-
公开(公告)号：US20250069380A1
公开(公告)日：2025-02-27
申请号：US18238004
申请日：2023-08-25
Applicant: NXP B.V.
Inventor： Tunc Alkanat , Ashish Pandharipande
Abstract: Techniques for using machine learning to produce sensor data from vision sensor data are disclosed. By using a limited amount of sensor data together with vision sensor data, a deep learning network can be trained to produce estimated sensor point cloud distributions from, e.g., vision sensor data alone. Using a deep learning network trained in this way, vehicles with limited or no other sensor functionality can be equipped with a camera to produce estimated sensor point cloud distributions. The estimated sensor point cloud distributions can then be used to improve vehicle safety through vehicle controls or driver notifications and/or to produce enhanced sensor data.
-
公开(公告)号：US20240410973A1
公开(公告)日：2024-12-12
申请号：US18206387
申请日：2023-06-06
Applicant: NXP B.V.
Inventor： Ashish Pandharipande , Wilhelmus Johannes van Houtum
Abstract: A first device operates to utilize RF signaling for both communication signaling and radar sensing. The first device transmits a first RF signal representing a first OFDM symbol at time index k−1 and transmits a second RF signal representing a second OFDM symbol at time index k. The first and second OFDM symbols represent communication data for receipt by at least a second device, and have cyclic prefixes of a length less than a channel length used for radar sensing by the JCAS device. A third RF signal that is a scattered representation of the second RF signal is received at the first device, and a compensation matrix determined from at least both the first and second OFDM symbols is used to compensate for ISI present in the third RF signal. From this compensated result a set pf radar channel coefficients representing the local environment are determined.
-
公开(公告)号：US20240219547A1
公开(公告)日：2024-07-04
申请号：US18148486
申请日：2022-12-30
Applicant: NXP B.V.
Inventor： Ashish Pandharipande , Wilhelmus Johannes van Houtum , Paul Mattheijssen , Leendert Albertus Dick van den Broeke
IPC: G01S13/00 , G01S7/00 , G01S7/02 , G01S13/931
CPC classification number: G01S13/003 , G01S7/006 , G01S7/023 , G01S13/931 , G01S13/584
Abstract: A radar system includes a receiver, a processor, and a non-transitory computer-readable medium storing machine instructions. The machine instructions, when executed by the processor, cause the processor to receive, within a communication frame, radar metadata including information indicative of sensing time slots within the communication frame. During the sensing time slots, the processor causes the receiver to obtain a set of radar reflections off of an object in an environment and determines, based on the set of received radar reflections and the radar metadata, at least one of a distance between the object and the radar system, a velocity of the object, and an angle of arrival for the object. In some implementations, the radar system is a first radar system, and the set of radar reflections are radar signals transmitted by a second radar system and reflected off of the object in the environment.
-
4.发明申请公开(公告)号：US20250069408A1
公开(公告)日：2025-02-27
申请号：US18238007
申请日：2023-08-25
Applicant: NXP B.V.
Inventor： Tunc Alkanat , Ashish Pandharipande
Abstract: Techniques for using machine learning to produce vehicle location sensor data from vision sensor data are disclosed. By using a limited amount of vehicle location sensor data together with vision sensor data, a deep learning network can be trained to produce estimated vehicle location sensor point cloud distributions from, e.g., vision sensor data alone. Using a deep learning network trained in this way, vehicles with limited or no sensor functionality can be equipped with a camera to produce estimated vehicle location sensor point cloud distributions. These estimated vehicle location sensor point cloud distributions can then be compared with general sensor point cloud distributions to improve detection of vehicles, environmental objects, and ghost objects, and subsequently used to improve vehicle safety through vehicle controls or driver notifications and/or to produce enhanced sensor data.
-
Patent Agency Ranking
公开(公告)号：US20240219512A1
公开(公告)日：2024-07-04
申请号：US18148498
申请日：2022-12-30
Applicant: NXP B.V.
