Patents by Inventor Ravi Teja Sukhavasi
Ravi Teja Sukhavasi 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: 20240095958Abstract: Methods for performing a calibration process for outward-facing cameras on devices such as head-mounted display devices are disclosed. Extrinsic parameters of the camera are first estimated using inputs to the calibration process such as information from an inertial measurement unit and points of interest within images captured by the camera that are tracked with time. Then, extrinsic and intrinsic parameters are concurrently determined in an optimization problem such that updated values of said parameters may be stored and used by applications that run on the device and make use of the camera. The calibration process may be extended to concurrently calibrate multiple cameras based, at least in part, on information from the inertial measurement unit that is local to the camera.Type: ApplicationFiled: September 13, 2023Publication date: March 21, 2024Applicant: Apple Inc.Inventors: Shuntaro Yamazaki, Ravi Teja Sukhavasi, Oleg Naroditsky, Stergios Roumeliotis, Daniel C Byrnes
-
Patent number: 11927668Abstract: Disclosed are techniques for employing deep learning to analyze radar signals. In an aspect, an on-board computer of a host vehicle receives, from a radar sensor of the vehicle, a plurality of radar frames, executes a neural network on a subset of the plurality of radar frames, and detects one or more objects in the subset of the plurality of radar frames based on execution of the neural network on the subset of the plurality of radar frames. Further, techniques for transforming polar coordinates to Cartesian coordinates in a neural network are disclosed. In an aspect, a neural network receives a plurality of radar frames in polar coordinate space, a polar-to-Cartesian transformation layer of the neural network transforms the plurality of radar frames to Cartesian coordinate space, and the neural network outputs the plurality of radar frames in the Cartesian coordinate space.Type: GrantFiled: November 27, 2019Date of Patent: March 12, 2024Assignee: QUALCOMM IncorporatedInventors: Daniel Hendricus Franciscus Fontijne, Amin Ansari, Bence Major, Ravi Teja Sukhavasi, Radhika Dilip Gowaikar, Xinzhou Wu, Sundar Subramanian, Michael John Hamilton
-
Patent number: 11899099Abstract: Disclosed are techniques for fusing camera and radar frames to perform object detection in one or more spatial domains. In an aspect, an on-board computer of a host vehicle receives, from a camera sensor of the host vehicle, a plurality of camera frames, receives, from a radar sensor of the host vehicle, a plurality of radar frames, performs a camera feature extraction process on a first camera frame of the plurality of camera frames to generate a first camera feature map, performs a radar feature extraction process on a first radar frame of the plurality of radar frames to generate a first radar feature map, converts the first camera feature map and/or the first radar feature map to a common spatial domain, and concatenates the first radar feature map and the first camera feature map to generate a first concatenated feature map in the common spatial domain.Type: GrantFiled: November 27, 2019Date of Patent: February 13, 2024Assignee: QUALCOMM IncorporatedInventors: Radhika Dilip Gowaikar, Ravi Teja Sukhavasi, Daniel Hendricus Franciscus Fontijne, Bence Major, Amin Ansari, Teck Yian Lim, Sundar Subramanian, Xinzhou Wu
-
Publication number: 20230419685Abstract: A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.Type: ApplicationFiled: September 1, 2023Publication date: December 28, 2023Inventors: Onkar Jayant DABEER, Kiran SOMASUNDARAM, Radhika Dilip GOWAIKAR, Ravi Teja SUKHAVASI
-
Patent number: 11776280Abstract: A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.Type: GrantFiled: August 31, 2021Date of Patent: October 3, 2023Assignee: QUALCOMM IncorporatedInventors: Onkar Jayant Dabeer, Kiran Somasundaram, Radhika Dilip Gowaikar, Ravi Teja Sukhavasi
-
Patent number: 11630197Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.Type: GrantFiled: January 2, 2020Date of Patent: April 18, 2023Assignee: QUALCOMM IncorporatedInventors: Jayakrishnan Unnikrishnan, Avdhut Joshi, Shivam Agarwal, Amir Salimi, Sree Sesha Aravind Vadrevu, Gautam Sachdeva, Yoga Y Nadaraajan, Ravi Teja Sukhavasi, Xinzhou Wu, Young-Ki Baik, Duck Hoon Kim, Hyun-Mook Cho
-
Patent number: 11443522Abstract: Methods of processing vehicle sensor information for object detection may include capturing generating a feature map based on captured sensor information, associating with each pixel of the feature map a prior box having a set of two or more width priors and a set of two or more height priors, determining a confidence value of each height prior and each width prior, outputting an indication of a detected object based on a highest confidence height prior and a highest confidence width prior, and performing a vehicle operation based on the output indication of a detected object. Embodiments may include determining for each pixel of the feature map one or more prior boxes having a center value, a size value, and a set of orientation priors, determining a confidence value for each orientation prior, and outputting an indication of the orientation of a detected object based on the highest confidence orientation.Type: GrantFiled: December 2, 2019Date of Patent: September 13, 2022Assignee: Qualcomm IncorporatedInventors: Bence Major, Daniel Hendricus Franciscus Fontijne, Ravi Teja Sukhavasi, Amin Ansari
-
Publication number: 20210397884Abstract: A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.Type: ApplicationFiled: August 31, 2021Publication date: December 23, 2021Inventors: Onkar Jayant Dabeer, Kiran Somasundaram, Radhika Dilip Gowaikar, Ravi Teja Sukhavasi
-
