Patents by Inventor Daniel Lam

Daniel Lam 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: 20250298077
    Abstract: An antenna device for establishing a wireless coupling to a device under test has an antenna structure, and a first blind mating waveguide flange coupled to the antenna structure, wherein the first waveguide flange comprises a ridged waveguide structure with at least two ridges.
    Type: Application
    Filed: June 5, 2025
    Publication date: September 25, 2025
    Inventors: José MOREIRA, Natsuki SHIOTA, Daniel LAM, Yuchang LIU
  • Publication number: 20250153363
    Abstract: Implementations described herein relate to training and refining robotic control policies using imitation learning techniques. A robotic control policy can be initially trained based on human demonstrations of various robotic tasks. Further, the robotic control policy can be refined based on human interventions while a robot is performing a robotic task. In some implementations, the robotic control policy may determine whether the robot will fail in performance of the robotic task, and prompt a human to intervene in performance of the robotic task. In additional or alternative implementations, a representation of the sequence of actions can be visually rendered for presentation to the human can proactively intervene in performance of the robotic task.
    Type: Application
    Filed: January 16, 2025
    Publication date: May 15, 2025
    Inventors: Seyed Mohammad Khansari Zadeh, Eric Jang, Daniel Lam, Daniel Kappler, Matthew Bennice, Brent Austin, Yunfei Bai, Sergey Levine, Alexander Irpan, Nicolas Sievers, Chelsea Finn
  • Patent number: 12226920
    Abstract: Implementations described herein relate to training and refining robotic control policies using imitation learning techniques. A robotic control policy can be initially trained based on human demonstrations of various robotic tasks. Further, the robotic control policy can be refined based on human interventions while a robot is performing a robotic task. In some implementations, the robotic control policy may determine whether the robot will fail in performance of the robotic task, and prompt a human to intervene in performance of the robotic task. In additional or alternative implementations, a representation of the sequence of actions can be visually rendered for presentation to the human can proactively intervene in performance of the robotic task.
    Type: Grant
    Filed: August 11, 2023
    Date of Patent: February 18, 2025
    Assignee: GOOGLE LLC
    Inventors: Seyed Mohammad Khansari Zadeh, Eric Jang, Daniel Lam, Daniel Kappler, Matthew Bennice, Brent Austin, Yunfei Bai, Sergey Levine, Alexander Irpan, Nicolas Sievers, Chelsea Finn
  • Publication number: 20240295880
    Abstract: A method includes receiving, by a robotic device, an indication that the robotic device was elected to be a leader robotic device by a plurality of robotic devices and receiving an indication of a new task in a remotely stored list of tasks. The method further includes determining, based on a remotely stored list of robotic devices, an additional robotic device to assign the new task. The remotely stored list of robotic devices comprises an entry for each respective robotic device of the plurality of robotic devices associating the respective robotic device with an identifier and a heartbeat. The method additionally includes assigning the new task to the additional robotic device based on the additional robotic device having an active heartbeat. Assigning the new task to the additional robotic device comprises associating the new task with the additional robotic device in the remotely stored list of tasks to cause the additional robotic device to carry out the new task.
    Type: Application
    Filed: March 1, 2023
    Publication date: September 5, 2024
    Inventors: Rainer Hessmer, Nikhil J. Joshi, Daniel Lam, Pavel Vodenski
  • Publication number: 20230381970
    Abstract: Implementations described herein relate to training and refining robotic control policies using imitation learning techniques. A robotic control policy can be initially trained based on human demonstrations of various robotic tasks. Further, the robotic control policy can be refined based on human interventions while a robot is performing a robotic task. In some implementations, the robotic control policy may determine whether the robot will fail in performance of the robotic task, and prompt a human to intervene in performance of the robotic task. In additional or alternative implementations, a representation of the sequence of actions can be visually rendered for presentation to the human can proactively intervene in performance of the robotic task.
    Type: Application
    Filed: August 11, 2023
    Publication date: November 30, 2023
    Inventors: Seyed Mohammad Khansari Zadeh, Eric Jang, Daniel Lam, Daniel Kappler, Matthew Bennice, Brent Austin, Yunfei Bai, Sergey Levine, Alexander Irpan, Nicolas Sievers, Chelsea Finn
  • Patent number: 11772272
    Abstract: Implementations described herein relate to training and refining robotic control policies using imitation learning techniques. A robotic control policy can be initially trained based on human demonstrations of various robotic tasks. Further, the robotic control policy can be refined based on human interventions while a robot is performing a robotic task. In some implementations, the robotic control policy may determine whether the robot will fail in performance of the robotic task, and prompt a human to intervene in performance of the robotic task. In additional or alternative implementations, a representation of the sequence of actions can be visually rendered for presentation to the human can proactively intervene in performance of the robotic task.