Inventor： Ashish Pandharipande , Cornelis Marinus Moerman
CPC classification number: G01S7/003 , G01S13/584
Abstract: A radar system includes a transmitter, a receiver, a processor, and a non-transitory computer-readable medium storing machine instructions. The machine instructions cause the processor to obtain an indication of an approaching object, perform radar sensing of a region of interest to obtain environmental information, and transmit the environmental information for the region of interest to a communication system of the approaching object. In some implementations, the processor obtains the indication of the approaching object by receiving, from the communication system of the approaching object, a request for the environmental information for the region of interest. In some implementations, the processor obtains the indication of the approaching object by determining a location of the approaching object relative to the region of interest, and the radar system transmits the environmental information in response to the location of the approaching object being within a threshold distance of the region of interest.
-
公开(公告)号：US20250078660A1
公开(公告)日：2025-03-06
申请号：US18816127
申请日：2024-08-27
Applicant: NXP B.V.
Inventor： Ashish Pandharipande , Christophe Marc Macours
Abstract: A method and apparatus for generating a vehicle acoustic alert signal for a vehicle comprising an acoustic vehicle alerting system (AVAS) is described. The method includes detecting and classifying an object. If the object is classified as a vulnerable road user (VRU), one or more VRU characteristics such as distance and velocity of the VRU are determined. An acoustic alert signal is generated and transmitted via the AVAS dependent on the at least one VRU characteristic. The at least one VRU characteristic is transmitted to a further vehicle for use in determining how the further vehicle generates an acoustic alert signal.
-
公开(公告)号：US20250060470A1
公开(公告)日：2025-02-20
申请号：US18235544
申请日：2023-08-18
Applicant: NXP B.V.
Abstract: A radar transceiver includes a radar transmitter and a radar receiver. The radar transmitter includes generation circuitry to generate a digital radar chirp sequence, and one or more digital-to-analog converters to convert the digital radar chirp sequence into a radar signal to be transmitted via one or more transmit antennas. The radar receiver includes one or more analog-to-digital converters to convert a received reflection of the radar signal to a received digital signal, and a mixer to mix the received digital signal with the digital chirp sequence to generate a digital de-chirped signal for velocity estimation followed by range estimation.
-
公开(公告)号：US20240125918A1
公开(公告)日：2024-04-18
申请号：US18045912
申请日：2022-10-12
Applicant: NXP B.V.
Inventor： Ashish Pandharipande , Wilhelmus Johannes van Houtum
CPC classification number: G01S13/878 , H04B7/0617 , H04L25/03006
Abstract: Joint communication and sensing by a joint communication and sensing system in a wireless network is disclosed. A transmitter is arranged to transmit a first beam in a direction selected from a plurality of directions stored in a memory, where each direction corresponds to a direction of a respective remote device. The first beam comprises communication symbols to be communicated to the remote device in the direction during a communication session with the remote device. A reflection of the transmitted first beam is received via a receive antenna during the communication session, where the reflected first beam comprises the communication symbols. A position of one or more objects is identified based on a timing of transmission and receipt of the communication symbols in the transmitted first beam and the reflected first beam respectively and the sense symbols in the transmitted second beam and the reflected second beam respectively.
-
公开(公告)号：US20240103152A1
公开(公告)日：2024-03-28
申请号：US17950360
申请日：2022-09-22
Applicant: NXP B.V.
Inventor： Ashish Pandharipande , Wilhelmus Johannes van Houtum , Leendert Albertus Dick van den Broeke , Paul Mattheijssen
IPC: G01S13/58 , G01S13/62 , G01S13/931
CPC classification number: G01S13/582 , G01S13/62 , G01S13/931
Abstract: Radar localization systems and methods are provided to determine the location of an object. The radar localization systems and methods can determine the location of an object based on data obtained from at least two radar measurements made by the radar localization device. In some embodiments, a radar localization system can be included in a wireless communications system that conducts both wireless communications and radar sensing. Radar localization systems include at least a computing unit that performs a radar localization method. Radar localization methods may use map data in object localization to eliminate non-feasible locations of the object.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.013 seconds)
