Patents by Inventor Mengxi WU
Mengxi WU has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11867515Abstract: According to an aspect of an embodiment, operations may comprise accessing a set of vehicle poses of one or more vehicles; for each of the set of vehicle poses, accessing a high definition (HD) map of a geographical region surrounding the vehicle pose, with the HD map comprising a three-dimensional (3D) representation of the geographical region, determining a measure of constrainedness for the vehicle pose, with the measure of constrainedness representing a confidence for performing localization for the vehicle pose based on 3D structures surrounding the vehicle pose, and storing the measure of constrainedness for the vehicle pose; and for each of the geographical regions surrounding each of the set of vehicle poses, determining a measure of constrainedness for the geographical region based on measures of constrainedness of vehicle poses within the geographical region, and storing the measure of constrainedness for the geographical region.Type: GrantFiled: July 19, 2022Date of Patent: January 9, 2024Assignee: NVIDIA CORPORATIONInventors: Di Zeng, Mengxi Wu, Derik Schroeter
-
Patent number: 11835342Abstract: Operations of the present disclosure include obtaining a first measure of velocity of a vehicle based on a plurality of locations determined for the vehicle. The operations also include obtaining, based on IMU measurements of an inertial measurement unit (IMU) of the vehicle, a second measure of velocity of the vehicle. In addition, the operations include performing calibration of the IMU based on the first measure of velocity and the second measure of velocity.Type: GrantFiled: June 29, 2020Date of Patent: December 5, 2023Assignee: NVIDIA CORPORATIONInventors: Di Zeng, Mengxi Wu
-
Publication number: 20230204784Abstract: According to an aspect of an embodiment, operations may comprise receiving, from a LIDAR mounted on a vehicle, a first 3D point cloud comprising points of a region around the vehicle as observed by the LIDAR. The operations may also comprise accessing an HD map comprising a second 3D point cloud comprising points of the region around the vehicle. The operations may also comprise segmenting LIDAR ground points from LIDAR non-ground points in the first 3D point cloud. The operations may also comprise segmenting map ground points from map non-ground points in the second 3D point cloud. The operations may also comprise determining a pose of the vehicle by matching the LIDAR ground points to the map ground points and by matching the LIDAR non-ground points to the map non-ground points.Type: ApplicationFiled: February 28, 2023Publication date: June 29, 2023Inventors: Di Zeng, Derik Schroeter, Mengxi Wu
-
Patent number: 11619724Abstract: According to an aspect of an embodiment, operations may comprise (a) accessing a portion of a high definition (HD) map comprising a point cloud of a region through which a vehicle is driving, (b) identifying a base LIDAR from a plurality of LIDARs mounted on the vehicle, (c) for each of the LIDARs: receiving a LIDAR scan comprising a point cloud of the region, and determining a pose for the LIDAR, (d) for each LIDAR other than the base LIDAR, determining a transform for the LIDAR with respect to the base LIDAR, (e) repeating (c) to generate a plurality of samples, (f) for each of the samples, repeating (d) to determine a plurality of transforms for each LIDAR with respect to the base LIDAR, and (g) calibrating each of the LIDARs other than the base LIDAR by determining an aggregate transform for the LIDAR.Type: GrantFiled: June 25, 2020Date of Patent: April 4, 2023Assignee: NVIDIA CORPORATIONInventors: Di Zeng, Mengxi Wu
-
Patent number: 11598876Abstract: According to an aspect of an embodiment, operations may comprise receiving, from a LIDAR mounted on a vehicle, a first 3D point cloud comprising points of a region around the vehicle as observed by the LIDAR. The operations may also comprise accessing an HD map comprising a second 3D point cloud comprising points of the region around the vehicle. The operations may also comprise segmenting LIDAR ground points from LIDAR non-ground points in the first 3D point cloud. The operations may also comprise segmenting map ground points from map non-ground points in the second 3D point cloud. The operations may also comprise determining a pose of the vehicle by matching the LIDAR ground points to the map ground points and by matching the LIDAR non-ground points to the map non-ground points.Type: GrantFiled: June 15, 2020Date of Patent: March 7, 2023Assignee: NVIDIA CORPORATIONInventors: Di Zeng, Derik Schroeter, Mengxi Wu
-