    Type: Grant
    Filed: March 16, 2021
    Date of Patent: October 3, 2023
    Assignee: GOOGLE LLC
    Inventors: Seyed Mohammad Khansari Zadeh, Eric Jang, Daniel Lam, Daniel Kappler, Matthew Bennice, Brent Austin, Yunfei Bai, Sergey Levine, Alexander Irpan, Nicolas Sievers, Chelsea Finn
  • Patent number: 11642780
    Abstract: A system includes a robotic device, a sensor disposed on the robotic device, and circuitry configured to perform operations. The operations include determining a map that represents stationary features of an environment and receiving, from the sensor, sensor data representing the environment. The operations also include determining, based on the sensor data, a representation of an actor within the environment, where the representation includes keypoints representing corresponding body locations of the actor. The operations also include determining that a portion of a particular stationary feature is positioned within a threshold distance of a particular keypoint and, based on thereon, updating the map to indicate that the portion is to be cleaned. The operations further include, based on the map as updated, causing the robotic device to clean the portion of the particular stationary feature.
    Type: Grant
    Filed: July 22, 2021
    Date of Patent: May 9, 2023
    Assignee: X Development LLC
    Inventors: Eden Rephaeli, Guy Satat, Daniel Lam, Benjamin Holson, Jiajun Xu
  • Publication number: 20220341906
    Abstract: A method includes receiving data collected by at least one sensor on a robotic device, wherein the data is to be used for an ambient environment state representation, and wherein the data represents ambient environment measurements collected at locations of the at least one sensor when the robotic device is passively monitoring an environment such that robotic device navigation is not based on the ambient environment state representation. The method further includes determining the ambient environment state representation using the data collected by the at least one sensor on the robotic device. The method also includes identifying, based on the ambient environment state representation, one or more anomalous ambient environment measurements. The method additionally includes causing, based on the one or more identified anomalous ambient environment measurements, the robotic device to actively monitor the environment such that robotic device navigation is based on the ambient environment state representation.
    Type: Application
    Filed: April 26, 2021
    Publication date: October 27, 2022
    Inventors: Daniel Lam, Justine Rembisz, Asa Weiss, Benjamin Holson
  • Publication number: 20220297303
    Abstract: Implementations described herein relate to training and refining robotic control policies using imitation learning techniques. A robotic control policy can be initially trained based on human demonstrations of various robotic tasks. Further, the robotic control policy can be refined based on human interventions while a robot is performing a robotic task. In some implementations, the robotic control policy may determine whether the robot will fail in performance of the robotic task, and prompt a human to intervene in performance of the robotic task. In additional or alternative implementations, a representation of the sequence of actions can be visually rendered for presentation to the human can proactively intervene in performance of the robotic task.
    Type: Application
    Filed: March 16, 2021
    Publication date: September 22, 2022
    Inventors: Seyed Mohammad Khansari Zadeh, Eric Jang, Daniel Lam, Daniel Kappler, Matthew Bennice, Brent Austin, Yunfei Bai, Sergey Levine, Alexander Irpan, Nicolas Sievers, Chelsea Finn
  • Publication number: 20220193888
    Abstract: A system includes a robotic device, a sensor disposed on the robotic device, and circuitry configured to perform operations. The operations include determining a map that represents stationary features of an environment and receiving, from the sensor, sensor data representing the environment. The operations also include determining, based on the sensor data, a representation of an actor within the environment, where the representation includes keypoints representing corresponding body locations of the actor. The operations also include determining that a portion of a particular stationary feature is positioned within a threshold distance of a particular keypoint and, based on thereon, updating the map to indicate that the portion is to be cleaned. The operations further include, based on the map as updated, causing the robotic device to clean the portion of the particular stationary feature.
