Patents by Inventor Albert Wu

Albert 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).

  • Publication number: 20240193784
    Abstract: An example system for performing segmentation of data based on tensor inputs includes memory storing computer-executable instructions defining a learning network, where the learning network includes a plurality of sequential encoder down-sampling blocks. A processor is configured to execute the computer-executable instructions to receive a multi-dimensional input tensor including at least a first dimension, a second dimension and a plurality of channels. The processor is also configured to process the received multi-dimensional input tensor by passing the received multi-dimensional input tensor through the plurality of sequential encoder down-sampling blocks of the learning network, and to generate an output tensor in response to processing the received multi-dimensional input tensor. The output tensor includes at least one segmentation classification.
    Type: Application
    Filed: February 23, 2024
    Publication date: June 13, 2024
    Inventors: Bing SONG, Nicholas James WITCHEY, Albert WU, Krsto SBUTEGA, Patrick SOON-SHIONG
  • Publication number: 20240149447
    Abstract: Apparatuses, systems, and techniques to generate a motion plan. In at least one embodiment, a motion plan is generated using a neural network based, at least in part, on a demonstration of a task.
    Type: Application
    Filed: September 7, 2023
    Publication date: May 9, 2024
    Inventors: Albert Wu, Clemens Eppner, Dieter Fox
  • Patent number: 11941813
    Abstract: An example system for performing segmentation of data based on tensor inputs includes memory storing computer-executable instructions defining a learning network, where the learning network includes a plurality of sequential encoder down-sampling blocks. A processor is configured to execute the computer-executable instructions to receive a multi-dimensional input tensor including at least a first dimension, a second dimension and a plurality of channels. The processor is also configured to process the received multi-dimensional input tensor by passing the received multi-dimensional input tensor through the plurality of sequential encoder down-sampling blocks of the learning network, and to generate an output tensor in response to processing the received multi-dimensional input tensor. The output tensor includes at least one segmentation classification.
    Type: Grant
    Filed: August 18, 2020
    Date of Patent: March 26, 2024
    Assignee: NantCell, Inc.
    Inventors: Bing Song, Nicholas James Witchey, Albert Wu, Krsto Sbutega, Patrick Soon-Shiong
  • Patent number: 11691623
    Abstract: Systems and methods for controlling a vehicle are described. A processor of a longitudinal planning system determines a state of the vehicle. The processor determines a state of a leader vehicle. The processor, based on the determined state of the vehicle and the determined state of the leader vehicle, determines a critical distance for the vehicle. The processor compares a distance between the vehicle and the leader vehicle with the critical distance. The processor, based on the comparison, determines whether the vehicle is too close to or too far from the leader vehicle. The processor, based on the determination, applies one or more of overshoot constraints, undershoot constraints, and critical constraints. After applying the one or more of overshoot constraints, undershoot constraints, and critical constraints, the processor determines a target acceleration for the vehicle. The processor controls the vehicle to track the target acceleration for the vehicle.
    Type: Grant
    Filed: February 11, 2022
    Date of Patent: July 4, 2023
    Assignee: NIO Technology (Anhui) Co., Ltd.
    Inventors: Albert Wu, Zhongkui Wang, Arek V. Sredzki, Keja S. A. Rowe
  • Patent number: 11572079
    Abstract: An apparatus and a method for controlling a velocity of an autonomous driving vehicle is provided. The method includes steps of: obtaining information of an environment surrounding the vehicle when an obstacle is detected to be on a planning path of the vehicle; obtaining an initial reference velocity profile of the vehicle; determining a safety factor based on the initial reference velocity profile, the information of the environment and information of the vehicle, wherein the safety factor at least comprises a safety distance between the vehicle and the obstacle for the vehicle to follow the obstacle; determining an optimized reference velocity profile based on the information of the environment, the information of the vehicle and the safety factor; and performing the step of determining the safety factor by using the optimized reference velocity profile as the initial reference velocity profile and the step of determining the optimized reference velocity iteratively.
    Type: Grant
    Filed: April 24, 2020
    Date of Patent: February 7, 2023
    Assignee: WERIDE CORP.
