison between the one or more ground plane locations and the one or more predicted image locations. Further, the method may include localizing a system to the 2D map data based on the determined cost.

Abstract: In various examples, accuracy determinations for localization in autonomous and semi-autonomous systems and applications are described herein. Systems and methods are disclosed that determine one or more errors associated with vehicle localization using various types of sensor data generated using a vehicle. For instance, a first component of the vehicle may use a map and first sensor data to determine an estimated pose of the vehicle. A second component of the vehicle may then determine the error(s) associated with the estimated pose based on both actual motion of the vehicle within the environment, as determined using second sensor data, and comparing features represented by the first sensor data to features represented by the map. In some examples, the second component may further determine information associated with the error(s), such as one or more uncertainties associated with the error(s).

Abstract: One or more embodiments of the present disclosure relate to generating RADAR (RAdio Detection And Ranging) point clouds based on RADAR data obtained from one or more RADAR sensors disposed on one or more ego-machines. In these or other embodiments, the RADAR point clouds may be communicated to a distributed map system that is configured to generate map data based on the RADAR point clouds. In some embodiments of the present disclosure, certain compression operations may be performed on the RADAR point clouds to reduce the amount of data that is communicated from the ego-machines to the map system.

Abstract: Provided are a function switchable random access memory, including: two electromagnetic portions configured to connect a current; a magnetic recording portion between the two electromagnetic portions and including a spin-orbit coupling layer and a magnetic tunnel junction; a pinning region between each of the electromagnetic portions and the magnetic recording portion; a cut-off region on a side of each of the electromagnetic portions opposite to the pinning region, the spin-orbit coupling layer is configured to generate a spin current under an action of the current; the two electromagnetic portions is configured to generate two magnetic domains with magnetization pointing in opposite directions under an action of the spin current; the magnetic tunnel junction is configured to generate a magnetic domain wall based on the two opposite magnetic domains and is configured to drive the magnetic domain wall to reciprocate under the action of the spin current.

Abstract: An end-to-end system for data generation, map creation using the generated data, and localization to the created map is disclosed. Mapstreams—or streams of sensor data, perception outputs from deep neural networks (DNNs), and/or relative trajectory data—corresponding to any number of drives by any number of vehicles may be generated and uploaded to the cloud. The mapstreams may be used to generate map data—and ultimately a fused high definition (HD) map—that represents data generated over a plurality of drives. When localizing to the fused HD map, individual localization results may be generated based on comparisons of real-time data from a sensor modality to map data corresponding to the same sensor modality. This process may be repeated for any number of sensor modalities and the results may be fused together to determine a final fused localization result.

Abstract: One or more embodiments of the present disclosure relate to generating RADAR (RAdio Detection And Ranging) point clouds based on RADAR data obtained from one or more RADAR sensors disposed on one or more ego-machines. In these or other embodiments, the RADAR point clouds may be communicated to a distributed map system that is configured to generate map data based on the RADAR point clouds. In some embodiments of the present disclosure, certain compression operations may be performed on the RADAR point clouds to reduce the amount of data that is communicated from the ego-machines to the map system.

Abstract: One or more embodiments of the present disclosure relate to generation of map data. In these or other embodiments, the generation of the map data may include determining whether objects indicated by the sensor data are static objects or dynamic objects. Additionally or alternatively, sensor data may be removed or included in the map data based on determinations as to whether it corresponds to static objects or dynamic objects.