    Type: Application
    Filed: July 22, 2021
    Publication date: June 23, 2022
    Inventors: Eden Rephaeli, Guy Satat, Daniel Lam, Benjamin Holson, Jiajun Xu
  • Publication number: 20220164889
    Abstract: A policy management system can manage a set of insurance policies, for example by performing automated operations to renew policies for subsequent terms. Some insurance policies may be associated with the same household, company, or other insured party, but may be associated with different cars or other insured elements. The policy management system can have a policy consolidator that identifies database records for a target policy and a related source policy, and can consolidate data from the source policy into the record of the target policy. Thereafter, the policy management system can perform policy renewal operations and other policy management operations together based on the consolidated data in the record for the target policy.
    Type: Application
    Filed: November 18, 2021
    Publication date: May 26, 2022
    Inventors: Troy Cottrell, Evan Stalter, David Poppen, Byron Musser, Hari Polukonda, Daniel Lam, Lynne Wagner, Tyhad Harrison
  • Patent number: 11097414
    Abstract: A system includes a robotic device, a sensor disposed on the robotic device, and circuitry configured to perform operations. The operations include determining a map that represents stationary features of an environment and receiving, from the sensor, sensor data representing the environment. The operations also include determining, based on the sensor data, a representation of an actor within the environment, where the representation includes keypoints representing corresponding body locations of the actor. The operations also include determining that a portion of a particular stationary feature is positioned within a threshold distance of a particular keypoint and, based on thereon, updating the map to indicate that the portion is to be cleaned. The operations further include, based on the map as updated, causing the robotic device to clean the portion of the particular stationary feature.
    Type: Grant
    Filed: December 22, 2020
    Date of Patent: August 24, 2021
    Assignee: X Development LLC
    Inventors: Eden Rephaeli, Guy Satat, Daniel Lam, Benjamin Holson, Jiajun Xu
  • Patent number: 10944148
    Abstract: Embodiments described herein perform incisions along the direction of the long axis of the waveguide, thereby exposing a trench structure which can be readily plated. Once divided and plated, the individual cut pieces can then be secured together to restore the original waveguide structure. In this fashion, multiple cut pieces can be secured together and used as “building blocks” to create a modular solution which can be used to provide a number of different customizable waveguide structures. Thus, embodiments described herein can perform plating procedures in a less expensive manner while achieving the benefits of ganged waveguide structures. Moreover, embodiments described herein can offer a modular approach to ganged waveguide design thereby allowing for end-user flexibility in testing.
    Type: Grant
    Filed: February 4, 2016
    Date of Patent: March 9, 2021
    Assignee: ADVANTEST CORPORATION
    Inventors: Don Lee, Daniel Lam, Roger Mcaleenan, Kosuke Miyao
  • Patent number: 10520360
    Abstract: A beam quality measurement system for determining beam quality of a high power laser beam from a laser system by power-in-the-bucket (PIB) measurements in a laboratory environment. The system includes a beam compressor assembly for compressing the diameter of the laser beam, and a diagnostic bench assembly that receives the reduced diameter low power beam from the beam compressor assembly. The bench assembly includes a pinhole array positioned at a focal plane of a lens and that includes a plurality of different sized pinholes and a translation stage for moving the pinhole array. The bench assembly also includes a power meter that receives the focused beam after it has passed through a pinhole in the pinhole array, where the power meter generates a signal that causes the stage to move the pinhole array to position another pinhole when the power meter identifies a maximum power received from one pinhole.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: December 31, 2019
    Assignee: Northrop Grumman Systems Corporation
    Inventors: Michael L. Dupuis, Daniel K. Smith, Daniel Lam, Christopher J. Lieto, Michael E. Farey, Joshua E. Rothenberg
  • Patent number: 10393772
    Abstract: Embodiments of the present disclosure utilize customizable waveguide fabrication technologies (e.g., 3D printer technology) and patch antenna arrays to create adaptable wave interfaces that can provide efficient signal routing for an ATE system. In this fashion, embodiments of the present disclosure allow for arbitrary waveguide routing from port to port and create high density port spacing at the PCB level and which specifically eliminates the large flange required of prior art waveguides. Furthermore, embodiments include the ability to integrate different waveguide components, including power splitters, couplers, terminations, etc., into a single structure. Thus, embodiments of the present disclosure can reduce signal path losses and simplify the mechanical construction of ATE systems while eliminating the need for coax cables and minimizing the length of PCB microstrips.