Patent number: 11594014Abstract: According to an aspect of an embodiment, operations may comprise obtaining a first point cloud that includes a first point. The operations also comprises obtaining a second point cloud that is a copy of the first point cloud and that includes a second point that is a copy of the first point. The operations also comprises moving the second point cloud with respect to the first point cloud according to a first vector. The operations also comprises identifying a closest point of the first point cloud that is closest to the second point of the second point cloud. The operations also comprises determining a second vector between the closest point and the second point. The operations also comprises determining a measure of usefulness of the first point based on the first vector and the second vector. The operations also comprises indicating the measure of usefulness of the first point.Type: GrantFiled: June 22, 2020Date of Patent: February 28, 2023Assignee: NVIDIA CORPORATIONInventors: Di Zeng, Mengxi Wu
-
Publication number: 20230018923Abstract: Operations may comprise obtaining a plurality of light detection and ranging (LIDAR) scans of a region. The operations may also comprise identifying a plurality of LIDAR poses that correspond to the plurality of LIDAR scans. In addition, the operations may comprise identifying, as a plurality of keyframes, a plurality of images of the region that are captured during capturing of the plurality of LIDAR scans. The operations may also comprise determining, based on the plurality of LIDAR poses, a plurality of camera poses that correspond to the keyframes. Further, the operations may comprise identifying a plurality of two-dimensional (2D) keypoints in the keyframes. The operations also may comprise generating one or more three-dimensional (3D) keypoints based on the plurality of 2D keypoints and the respective camera poses of the plurality of keyframes.Type: ApplicationFiled: June 21, 2022Publication date: January 19, 2023Inventors: Ronghua Zhang, Derik Schroeter, Mengxi Wu, Di Zeng
-
Publication number: 20220373337Abstract: According to an aspect of an embodiment, operations may comprise accessing a set of vehicle poses of one or more vehicles; for each of the set of vehicle poses, accessing a high definition (HD) map of a geographical region surrounding the vehicle pose, with the HD map comprising a three-dimensional (3D) representation of the geographical region, determining a measure of constrainedness for the vehicle pose, with the measure of constrainedness representing a confidence for performing localization for the vehicle pose based on 3D structures surrounding the vehicle pose, and storing the measure of constrainedness for the vehicle pose; and for each of the geographical regions surrounding each of the set of vehicle poses, determining a measure of constrainedness for the geographical region based on measures of constrainedness of vehicle poses within the geographical region, and storing the measure of constrainedness for the geographical region.Type: ApplicationFiled: July 19, 2022Publication date: November 24, 2022Inventors: Di Zeng, Mengxi Wu, Derik Schroeter
-
Patent number: 11491486Abstract: Aspects of the present disclosure describe systems, methods, and structures for acoustic wave-based separation of particulates in a fluidic flow. Illustrative systems, methods, and structures according to aspects of the present disclosure may advantageously provide for the continuous, label-free, non-invasive separation of the particulates that include—among other types—difficult-to-separate biological particulates and in particular those in blood including circulating tumor cells and micro-blood-borne particles and other subgroups of extracellular vesicles including nanoscale exosomes.Type: GrantFiled: August 29, 2018Date of Patent: November 8, 2022Assignee: Duke UniversityInventors: Jun Huang, Mengxi Wu
-
Patent number: 11391578Abstract: According to an aspect of an embodiment, operations may comprise accessing a set of vehicle poses of one or more vehicles; for each of the set of vehicle poses, accessing a high definition (HD) map of a geographical region surrounding the vehicle pose, with the HD map comprising a three-dimensional (3D) representation of the geographical region, determining a measure of constrainedness for the vehicle pose, with the measure of constrainedness representing a confidence for performing localization for the vehicle pose based on 3D structures surrounding the vehicle pose, and storing the measure of constrainedness for the vehicle pose; and for each of the geographical regions surrounding each of the set of vehicle poses, determining a measure of constrainedness for the geographical region based on measures of constrainedness of vehicle poses within the geographical region, and storing the measure of constrainedness for the geographical region.Type: GrantFiled: July 2, 2020Date of Patent: July 19, 2022Assignee: NVIDIA CORPORATIONInventors: Di Zeng, Mengxi Wu, Derik Schroeter
