Patents by Inventor Junsheng Fu

Junsheng Fu 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: 11922814
    Abstract: The present disclosure relates to a method to control a vehicle system. The method includes detecting a deviating vehicle having at least one of a deviating behaviour and a deviating vehicle property by means of a perception system of a first vehicle, wherein the perception system includes at least one sensor device configured to monitor a surrounding environment of the first vehicle; assigning a deviating vehicle classification to the deviating vehicle based on the deviating behaviour and/or deviating vehicle property; determining at least one second vehicle to receive information relating to the deviating vehicle; and transmitting to each determined second vehicle a set of information relating to the deviating vehicle, said set of information including at least one of the deviating vehicle classification and a predetermined instruction to be performed by the determined second vehicle, wherein the predetermined instruction is dependent on the deviating vehicle classification.
    Type: Grant
    Filed: October 13, 2020
    Date of Patent: March 5, 2024
    Assignee: Zenuity AB
    Inventors: Junsheng Fu, Andreas Schindler, Mattias Brännström
  • Publication number: 20230365154
    Abstract: The present invention relates to determination of a state of a vehicle on a road portion. The vehicle includes an Automated Driving System (ADS) feature. At first, map data associated with the road portion, positioning data indicating a pose of the vehicle on the road, and sensor data of the vehicle are obtained. Then, a plurality of filters for the road portion are initialized. Further, one or more sensor data point(s) in the obtained sensor data is associated to a corresponding map-element of the obtained map data to determine one or more normalized similarity score(s). Now, based on the determined one or more normalized similarity score(s), one or more multivariate time-series data are also determined and provided as input to a trained machine-learning algorithm. Then, one of the initialized filters is selected by the machine learning algorithm to indicate a current state of the vehicle on the road portion.
    Type: Application
    Filed: May 15, 2023
    Publication date: November 16, 2023
    Inventors: Axel BEAUVISAGE, Junsheng FU, Theodor STENHAMMAR, David BEJMER
  • Publication number: 20230356753
    Abstract: An assessment system obtains a state of the vehicle, and identifies lane segments void from road users. Input having data associated with the lane segments, data associated with the road users states and historic data associated with the road users states and/or lane segments, is encoded into respective states-related data associated with the road users states and segment-related data associated with dynamic start and end boundaries of the lane segments. One or more neural networks encode the road users states in view of the lane segments spatially and temporally, and output spatial- and temporal-processed respective states-related data and segment-related data. The output data associated with one or more of the road users (target road users) is fed to at least a first behavior-predicting neural network to predict and output data indicating predicted near-future behavior of the target road users in view of one or more of the lane segments.
    Type: Application
    Filed: May 8, 2023
    Publication date: November 9, 2023
    Inventors: Dapeng LIU, Junsheng FU
  • Publication number: 20230322236
    Abstract: A method performed by a vehicle pose assessment system for supporting determining a pose of a vehicle in view of a digital map. The approach provided by the method alleviates finding lane segments of the digital map corresponding to current sensor detections, which in turn may support accurate and/or improved vehicle localization. An apparatus and computer storage medium for supporting determining a pose of a vehicle in view of a digital map are also provided.
    Type: Application
    Filed: March 30, 2023
    Publication date: October 12, 2023
    Inventors: Junsheng FU, Axel BEAUVISAGE, Blazej SLUSAREK, Eduardo Sesma CASELLES, Pontus KIELÉN, Markus HAMMARSTEN, Tony GUSTAFSSON, Eiliv HÄGG
  • Patent number: 11691626
    Abstract: The present disclosure relates to an overtaking estimating system for estimation of a minimum overtaking speed of a vehicle. The overtaking estimating system determines in view of a host vehicle a remaining distance of an overtaking lane contiguous to a driving lane of the host vehicle. The system further determines a delta distance between the host vehicle and a preceding vehicle positioned in the host vehicle driving lane. Moreover, the system determines a delta time for the host vehicle to reach the preceding vehicle. The system further determines, based on the delta distance, the delta time and a determined host vehicle speed, a speed of the preceding vehicle. Furthermore, the system determines, based on the remaining distance, the delta distance, the preceding vehicle speed, and an overtaking-affecting parameter, a minimum overtaking speed of the host vehicle for overtaking the preceding vehicle in the remaining distance of the overtaking lane.