    Inventors: Zhiyuan Zuo, Albert Wu, Qiu Jin, Tianming Lu, Zeyin Zhang, Xuanzhu Lin, Xiong Wu, Yiqing Yang, Hua Zhong
  • Publication number: 20220161797
    Abstract: Systems and methods for controlling a vehicle are described. A processor of a longitudinal planning system determines a state of the vehicle. The processor determines a state of a leader vehicle. The processor, based on the determined state of the vehicle and the determined state of the leader vehicle, determines a critical distance for the vehicle. The processor compares a distance between the vehicle and the leader vehicle with the critical distance. The processor, based on the comparison, determines whether the vehicle is too close to or too far from the leader vehicle. The processor, based on the determination, applies one or more of overshoot constraints, undershoot constraints, and critical constraints. After applying the one or more of overshoot constraints, undershoot constraints, and critical constraints, the processor determines a target acceleration for the vehicle. The processor controls the vehicle to track the target acceleration for the vehicle.
    Type: Application
    Filed: February 11, 2022
    Publication date: May 26, 2022
    Applicant: NIO USA, Inc.
    Inventors: Albert Wu, Zhongkui Wang, Arek V. Sredzki, Keja S.A. Rowe
  • Patent number: 11247675
    Abstract: Systems and methods for controlling a vehicle are described. A processor of a longitudinal planning system determines a state of the vehicle. The processor determines a state of a leader vehicle. The processor, based on the determined state of the vehicle and the determined state of the leader vehicle, determines a critical distance for the vehicle. The processor compares a distance between the vehicle and the leader vehicle with the critical distance. The processor, based on the comparison, determines whether the vehicle is too close to or too far from the leader vehicle. The processor, based on the determination, applies one or more of overshoot constraints, undershoot constraints, and critical constraints. After applying the one or more of overshoot constraints, undershoot constraints, and critical constraints, the processor determines a target acceleration for the vehicle. The processor controls the vehicle to track the target acceleration for the vehicle.
    Type: Grant
    Filed: June 24, 2019
    Date of Patent: February 15, 2022
    Assignee: NIO USA, INC.
    Inventors: Albert Wu, Zhongkui Wang, Arek V. Sredzki, Keja S. A. Rowe
  • Patent number: 11200799
    Abstract: An Internet of Things (IoT) technique for vehicular traffic management, including an IoT sensor to measure traffic data of vehicular traffic, a traffic analyzer to determine a traffic event based on the traffic data, and an IoT gateway to issue a response based on the traffic event.
    Type: Grant
    Filed: September 30, 2016
    Date of Patent: December 14, 2021
    Assignee: Intel Corporation
    Inventors: Bradut Vrabete, Wen-Kuang Yu, Sam Hsu, Albert Wu, Richard Lin, Wilson Y. Lee
  • Patent number: 11014569
    Abstract: Methods and systems for autonomously steering a moving vehicle are disclosed. A processor determines a longitudinal velocity, a longitudinal acceleration, a lateral acceleration, and a yaw rate of the vehicle. The processor estimates, based on the longitudinal velocity, lateral acceleration, and yaw rate of the vehicle, a change in lateral velocity over time. The processor estimates, based on the change in the lateral velocity over time, the yaw rate, a distance between the front axle of the vehicle and a center of gravity of the vehicle, and a distance between the rear axle of the vehicle and the center of gravity of the vehicle, a lateral front velocity of the vehicle and a lateral rear velocity of the vehicle. Using calculations, a state estimation model for the vehicle is updated by the processor using a lateral acceleration bias. The updated state estimation model is used to autonomously steer the vehicle.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: May 25, 2021
    Assignee: NIO USA, Inc.
    Inventors: Omid Ghasemalizadeh, Albert Wu, Zhongkui Wang
  • Publication number: 20210056363
    Abstract: An example system for performing segmentation of data based on tensor inputs includes memory storing computer-executable instructions defining a learning network, where the learning network includes a plurality of sequential encoder down-sampling blocks. A processor is configured to execute the computer-executable instructions to receive a multi-dimensional input tensor including at least a first dimension, a second dimension and a plurality of channels. The processor is also configured to process the received multi-dimensional input tensor by passing the received multi-dimensional input tensor through the plurality of sequential encoder down-sampling blocks of the learning network, and to generate an output tensor in response to processing the received multi-dimensional input tensor. The output tensor includes at least one segmentation classification.