    Type: Grant
    Filed: February 4, 2016
    Date of Patent: August 27, 2019
    Assignee: ADVANTEST CORPORATION
    Inventors: Don Lee, Daniel Lam, Roger McAleenan, Kosuke Miyao
  • Patent number: 10377039
    Abstract: Methods, apparatus, systems, and computer-readable media are provided for creating, storing, and/or offloading tagged robot sensor data. In various implementations, a first plurality of sensor data points that are sampled by one or more sensors associated with a robot and that share a first attribute may be identified. Each of the first plurality of sensor data points may be tagged with a first tag, which may be indicative of the first attribute. A context in which a robot is operating may be identified. A first transport rule that governs how sensor data points tagged with the first tag are treated when the robot operates in the context may then be identified. At least a subset of the first plurality of tagged sensor data points may then be offloaded from the robot and/or stored locally on the robot pursuant to the first transport rule.
    Type: Grant
    Filed: September 19, 2018
    Date of Patent: August 13, 2019
    Assignee: X DEVELOPMENT LLC
    Inventors: Jamie Moline Gennis, Andre Hentz, Daniel Lam
  • Patent number: 10381707
    Abstract: Embodiments of the present disclosure use customizable waveguides that can be positioned next to each other in a structure that contains one single flange to provide a physical connection for the waveguides. In this fashion, many waveguides can be positioned within a small area to accommodate a tightly packed patch antenna array so that the waveguides can be positioned very close to the socket. As such, embodiments of the present disclosure allow more waveguides to be packed into a small area by providing a single structure that houses many waveguides and share only a single flange connection element that can be sized appropriately.
    Type: Grant
    Filed: February 4, 2016
    Date of Patent: August 13, 2019
    Assignee: ADVANTEST CORPORATION
    Inventors: Don Lee, Daniel Lam, Roger Mcaleenan, Kosuke Miyao
  • Patent number: 10371716
    Abstract: A structure for performing socket power calibration comprises a plurality of socket ports on a load board electrically coupled to a plurality of traces on a first end of a flexible printed circuit board, wherein the plurality of traces are configured to allow traversal of an electrical signal from the plurality of socket ports to a waveguide. The structure further comprises the plurality of traces, wherein the traces are operable to terminate on a second end of the flexible printed circuit board into a plurality of patch antennas, wherein the plurality of patch antennas is adapted to radiate the electrical signal into the waveguide. Finally, the structure also comprises a power sensor electrically coupled to the waveguide, wherein the waveguide is configured to communicate the electrical signal from the waveguide to the power sensor.
    Type: Grant
    Filed: June 29, 2016
    Date of Patent: August 6, 2019
    Assignee: ADVANTEST CORPORATION
    Inventors: Donald Lee, Daniel Lam
  • Patent number: 10118296
    Abstract: Methods, apparatus, systems, and computer-readable media are provided for creating, storing, and/or offloading tagged robot sensor data. In various implementations, a first plurality of sensor data points that are sampled by one or more sensors associated with a robot and that share a first attribute may be identified. Each of the first plurality of sensor data points may be tagged with a first tag, which may be indicative of the first attribute. A context in which a robot is operating may be identified. A first transport rule that governs how sensor data points tagged with the first tag are treated when the robot operates in the context may then be identified. At least a subset of the first plurality of tagged sensor data points may then be offloaded from the robot and/or stored locally on the robot pursuant to the first transport rule.
    Type: Grant
    Filed: September 10, 2015
    Date of Patent: November 6, 2018
    Assignee: X DEVELOPMENT LLC
    Inventors: Jamie Moline Gennis, Andre Hentz, Daniel Lam
  • Patent number: 10114067
    Abstract: A structure for signal transmission is disclosed. The structure comprises a first plurality of waveguides tightly disposed together and disposed substantially in parallel with each other, each of said waveguides having a first opening and a second opening, wherein each first opening is operable to align with a patch antenna, and wherein the first plurality of waveguides is disposed adjacent to a socket. The integrated structure further comprises the socket which comprises an opening operable to support an insertion of a device under test (DUT), wherein the DUT is communicatively coupled to a plurality of microstrip transmission lines on a printed circuit board (PCB) underlying the socket for transmitting test signals from the DUT, wherein each of the microstrip transmission lines is electrically coupled to a respective patch antenna. Further, the first plurality of waveguides and the socket are integrated into a single plastic or metal structure.
    Type: Grant
    Filed: February 4, 2016
    Date of Patent: October 30, 2018
    Assignee: ADVANTEST CORPORATION
    Inventors: Daniel Lam, Don Lee, Roger McAleenan, Kosuke Miyao