Patents by Inventor Min Bai

Min Bai 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: 12248075
    Abstract: Systems and methods for identifying travel way features in real time are provided. A method can include receiving two-dimensional and three-dimensional data associated with the surrounding environment of a vehicle. The method can include providing the two-dimensional data as one or more input into a machine-learned segmentation model to output a two-dimensional segmentation. The method can include fusing the two-dimensional segmentation with the three-dimensional data to generate a three-dimensional segmentation. The method can include storing the three-dimensional segmentation in a classification database with data indicative of one or more previously generated three-dimensional segmentations. The method can include providing one or more datapoint sets from the classification database as one or more inputs into a machine-learned enhancing model to obtain an enhanced three-dimensional segmentation.
    Type: Grant
    Filed: May 23, 2024
    Date of Patent: March 11, 2025
    Assignee: AURORA OPERATIONS, INC.
    Inventors: Raquel Urtasun, Min Bai, Shenlong Wang
  • Publication number: 20250002050
    Abstract: Techniques for improving the performance of an autonomous vehicle (AV) by automatically annotating objects surrounding the AV are described herein. A system can obtain sensor data from a sensor coupled to the AV and generate an initial object trajectory for an object using the sensor data. Additionally, the system can determine a fixed value for the object size of the object based on the initial object trajectory. Moreover, the system can generate an updated initial object trajectory, wherein the object size corresponds to the fixed value. Furthermore, the system can determine, based on the sensor data and the updated initial object trajectory, a refined object trajectory. Subsequently, the system can generate a multi-dimensional label for the object based on the refined object trajectory. A motion plan for controlling the AV can be generated based on the multi-dimensional label.
    Type: Application
    Filed: September 12, 2024
    Publication date: January 2, 2025
    Inventors: Bin Yang, Ming Liang, Wenyuan Zeng, Min Bai, Raquel Urtasun
  • Publication number: 20240427022
    Abstract: Systems and methods for identifying travel way features in real time are provided. A method can include receiving two-dimensional and three-dimensional data associated with the surrounding environment of a vehicle. The method can include providing the two-dimensional data as one or more input into a machine-learned segmentation model to output a two-dimensional segmentation. The method can include fusing the two-dimensional segmentation with the three-dimensional data to generate a three-dimensional segmentation. The method can include storing the three-dimensional segmentation in a classification database with data indicative of one or more previously generated three-dimensional segmentations. The method can include providing one or more datapoint sets from the classification database as one or more inputs into a machine-learned enhancing model to obtain an enhanced three-dimensional segmentation.
    Type: Application
    Filed: May 23, 2024
    Publication date: December 26, 2024
    Inventors: Raquel Urtasun, Min Bai, Shenlong Wang
  • Patent number: 12116015
    Abstract: Techniques for improving the performance of an autonomous vehicle (AV) by automatically annotating objects surrounding the AV are described herein. A system can obtain sensor data from a sensor coupled to the AV and generate an initial object trajectory for an object using the sensor data. Additionally, the system can determine a fixed value for the object size of the object based on the initial object trajectory. Moreover, the system can generate an updated initial object trajectory, wherein the object size corresponds to the fixed value. Furthermore, the system can determine, based on the sensor data and the updated initial object trajectory, a refined object trajectory. Subsequently, the system can generate a multi-dimensional label for the object based on the refined object trajectory. A motion plan for controlling the AV can be generated based on the multi-dimensional label.
    Type: Grant
    Filed: November 17, 2021
    Date of Patent: October 15, 2024
    Assignee: AURORA OPERATIONS, INC.
    Inventors: Bin Yang, Ming Liang, Wenyuan Zeng, Min Bai, Raquel Urtasun
  • Patent number: 12032067
    Abstract: Systems and methods for identifying travel way features in real time are provided. A method can include receiving two-dimensional and three-dimensional data associated with the surrounding environment of a vehicle. The method can include providing the two-dimensional data as one or more input into a machine-learned segmentation model to output a two-dimensional segmentation. The method can include fusing the two-dimensional segmentation with the three-dimensional data to generate a three-dimensional segmentation. The method can include storing the three-dimensional segmentation in a classification database with data indicative of one or more previously generated three-dimensional segmentations. The method can include providing one or more datapoint sets from the classification database as one or more inputs into a machine-learned enhancing model to obtain an enhanced three-dimensional segmentation.
    Type: Grant
    Filed: December 10, 2021
    Date of Patent: July 9, 2024
    Assignee: UATC, LLC
    Inventors: Raquel Urtasun, Min Bai, Shenlong Wang
  • Patent number: 12008792
    Abstract: Adjustments to bounding shapes for detected objects in image data may be independently determined. A bounding shape for an object detected in image data may be obtained. Independently determined adjustments for one or more edges of the bounding shape may be determined according to a multi-scale feature map generated from different resolutions of the image data that is provided as input to different dimension decoders to determine the adjustments to the bounding shape and respective confidence scores for the adjustments. The confidence scores are evaluated with respect to a confidence threshold to determine whether to provide the adjustments to the one or more edges of the bounding shape.
