Patents by Inventor Jia Pu
Jia Pu 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: 11961536Abstract: According to one aspect, a method for detecting a location from which at least one sound signal originates, includes obtaining, on a microphone array of a vehicle, the at least one sound signal from a sound source, the sound source being external to the vehicle, the vehicle having a plurality of sides. The method also includes identifying, based on at least one measure associated with the at least one sound signal as obtained on the microphone array, at least a first side of the plurality of sides as being closest to the sound source.Type: GrantFiled: December 7, 2021Date of Patent: April 16, 2024Assignee: Nuro, Inc.Inventors: Joseph Daniel Penniman, Peter Jon Kardassakis, Matthew Jeremy Sarett, Adithya C. Ganesh, Jia Pu
-
Publication number: 20240090081Abstract: Apparatuses, systems, and methods for a user equipment device (UE) to perform methods for Fifth Generation New Radio (5G NR) frequency range two (FR2) based communications beam management. The UE may configure, via communications with a base station, serving the UE, a group ID for PUCCH resources within a group of PUCCHs, e.g., for FR2 based communications. The UE may receive, from the base station, an update to one or more PUCCH resources within the group of PUCCHs via a medium access control (MAC) control element (CE) that may include one of a resource ID indicating an update to a PUCCH resource or the group ID to update the group of PUCCH resources. The UE may update, based on the MAC-CE, the one or more PUCCH resources within the group of PUCCHs.Type: ApplicationFiled: November 13, 2023Publication date: March 14, 2024Inventors: Haitong Sun, Dawei Zhang, Hong He, Jia Tang, Pengkai Zhao, Tianyan Pu, Wei Zeng, Wei Zhang, Yuchul Kim, Yushu Zhang
-
Publication number: 20240080780Abstract: Apparatuses, systems, and methods for providing maximum transmit power control when utilizing multiple radio access technologies. For example, a wireless communication device comprising two cellular radios may intend to transmit on the first radio, while concurrently transmitting on the second radio. To ensure compliance with a maximum transmit power limitation, the device may determine an allowed transmit power level of the first radio, representing a difference between the maximum transmit power limitation and the current transmit power level being transmitted by the second radio. The device may also determine a threshold power level for a communication by the first radio. If the allowed transmit power level meets the threshold power level, then the device may transmit the first communication having a power level between the threshold power level and the allowed transmit power level. Otherwise, the device may forego transmission of the first communication.Type: ApplicationFiled: September 18, 2023Publication date: March 7, 2024Inventors: Haitong Sun, Johnson O. Sebeni, Zhu Ji, Dawei Zhang, Wei Zhang, Yuchul Kim, Tianyan Pu, Pengkai Zhao, Wei Zeng, Jia Tang, Ping Wang, Wanping Zhang, Yang Li
-
Patent number: 11900692Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.Type: GrantFiled: December 29, 2021Date of Patent: February 13, 2024Assignee: GM Cruise Holdings LLCInventors: Clement Creusot, Divya Thuremella, Na Yu, Jia Pu
-
Patent number: 11763574Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.Type: GrantFiled: October 29, 2021Date of Patent: September 19, 2023Assignee: GM CRUISE HOLDINGS LLCInventors: Clement Creusot, Divya Thuremella, Na Yu, Jia Pu
-
Publication number: 20220180895Abstract: According to one aspect, a method for detecting a location from which at least one sound signal originates, includes obtaining, on a microphone array of a vehicle, the at least one sound signal from a sound source, the sound source being external to the vehicle, the vehicle having a plurality of sides. The method also includes identifying, based on at least one measure associated with the at least one sound signal as obtained on the microphone array, at least a first side of the plurality of sides as being closest to the sound source.Type: ApplicationFiled: December 7, 2021Publication date: June 9, 2022Applicant: Nuro, Inc.Inventors: Joseph Daniel PENNIMAN, Peter Jon KARDASSAKIS, Matthew Jeremy SARETT, Adithya C. GANESH, Jia PU
-
Publication number: 20220122365Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.Type: ApplicationFiled: December 29, 2021Publication date: April 21, 2022Applicant: GM Cruise Holdings LLCInventors: Clement Creusot, Divya Thuremella, Na Yu, Jia Pu
-
Patent number: 11288527Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.Type: GrantFiled: February 28, 2020Date of Patent: March 29, 2022Assignee: GM Cruise Holdings LLCInventors: Clement Creusot, Divya Thuremella, Na Yu, Jia Pu
-
Publication number: 20220051037Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.Type: ApplicationFiled: October 29, 2021Publication date: February 17, 2022Applicant: GM Cruise Holdings LLCInventors: Clement Creusot, Divya Thuremella, Na Yu, Jia Pu
-
Patent number: 11195033Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.Type: GrantFiled: February 27, 2020Date of Patent: December 7, 2021Assignee: GM Cruise Holdings LLCInventors: Clement Creusot, Divya Thuremella, Na Yu, Jia Pu
-
Publication number: 20210271906Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.Type: ApplicationFiled: February 28, 2020Publication date: September 2, 2021Applicant: GM Cruise Holdings LLCInventors: Clement Creusot, Divya Thuremella, Na Yu, Jia Pu
-
Publication number: 20210271905Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.Type: ApplicationFiled: February 27, 2020Publication date: September 2, 2021Applicant: GM Cruise Holdings LLCInventors: Clement Creusot, Divya Thuremella, Na Yu, Jia Pu
-
Patent number: 8706472Abstract: Disambiguating multiple readings in language conversion is disclosed, including: receiving an input data to be converted into a set of characters comprising a symbolic representation of the input data in a target symbolic system; and using a language model that distinguishes between a first reading and a second reading of a character of the target symbolic system to determine a probability that the heteronymous character should be used to represent a corresponding portion of the input data.Type: GrantFiled: August 11, 2011Date of Patent: April 22, 2014Assignee: Apple Inc.Inventors: Brent D. Ramerth, Devang K. Naik, Douglas R. Davidson, Jannes G. A. Dolfing, Jia Pu
-
Publication number: 20130041647Abstract: Disambiguating multiple readings in language conversion is disclosed, including: receiving an input data to be converted into a set of characters comprising a symbolic representation of the input data in a target symbolic system; and using a language model that distinguishes between a first reading and a second reading of a character of the target symbolic system to determine a probability that the heteronymous character should be used to represent a corresponding portion of the input data.Type: ApplicationFiled: August 11, 2011Publication date: February 14, 2013Applicant: APPLE INC.Inventors: Brent D. Ramerth, Devang K. Naik, Douglas R. Davidson, Jannes G. A. Dolfing, Jia Pu