    Type: Application
    Filed: August 18, 2020
    Publication date: February 25, 2021
    Inventors: Bing SONG, Nicholas James WITCHEY, Albert WU, Krsto SBUTEGA, Patrick SOON-SHIONG
  • Patent number: 10906549
    Abstract: Systems of an electrical vehicle and the operations thereof are provided. A vehicle control system of a vehicle determines a range of lane change initiation times. For a plurality of lane change initiation times in the range of lane change initiation times the vehicle control system determines a set of reachable states. The set of reachable states comprises a plurality of reachable states. For one or more reachable states of the plurality of reachable states the vehicle control system computes an ensuing trajectory. The vehicle control system compares each of the computed ensuing trajectories. Based on the comparison of the computed ensuing trajectories the vehicle control system determines an optimal lane change maneuver. The vehicle control system executes the optimal lane change maneuver by controlling the vehicle from a first lane to a second lane.
    Type: Grant
    Filed: December 7, 2018
    Date of Patent: February 2, 2021
    Assignee: NIO USA, Inc.
    Inventor: Albert Wu
  • Publication number: 20200398836
    Abstract: Systems and methods for controlling a vehicle are described. A processor of a longitudinal planning system determines a state of the vehicle. The processor determines a state of a leader vehicle. The processor, based on the determined state of the vehicle and the determined state of the leader vehicle, determines a critical distance for the vehicle. The processor compares a distance between the vehicle and the leader vehicle with the critical distance. The processor, based on the comparison, determines whether the vehicle is too close to or too far from the leader vehicle. The processor, based on the determination, applies one or more of overshoot constraints, undershoot constraints, and critical constraints. After applying the one or more of overshoot constraints, undershoot constraints, and critical constraints, the processor determines a target acceleration for the vehicle. The processor controls the vehicle to track the target acceleration for the vehicle.
    Type: Application
    Filed: June 24, 2019
    Publication date: December 24, 2020
    Inventors: Albert Wu, Zhongkui Wang, Arek V. Sredzki, Keja S.A. Rowe
  • Publication number: 20200363816
    Abstract: A method for controlling a vehicle using a model predictive controller generating consecutive sets of reference states at a calculation frequency. In one embodiment, the method comprises: receiving a trajectory reference for guiding movement of the vehicle; generating, in a calculation cycle repeated at the calculation frequency, a set of reference states based on an initial state of the vehicle at a start time of the calculation cycle and the trajectory reference; sending the set of reference states to a second controller; detecting, by the second controller at a detection frequency equal to or higher than the calculation frequency, an updated state of the vehicle; generating a vehicle control parameter value based on the updated state of the vehicle and a reference state of the set of reference states; and controlling the vehicle using the vehicle control parameter value.
    Type: Application
    Filed: May 14, 2020
    Publication date: November 19, 2020
    Inventors: Zhiyuan ZUO, Albert WU, Qiu JIN, Tianming LU, Zeyin ZHANG, Xuanzhu LIN, Xiong WU, Yiqing YANG, Hua ZHONG, Zhilong LIU
  • Publication number: 20200339153
    Abstract: An apparatus and a method for controlling a velocity of an autonomous driving vehicle is provided. The method includes steps of: obtaining information of an environment surrounding the vehicle when an obstacle is detected to be on a planning path of the vehicle; obtaining an initial reference velocity profile of the vehicle; determining a safety factor based on the initial reference velocity profile, the information of the environment and information of the vehicle, wherein the safety factor at least comprises a safety distance between the vehicle and the obstacle for the vehicle to follow the obstacle; determining an optimized reference velocity profile based on the information of the environment, the information of the vehicle and the safety factor; and performing the step of determining the safety factor by using the optimized reference velocity profile as the initial reference velocity profile and the step of determining the optimized reference velocity iteratively.
    Type: Application
    Filed: April 24, 2020
    Publication date: October 29, 2020
    Inventors: Zhiyuan ZUO, Albert WU, Qiu JIN, Tianming LU, Zeyin ZHANG, Xuanzhu LIN, Xiong WU, Yiqing YANG, Hua ZHONG
  • Publication number: 20200180633
    Abstract: Systems of an electrical vehicle and the operations thereof are provided. A vehicle control system of a vehicle determines a range of lane change initiation times. For a plurality of lane change initiation times in the range of lane change initiation times the vehicle control system determines a set of reachable states. The set of reachable states comprises a plurality of reachable states. For one or more reachable states of the plurality of reachable states the vehicle control system computes an ensuing trajectory. The vehicle control system compares each of the computed ensuing trajectories. Based on the comparison of the computed ensuing trajectories the vehicle control system determines an optimal lane change maneuver. The vehicle control system executes the optimal lane change maneuver by controlling the vehicle from a first lane to a second lane.