-
Patent number: 11367208Abstract: Operations may comprise obtaining a plurality of light detection and ranging (LIDAR) scans of a region. The operations may also comprise identifying a plurality of LIDAR poses that correspond to the plurality of LIDAR scans. In addition, the operations may comprise identifying, as a plurality of keyframes, a plurality of images of the region that are captured during capturing of the plurality of LIDAR scans. The operations may also comprise determining, based on the plurality of LIDAR poses, a plurality of camera poses that correspond to the keyframes. Further, the operations may comprise identifying a plurality of two-dimensional (2D) keypoints in the keyframes. The operations also may comprise generating one or more three-dimensional (3D) keypoints based on the plurality of 2D keypoints and the respective camera poses of the plurality of keyframes.Type: GrantFiled: June 25, 2020Date of Patent: June 21, 2022Assignee: NVIDIA CORPORATIONInventors: Ronghua Zhang, Derik Schroeter, Mengxi Wu, Di Zeng
-
Publication number: 20210292787Abstract: The present invention relates to a pseudotyped insect baculovirus gene transfer system and a virus for shrimps, and a construction method and use thereof. The present invention belongs to the technical field of genetic engineering. The pseudotyped insect baculovirus gene transfer system for shrimps disclosed in the present invention includes a Bac-to-Bac insect baculovirus expression system, an expression plasmid carrying shrimp virus envelope protein gene and an insect packaging cell. The present invention can achieve stable and efficient transfer and expression of a foreign gene in a shrimp tissue and cell.Type: ApplicationFiled: August 19, 2020Publication date: September 23, 2021Inventors: Huarong GUO, Mengxi WU
-
Patent number: 11085863Abstract: The present disclosure provides an online monitoring and source apportionment method for atmospheric particles containing heavy metals, and belongs to the technical field of online quantification and source tracing of atmospheric particles containing heavy metals. The single particle aerosol mass spectrometer and X-ray fluorescence spectrometer are combined to quickly determine the concentration, time series, chemical compositions and mixing state of atmospheric particles containing heavy metals from both qualitative and quantitative perspectives. A heavy metal-containing particle mass concentration limit system is incorporated into the X-ray fluorescence spectrometer. Once the mass concentration of a particle containing heavy metals exceeds the standard, the aerosol mass spectrometer can immediately receive this alert through the information transmission system.Type: GrantFiled: February 5, 2021Date of Patent: August 10, 2021Assignee: Jinan UniversityInventors: Mei Li, Mengxi Wu, Chunlei Cheng
-
Publication number: 20210156781Abstract: The present disclosure provides an online monitoring and source apportionment method for atmospheric particles containing heavy metals, and belongs to the technical field of online quantification and source tracing of atmospheric particles containing heavy metals. The single particle aerosol mass spectrometer and X-ray fluorescence spectrometer are combined to quickly determine the concentration, time series, chemical compositions and mixing state of atmospheric particles containing heavy metals from both qualitative and quantitative perspectives. A heavy metal-containing particle mass concentration limit system is incorporated into the X-ray fluorescence spectrometer. Once the mass concentration of a particle containing heavy metals exceeds the standard, the aerosol mass spectrometer can immediately receive this alert through the information transmission system.Type: ApplicationFiled: February 5, 2021Publication date: May 27, 2021Inventors: Mei LI, Mengxi WU, Chunlei CHENG
-
Publication number: 20210154668Abstract: Aspects of the present disclosure describe systems, methods, and structures for acoustic wave-based separation of particulates in a fluidic flow. Illustrative systems, methods, and structures according to aspects of the present disclosure may advantageously provide for the continuous, label-free, non-invasive separation of the particulates that include—among other types—difficult-to-separate biological particulates and in particular those in blood including circulating tumor cells and micro-blood-borne particles and other subgroups of extracellular vesicles including nanoscale exosomes.Type: ApplicationFiled: August 29, 2018Publication date: May 27, 2021Inventors: Jun HUANG, Mengxi WU