    Type: Grant
    Filed: November 24, 2020
    Date of Patent: July 4, 2023
    Assignee: Zenuity AB
    Inventors: Junsheng Fu, Marcus Olsson, Viktor Runemalm, Rafael Valencia Carreño
  • Publication number: 20230202497
    Abstract: The present disclosure relates to a method for determining a state of a vehicle on a road portion having two or more lanes. The method comprises obtaining map data associated with the road portion and positioning data indicating a position of the vehicle on the road and a sensor data from a sensor system of the vehicle. The method further comprises initializing a filter per lane of the road portion based on the obtained map data, the obtained positioning data, and the obtained sensor data, wherein each filter indicates an estimated state of the vehicle on the road portion. Then, selecting one of the initialized filters using a trained machine-learning algorithm, configured to use the obtained map data, the positioning data, the sensor data, and each estimated state as indicated by each filter as input and to output a current state of the vehicle on the road portion.
    Type: Application
    Filed: December 27, 2022
    Publication date: June 29, 2023
    Inventors: Junsheng FU, Axel BEAUVISAGE
  • Publication number: 20230166761
    Abstract: The present disclosure relates to a method, system, a vehicle and a computer-readable storage medium. The method comprises determining a fulfilment of a set of predefined Operational Design Domain (ODD) conditions for an Automated Driving System (ADS) feature of an ego-vehicle at least partly based on sensor data obtained from on-board sensors of the ego-vehicle and determining a first ODD exit boundary along an estimated route to be travelled by the ego-vehicle. The method further comprises obtaining data from at least one external vehicle located on the estimated route to be travelled by the ego-vehicle. Further, the method comprises evaluating the obtained data from the at least one external vehicle against an ODD assessment scheme to determine a fulfilment of the predefined ODD conditions in the surrounding environment of the external vehicle and determining a second ODD exit boundary along the estimated route of the ego-vehicle based on the evaluation.
    Type: Application
    Filed: November 28, 2022
    Publication date: June 1, 2023
    Inventors: Majid KHORSAND VAKILZADEH, Zhennan FEI, Junsheng FU
  • Patent number: 11429189
    Abstract: A method including recognizing at least one gesture to define at least one computer-implemented virtual boundary in a monitoring space, wherein the gesture includes a motion along a path and at a location in a monitored scene space wherein there is a correspondence between the monitoring space and the monitored scene space; causing implementation of the at least one virtual boundary in the monitoring space corresponding to the scene space, wherein at least part of the virtual boundary is determined by the path in the monitored scene space and the at least part of the virtual boundary is located in the monitoring space at a corresponding location equivalent to the path location; and processing received data to generate a response event when there is, relative to the at least one virtual boundary, a change in a portion of the monitored scene space.
    Type: Grant
    Filed: December 21, 2015
    Date of Patent: August 30, 2022
    Assignee: Nokia Technologies Oy
    Inventors: Antti Eronen, Jussi Leppanen, Arto Lehtiniemi, Junsheng Fu
  • Publication number: 20220242455
    Abstract: A method performed by a scenario reconstruction system for supporting assessment of unforeseen driving scenarios of a host vehicle. The scenario reconstruction system stores timestamped sensor data comprising the host vehicle's geographical position and surroundings captured with support from one or more surrounding detecting sensors onboard the host vehicle. The system detects at a scenario time instance, involvement of the host vehicle in an unforeseen driving scenario. Moreover, the scenario reconstruction system derives from the timestamped sensor data, subsets of sensor data and identifies one or more surrounding detecting sensors-provided entities respectively present in the subsets pertinent at least two respective separate timestamps.
    Type: Application
    Filed: January 28, 2022
    Publication date: August 4, 2022
    Inventors: Junsheng FU, Zhennan FEI, Majid Khorsand VAKILZADEH
  • Publication number: 20220205804
    Abstract: The present disclosure relates to a method for determining a vehicle pose, predicting a pose (xk, yk, ?k) of vehicle on a map based on sensor data acquired by a vehicle localization system, transforming a set of map road references of a segment of a digital map from a global coordinate system to an image-frame coordinate system of a vehicle-mounted camera based on map data and predicted pose of the vehicle. The transformed set of map road references form a set of polylines in image-frame coordinate system. Identifying a set of corresponding image road reference features in an image acquired by vehicle mounted camera, where each identified road references feature defines a set of measurement coordinates (xi, yi) in image-frame. Projecting each of identified set of image road reference features onto formed set of polylines in order to obtain a set of projection points.