    Type: Application
    Filed: December 7, 2018
    Publication date: June 11, 2020
    Inventor: Albert Wu
  • Publication number: 20200039523
    Abstract: Methods and systems for autonomously steering a moving vehicle are disclosed. A processor determines a longitudinal velocity, a longitudinal acceleration, a lateral acceleration, and a yaw rate of the vehicle. The processor estimates, based on the longitudinal velocity, lateral acceleration, and yaw rate of the vehicle, a change in lateral velocity over time. The processor estimates, based on the change in the lateral velocity over time, the yaw rate, a distance between the front axle of the vehicle and a center of gravity of the vehicle, and a distance between the rear axle of the vehicle and the center of gravity of the vehicle, a lateral front velocity of the vehicle and a lateral rear velocity of the vehicle. Using calculations, a state estimation model for the vehicle is updated by the processor using a lateral acceleration bias. The updated state estimation model is used to autonomously steer the vehicle.
    Type: Application
    Filed: July 31, 2018
    Publication date: February 6, 2020
    Inventors: Omid Ghasemalizadeh, Albert Wu, Zhongkui Wang
  • Publication number: 20190251837
    Abstract: An Internet of Things (IoT) technique for vehicular traffic management, including an IoT sensor to measure traffic data of vehicular traffic, a traffic analyzer to determine a traffic event based on the traffic data, and an IoT gateway to issue a response based on the traffic event.
    Type: Application
    Filed: September 30, 2016
    Publication date: August 15, 2019
    Inventors: Bradut Vrabete, Wen-Kuang Yu, Sam Hsu, Albert Wu, Richard Lin, Wilson Y. Lee
  • Patent number: 9768144
    Abstract: Embodiments of the present disclosure provide an apparatus comprising a semiconductor substrate having a first surface, a second surface that is disposed opposite to the first surface, wherein at least a portion of the first surface is recessed to form a recessed region of the semiconductor substrate, and one or more vias formed in the recessed region of the semiconductor substrate to provide an electrical or thermal pathway between the first surface and the second surface of the semiconductor substrate, and a die coupled to the semiconductor substrate, the die being electrically coupled to the one or more vias formed in the recessed region of the semiconductor substrate. Other embodiments may be described and/or claimed.
    Type: Grant
    Filed: February 5, 2016
    Date of Patent: September 19, 2017
    Assignee: Marvell World Trade Ltd.
    Inventors: Albert Wu, Roawen Chen, Chung Chyung (Justin) Han, Shiann-Ming Liou, Chien-Chuan Wei, Runzi Chang, Scott Wu, Chuan-Cheng Cheng
  • Patent number: 9659851
    Abstract: Some of the embodiments of the present disclosure provide a semiconductor package interposer comprising a substrate having a first surface and a second surface, a plurality of vias extending between the first surface and the second surface of the substrate, the plurality of vias electrically connecting electrical connectors or circuitry on the first surface of the substrate to electrical connectors or circuitry on the second surface of the substrate, and metal plugs at least partially filling the plurality of vias. At least one of (i) the first surface or (ii) the second surface of the substrate includes depressions at distal ends of the metal plugs.
    Type: Grant
    Filed: February 3, 2015
    Date of Patent: May 23, 2017
    Assignee: Marvell World Trade Ltd.
    Inventors: Long-Ching Wang, Albert Wu, Scott Wu
  • Patent number: 9565770
    Abstract: In an embodiment, there is provided a method of creating a package, the method comprising: providing an initial substrate, wherein the initial substrate comprises a carrier foil, a functional copper foil, and an interface release layer between the carrier foil and the functional copper foil; building up copper portions on the functional copper foil; attaching a chip to a first copper portion; coupling the chip to a second copper portion; encapsulating at least the chip and the copper portions with a mold; and removing the carrier foil and interface release layer.
    Type: Grant
    Filed: August 8, 2013
    Date of Patent: February 7, 2017
    Assignee: Marvell World Trade Ltd.
    Inventors: Sehat Sutardja, Albert Wu, Hyun J Shin