-
Publication number: 20210003404Abstract: According to an aspect of an embodiment, operations may comprise accessing a set of vehicle poses of one or more vehicles; for each of the set of vehicle poses, accessing a high definition (HD) map of a geographical region surrounding the vehicle pose, with the HD map comprising a three-dimensional (3D) representation of the geographical region, determining a measure of constrainedness for the vehicle pose, with the measure of constrainedness representing a confidence for performing localization for the vehicle pose based on 3D structures surrounding the vehicle pose, and storing the measure of constrainedness for the vehicle pose; and for each of the geographical regions surrounding each of the set of vehicle poses, determining a measure of constrainedness for the geographical region based on measures of constrainedness of vehicle poses within the geographical region, and storing the measure of constrainedness for the geographical region.Type: ApplicationFiled: July 2, 2020Publication date: January 7, 2021Inventors: Di Zeng, Mengxi Wu, Derik Schroeter
-
Publication number: 20200408887Abstract: According to an aspect of an embodiment, operations may comprise (a) accessing a portion of a high definition (HD) map comprising a point cloud of a region through which a vehicle is driving, (b) identifying a base LIDAR from a plurality of LIDARs mounted on the vehicle, (c) for each of the LIDARs: receiving a LIDAR scan comprising a point cloud of the region, and determining a pose for the LIDAR, (d) for each LIDAR other than the base LIDAR, determining a transform for the LIDAR with respect to the base LIDAR, (e) repeating (c) to generate a plurality of samples, (f) for each of the samples, repeating (d) to determine a plurality of transforms for each LIDAR with respect to the base LIDAR, and (g) calibrating each of the LIDARs other than the base LIDAR by determining an aggregate transform for the LIDAR.Type: ApplicationFiled: June 25, 2020Publication date: December 31, 2020Inventors: Di Zeng, Mengxi Wu
-
Publication number: 20200408529Abstract: Operations of the present disclosure include obtaining a first measure of velocity of a vehicle based on a plurality of locations determined for the vehicle. The operations also include obtaining, based on IMU measurements of an inertial measurement unit (IMU) of the vehicle, a second measure of velocity of the vehicle. In addition, the operations include performing calibration of the IMU based on the first measure of velocity and the second measure of velocity.Type: ApplicationFiled: June 29, 2020Publication date: December 31, 2020Inventors: Di Zeng, Mengxi Wu
-
Publication number: 20200410702Abstract: Operations may comprise obtaining a plurality of light detection and ranging (LIDAR) scans of a region. The operations may also comprise identifying a plurality of LIDAR poses that correspond to the plurality of LIDAR scans. In addition, the operations may comprise identifying, as a plurality of keyframes, a plurality of images of the region that are captured during capturing of the plurality of LIDAR scans. The operations may also comprise determining, based on the plurality of LIDAR poses, a plurality of camera poses that correspond to the keyframes. Further, the operations may comprise identifying a plurality of two-dimensional (2D) keypoints in the keyframes. The operations also may comprise generating one or more three-dimensional (3D) keypoints based on the plurality of 2D keypoints and the respective camera poses of the plurality of keyframes.Type: ApplicationFiled: June 25, 2020Publication date: December 31, 2020Inventors: Ronghua Zhang, Derik Schroeter, Mengxi Wu, Di Zeng
-
Publication number: 20200401845Abstract: According to an aspect of an embodiment, operations may comprise obtaining a first point cloud that includes a first point. The operations also comprises obtaining a second point cloud that is a copy of the first point cloud and that includes a second point that is a copy of the first point. The operations also comprises moving the second point cloud with respect to the first point cloud according to a first vector. The operations also comprises identifying a closest point of the first point cloud that is closest to the second point of the second point cloud. The operations also comprises determining a second vector between the closest point and the second point. The operations also comprises determining a measure of usefulness of the first point based on the first vector and the second vector. The operations also comprises indicating the measure of usefulness of the first point.Type: ApplicationFiled: June 22, 2020Publication date: December 24, 2020Inventors: Di Zeng, Mengxi Wu