    Type: Application
    Filed: December 27, 2021
    Publication date: June 30, 2022
    Inventors: Junsheng FU, Han ZHANG, Tony GUSTAFSSON, Andreas SCHINDLER, Eduardo SESMA CASELLES, Erik STEINMETZ, Pontus KIELÉN, Axel BEAUVISAGE, Joakim LIN SÖRSTEDT
  • Publication number: 20220144267
    Abstract: The present disclosure relates to a method performed by a deviation assessment system of a vehicle for supporting transitioning of speed control from an ADAS or AD system of the vehicle, to a vehicle driver. The deviation assessment system derives a current system-initiated value of a speed-affecting system parameter pertinent speed control by the ADAS or AD system. The deviation assessment system further derives a value of a corresponding speed-affecting intervention parameter pertinent a driver-initiated speed-affecting intervention of the speed control. Moreover, the deviation assessment system presents on a vehicle display a graphical representation indicative of a discrepancy between the system-initiated value and the driver-initiated value. The disclosure also relates to a deviation assessment system in accordance with the foregoing, a vehicle comprising such a deviation assessment system, and a respective corresponding computer program product and non-volatile computer readable storage medium.
    Type: Application
    Filed: October 25, 2021
    Publication date: May 12, 2022
    Inventors: Junsheng FU, Sheng XU
  • Publication number: 20210155247
    Abstract: The present disclosure relates to an overtaking estimating system for estimation of a minimum overtaking speed of a vehicle. The overtaking estimating system determines in view of a host vehicle a remaining distance of an overtaking lane contiguous to a driving lane of the host vehicle. The system further determines a delta distance between the host vehicle and a preceding vehicle positioned in the host vehicle driving lane. Moreover, the system determines a delta time for the host vehicle to reach the preceding vehicle. The system further determines, based on the delta distance, the delta time and a determined host vehicle speed, a speed of the preceding vehicle. Furthermore, the system determines, based on the remaining distance, the delta distance, the preceding vehicle speed, and an overtaking-affecting parameter, a minimum overtaking speed of the host vehicle for overtaking the preceding vehicle in the remaining distance of the overtaking lane.
    Type: Application
    Filed: November 24, 2020
    Publication date: May 27, 2021
    Inventors: Junsheng FU, Marcus OLSSON, Viktor RUNEMALM, Rafael Valencia CARREÑO
  • Publication number: 20210114624
    Abstract: The present disclosure relates to a method to control a vehicle system. The method includes detecting a deviating vehicle having at least one of a deviating behaviour and a deviating vehicle property by means of a perception system of a first vehicle, wherein the perception system includes at least one sensor device configured to monitor a surrounding environment of the first vehicle; assigning a deviating vehicle classification to the deviating vehicle based on the deviating behaviour and/or deviating vehicle property; determining at least one second vehicle to receive information relating to the deviating vehicle; and transmitting to each determined second vehicle a set of information relating to the deviating vehicle, said set of information including at least one of the deviating vehicle classification and a predetermined instruction to be performed by the determined second vehicle, wherein the predetermined instruction is dependent on the deviating vehicle classification.
    Type: Application
    Filed: October 13, 2020
    Publication date: April 22, 2021
    Inventors: Junsheng FU, Andreas SCHINDLER, Mattias BRÄNNSTRÖM
  • Patent number: 10102675
    Abstract: The embodiments relate to a method and to technical equipment for implementing the method. The method includes receiving an image with location information from a client; requesting processed region data from a media server based on the location information, said processed region data including one or more images with the corresponding location information; applying a first process for determining a pose of a device for the received image by means of the processed region data; if the first process fails to result the pose of the device, applying a second process for determining a pose of a device for the received image by means of the processed region data; saving the image with the determined pose of the device to the media server; providing the image and the pose of the device to a client for client rendering.