    Type: Grant
    Filed: December 10, 2021
    Date of Patent: June 11, 2024
    Assignee: Amazon Technologies, Inc.
    Inventors: Min Bai, Jonathan Buck, Patrick Guy Haffner, Kumar Hemachandra Chellapilla, Li Erran Li
  • Patent number: 11972606
    Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.
    Type: Grant
    Filed: May 8, 2023
    Date of Patent: April 30, 2024
    Assignee: UATC, LLC
    Inventors: Min Bai, Gellert Sandor Mattyus, Namdar Homayounfar, Shenlong Wang, Shrinidihi Kowshika Lakshmikanth, Raquel Urtasun
  • Publication number: 20230274540
    Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.
    Type: Application
    Filed: May 8, 2023
    Publication date: August 31, 2023
    Inventors: Min Bai, Gellert Sandor Mattyus, Namdar Homayounfar, Shenlong Wang, Shrinidihi Kowshika Lakshmikanth, Raquel Urtasun
  • Patent number: 11682196
    Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.
    Type: Grant
    Filed: June 25, 2021
    Date of Patent: June 20, 2023
    Assignee: UATC, LLC
    Inventors: Min Bai, Gellert Sandor Mattyus, Namdar Homayounfar, Shenlong Wang, Shrindihi Kowshika Lakshmikanth, Raquel Urtasun
  • Publication number: 20220153310
    Abstract: Techniques for improving the performance of an autonomous vehicle (AV) by automatically annotating objects surrounding the AV are described herein. A system can obtain sensor data from a sensor coupled to the AV and generate an initial object trajectory for an object using the sensor data. Additionally, the system can determine a fixed value for the object size of the object based on the initial object trajectory. Moreover, the system can generate an updated initial object trajectory, wherein the object size corresponds to the fixed value. Furthermore, the system can determine, based on the sensor data and the updated initial object trajectory, a refined object trajectory. Subsequently, the system can generate a multi-dimensional label for the object based on the refined object trajectory. A motion plan for controlling the AV can be generated based on the multi-dimensional label.
    Type: Application
    Filed: November 17, 2021
    Publication date: May 19, 2022
    Inventors: Bin Yang, Ming Liang, Wenyuan Zeng, Min Bai, Raquel Urtasun
  • Publication number: 20220101600
    Abstract: Systems and methods for identifying travel way features in real time are provided. A method can include receiving two-dimensional and three-dimensional data associated with the surrounding environment of a vehicle. The method can include providing the two-dimensional data as one or more input into a machine-learned segmentation model to output a two-dimensional segmentation. The method can include fusing the two-dimensional segmentation with the three-dimensional data to generate a three-dimensional segmentation. The method can include storing the three-dimensional segmentation in a classification database with data indicative of one or more previously generated three-dimensional segmentations. The method can include providing one or more datapoint sets from the classification database as one or more inputs into a machine-learned enhancing model to obtain an enhanced three-dimensional segmentation.
    Type: Application
    Filed: December 10, 2021
    Publication date: March 31, 2022
    Inventors: Raquel Urtasun, Min Bai, Shenlong Wang
  • Patent number: 11217012
    Abstract: Systems and methods for identifying travel way features in real time are provided. A method can include receiving two-dimensional and three-dimensional data associated with the surrounding environment of a vehicle. The method can include providing the two-dimensional data as one or more input into a machine-learned segmentation model to output a two-dimensional segmentation. The method can include fusing the two-dimensional segmentation with the three-dimensional data to generate a three-dimensional segmentation. The method can include storing the three-dimensional segmentation in a classification database with data indicative of one or more previously generated three-dimensional segmentations. The method can include providing one or more datapoint sets from the classification database as one or more inputs into a machine-learned enhancing model to obtain an enhanced three-dimensional segmentation.
    Type: Grant
    Filed: November 15, 2019
    Date of Patent: January 4, 2022
    Assignee: UATC, LLC
    Inventors: Raquel Urtasun, Min Bai, Shenlong Wang
  • Publication number: 20210326607
    Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.
    Type: Application
    Filed: June 25, 2021
    Publication date: October 21, 2021
    Inventors: Min Bai, Gellert Sandor Mattyus, Namdar Homayounfar, Shenlong Wang, Shrindihi Kowshika Lakshmikanth, Raquel Urtasun
  • Patent number: 11080537
    Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.