    Type: Grant
    Filed: June 27, 2014
    Date of Patent: October 16, 2018
    Assignee: Nokia Technologies Oy
    Inventors: Lixin Fan, Ville-Veikko Mattila, Yu You, Kimmo Roimela, Junsheng Fu, Antti Eronen
  • Patent number: 9996934
    Abstract: The invention relates to a method comprising obtaining a desired field of view (FOV) for an image arranged to be captured, determining a required field of view (r_fov) of the FOV for each active camera sensor of a camera array having a field of view (fov), comparing the r_fov and the fov, and determining a bend angle between adjacent camera sensors to achieve the FOV by camera sensors of the camera sensor array, if the r_fov is less than or equal to the fov. The invention further relates to an apparatus, a system and a computer program product that perform the method.
    Type: Grant
    Filed: February 22, 2016
    Date of Patent: June 12, 2018
    Assignee: Nokia Technologies Oy
    Inventors: Sujeet Shyamsundar Mate, Jussi Leppanen, Junsheng Fu, Pouria Babahajiani
  • Publication number: 20170364159
    Abstract: A method including recognizing at least one gesture to define at least one computer-implemented virtual boundary in a monitoring space, wherein the gesture includes a motion along a path and at a location in a monitored scene space wherein there is a correspondence between the monitoring space and the monitored scene space; causing implementation of the at least one virtual boundary in the monitoring space corresponding to the scene space, wherein at least part of the virtual boundary is determined by the path in the monitored scene space and the at least part of the virtual boundary is located in the monitoring space at a corresponding location equivalent to the path location; and processing received data to generate a response event when there is, relative to the at least one virtual boundary, a change in a portion of the monitored scene space.
    Type: Application
    Filed: December 21, 2015
    Publication date: December 21, 2017
    Inventors: Antti ERONEN, Jussi LEPPANEN, Arto LEHTINIEMI, Junsheng FU
  • Patent number: 9699375
    Abstract: An approach is provided for processing and/or facilitating a processing of one or more images to determine camera location information, camera pose information, or a combination thereof associated with at least one camera capturing the one or more images, wherein the camera location information, the camera pose information, or a combination thereof is represented according to a global coordinate system. The approach involves causing, at least in part, an association of the camera location information, the camera pose information, or a combination thereof with the one or more images as meta-data information.
    Type: Grant
    Filed: August 30, 2013
    Date of Patent: July 4, 2017
    Assignee: Nokia Technology Oy
    Inventors: Lixin Fan, Junsheng Fu, Kimmo Tapio Roimela, Yu You
  • Publication number: 20170132843
    Abstract: The embodiments relate to a method and to technical equipment for implementing the method. The method includes receiving an image with location information from a client; requesting processed region data from a media server based on the location information, said processed region data including one or more images with the corresponding location information; applying a first process for determining a pose of a device for the received image by means of the processed region data; if the first process fails to result the pose of the device, applying a second process for determining a pose of a device for the received image by means of the processed region data; saving the image with the determined pose of the device to the media server; providing the image and the pose of the device to a client for client rendering.
    Type: Application
    Filed: June 27, 2014
    Publication date: May 11, 2017
    Inventors: Lixin FAN, Ville-Veikko MATTILA, Yu YOU, Kimmo ROIMELA, Junsheng FU, Antti ERONEN
  • Patent number: 9596404
    Abstract: An approach is provided for processing of at least one preview image presented at at least one device to cause, at least in part, an extraction of camera pose information associated with the at least one preview image. The approach also involves determining one or more movement interactions of the at least one device relative to the camera pose information to cause, at least in part, a specification of requested camera pose information. The approach further involves causing, at least in part, a generation of at least one request to capture at least one media item based, at least in part, on the requested camera pose information.
    Type: Grant
    Filed: October 23, 2013
    Date of Patent: March 14, 2017
    Assignee: Nokia Technologies Oy
    Inventors: Junsheng Fu, Sujeet Shyamsundar Mate
  • Patent number: 9558559
    Abstract: An approach is provided for processing and/or facilitating a processing of one or more images to determine camera location information, camera pose information, or a combination thereof associated with at least one camera capturing the one or more images, wherein the camera location information, the camera pose information, or a combination thereof is represented according to a global coordinate system. The approach involves causing, at least in part, an association of the camera location information, the camera pose information, or a combination thereof with the one or more images as meta-data information.
    Type: Grant
    Filed: April 5, 2013
    Date of Patent: January 31, 2017
    Assignee: NOKIA TECHNOLOGIES OY
    Inventors: Lixin Fan, Junsheng Fu, Kimmo Roimela, Yu You