    Type: Grant
    Filed: September 5, 2018
    Date of Patent: August 3, 2021
    Assignee: UATC, LLC
    Inventors: Min Bai, Gellert Sandor Mattyus, Namdar Homayounfar, Shenlong Wang, Shrindihi Kowshika Lakshmikanth, Raquel Urtasun
  • Patent number: 10803328
    Abstract: Systems and methods for detecting objects are provided. In one example, a computer-implemented method includes receiving sensor data from one or more sensors configured to generate sensor data. The method includes inputting the sensor data to a machine-learned model that generates a class prediction and an instance prediction for each of a plurality of portions of the sensor data. The instance prediction includes an energy value based on a distance to at least one object boundary. The machine learned model can be trained to generate a common energy value to represent the at least one object boundary. The method includes generating as outputs of the machine-learned model, an instance prediction and a class prediction corresponding to each of the plurality of portions of the sensor data. The method includes generating one or more object segments based at least in part on the instance predictions and the class predictions.
    Type: Grant
    Filed: September 6, 2018
    Date of Patent: October 13, 2020
    Assignee: UATC, LLC
    Inventors: Min Bai, Raquel Urtasun
  • Patent number: 10803325
    Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain rasterized LIDAR data associated with a surrounding environment of an autonomous vehicle. The rasterized LIDAR data can include LIDAR image data that is rasterized from a LIDAR point cloud. The computing system can access data indicative of a machine-learned lane boundary detection model. The computing system can input the rasterized LIDAR data associated with the surrounding environment of the autonomous vehicle into the machine-learned lane boundary detection model. The computing system can obtain an output from the machine-learned lane boundary detection model. The output can be indicative of one or more lane boundaries within the surrounding environment of the autonomous vehicle.
    Type: Grant
    Filed: September 5, 2018
    Date of Patent: October 13, 2020
    Assignee: UATC, LLC
    Inventors: Min Bai, Gellert Sandor Mattyus, Namdar Homayounfar, Shenlong Wang, Shrindihi Kowshika Lakshmikanth, Raquel Urtasun, Wei-Chiu Ma
  • Publication number: 20200160532
    Abstract: Systems and methods for identifying travel way features in real time are provided. A method can include receiving two-dimensional and three-dimensional data associated with the surrounding environment of a vehicle. The method can include providing the two-dimensional data as one or more input into a machine-learned segmentation model to output a two-dimensional segmentation. The method can include fusing the two-dimensional segmentation with the three-dimensional data to generate a three-dimensional segmentation. The method can include storing the three-dimensional segmentation in a classification database with data indicative of one or more previously generated three-dimensional segmentations. The method can include providing one or more datapoint sets from the classification database as one or more inputs into a machine-learned enhancing model to obtain an enhanced three-dimensional segmentation.
    Type: Application
    Filed: November 15, 2019
    Publication date: May 21, 2020
    Inventors: Raquel Urtasun, Min Bai, Shenlong Wang
  • Patent number: 10550073
    Abstract: The present invention relates to a benzamide derivative of general formula I, a drug composition containing same and a use thereof as a drug, wherein the definitions of R1, Z and Q are as described in the description.
    Type: Grant
    Filed: September 30, 2016
    Date of Patent: February 4, 2020
    Assignee: CSPC Zhongqi Pharmaceutical Technology (Shijiazhuang) Co., Ltd.
    Inventors: Ying Shi, Yi Mi, Hanyu Yang, Xuliang Wang, Denghuang Gong, Min Bai, Xiaozhuo Chen, Yujie Chen, Xuejiao Zhang, Yuxiu Ma, Qingzhi Gao
  • Patent number: 10527319
    Abstract: The present invention relates to a geothermal heat exchange system and a method of constructing a geothermal heat exchange system, and more specifically, to a geothermal heat exchange system which is to be installed in a borehole in the ground, the borehole being divided into a ground surface section and a shallow geothermal source section, the shallow geothermal source section of the borehole, which is hardly influenced by the atmospheric or ground surface temperatures, is filled with conventional heat conductive grouting material with high thermal conductivity, and the ground surface section of the borehole is filled with thermal insulation grouting material or thermal insulation cartridges to prevent the heat transferring medium in the geothermal heat exchange system, which has the geothermal heat obtained from the shallow geothermal source, from losing heat in the winter time or obtaining heat in the summer time when it passes through the ground surface section which is much influenced by the atmospheric
    Type: Grant
    Filed: June 11, 2018
    Date of Patent: January 7, 2020
    Assignee: BIC INC.
    Inventor: Min Bai
  • Publication number: 20190147254
    Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.
    Type: Application
    Filed: September 5, 2018
    Publication date: May 16, 2019
    Inventors: Min Bai, Gellert Sandor Mattyus, Namdar Homayounfar, Shenlong Wang, Shrindihi Kowshika Lakshmikanth, Raquel Urtasun