Patent number: 11120296Abstract: A method performed by an apparatus is described. The method includes receiving a first set of object data corresponding to a first journey. The method also includes receiving a second set of object data corresponding to a second journey. The method further includes determining a similarity metric between the first set of object data and the second set of object data. The similarity metric indicates a distance between the first set of object data and the second set of object data for at least one object. The method additionally includes clustering the first set of object data and the second set of object data for the at least one object based on the similarity metric to produce at least one object cluster. The method also includes producing map data based on the at least one object cluster.Type: GrantFiled: April 4, 2019Date of Patent: September 14, 2021Assignee: QUALCOMM IncorporatedInventors: Onkar Jayant Dabeer, Kiran Somasundaram, Radhika Dilip Gowaikar, Ravi Teja Sukhavasi
-
Patent number: 11115170Abstract: Techniques and devices are described for wireless communication. A base station may determine a parameter associated with a transmission such as hybrid automatic repeat request (HARQ) feedback, a signal-to-noise ratio, or a determination regarding whether the transmission was successfully decoded. The base station may then determine a contention window adjustment value based on the parameter. The base station may then apply weighting factor (e.g., based on the time of the transmission, a number of devices being served, aspects of the transmission parameter, etc.) to the contention window adjustment value may adjust a contention window size for a second transmission based on the weighted contention window adjustment value (and, in some cases, other weighted adjustments based on other transmissions). The base station may then perform a clear channel assessment (CCA) based on the contention window size.Type: GrantFiled: February 4, 2019Date of Patent: September 7, 2021Assignee: QUALCOMM IncorporatedInventors: Srinivas Yerramalli, Tao Luo, Aleksandar Damnjanovic, Peter Gaal, Ravi Teja Sukhavasi, Xiaoxia Zhang
-
Publication number: 20210255304Abstract: Disclosed are techniques for employing deep learning to analyze radar signals. In an aspect, an on-board computer of a host vehicle receives, from a radar sensor of the vehicle, a plurality of radar frames, executes a neural network on a subset of the plurality of radar frames, and detects one or more objects in the subset of the plurality of radar frames based on execution of the neural network on the subset of the plurality of radar frames. Further, techniques for transforming polar coordinates to Cartesian coordinates in a neural network are disclosed. In an aspect, a neural network receives a plurality of radar frames in polar coordinate space, a polar-to-Cartesian transformation layer of the neural network transforms the plurality of radar frames to Cartesian coordinate space, and the neural network outputs the plurality of radar frames in the Cartesian coordinate space.Type: ApplicationFiled: November 27, 2019Publication date: August 19, 2021Inventors: Daniel Hendricus Franciscus FONTIJNE, Amin ANSARI, Bence MAJOR, Ravi Teja SUKHAVASI, Radhika Dilip GOWAIKAR, Xinzhou WU, Sundar SUBRAMANIAN, Michael John HAMILTON
-
Patent number: 10999886Abstract: Various aspects related to techniques for harmonization between common reference signal (CRS) and demodulation reference signal (DM-RS) based transmission modes (TMs) in unlicensed spectrum are described. In one aspect, a downlink/uplink (DL/UL) subframe configuration may be signaled for each subframe. Information provided by the DL/UL subframe configuration may indicate whether the respective downlink subframe is a single-frequency network (MBSFN) subframe (associated with DM-RS-based TM) or a non-MBSFN subframe (associated with CRS-based TM). In another aspect, periodic as well as aperiodic channel state information (CSI) reporting requests may be supported. In yet another aspect, discontinued reception (DRX) wake ups for unlicensed carriers may be explicitly or implicitly indicated to a user equipment (UE) via a carrier in a licensed spectrum.Type: GrantFiled: August 9, 2016Date of Patent: May 4, 2021Assignee: QUALCOMM IncorporatedInventors: Peter Gaal, Srinivas Yerramalli, Durga Prasad Malladi, Yongbin Wei, Alexei Yurievitch Gorokhov, Brian Banister, Michael Lee McCloud, Tao Luo, Supratik Bhattacharjee, Chengjin Zhang, Ravi Teja Sukhavasi
-
Publication number: 20200218913Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.Type: ApplicationFiled: January 2, 2020Publication date: July 9, 2020Inventors: Jayakrishnan UNNIKRISHNAN, Avdhut JOSHI, Shivam AGARWAL, Amir SALIMI, Sree Sesha Aravind VADREVU, Gautam SACHDEVA, Yoga Y NADARAAJAN, Ravi Teja SUKHAVASI, Aolin XU, Xinzhou WU, Young-Ki BAIK, Duck Hoon KIM, Hyun-Mook CHO
-
Patent number: 10687218Abstract: Methods and apparatus for wireless communication are described. A method may include receiving at a user equipment (UE) a number of allocated interlaces for an uplink transmission over a shared spectrum, each of which may include a plurality of non-contiguous resource blocks (RB) of the shared spectrum. In some cases, the number of allocated interlaces is unsupported by joint interlace precoding hardware of the UE and the allocated interlaces may be partitioned into subsets of interlaces which may be a size supported by the joint interlace precoding hardware. Reference signals may be generated for the RBs of the allocated interlaces according to a reference signal sequence based on an ordering of the RBs for the allocated interlaces within the shared spectrum.Type: GrantFiled: November 4, 2014Date of Patent: June 16, 2020Assignee: QUALCOMM IncorporatedInventors: Srinivas Yerramalli, Tao Luo, Durga Prasad Malladi, Naga Bhushan, Yongbin Wei, Peter Gaal, Wanshi Chen, Aleksandar Damnjanovic, Tingfang Ji, Ravi Teja Sukhavasi
-
Publication number: 20200175315Abstract: Disclosed are techniques for fusing camera and radar frames to perform object detection in one or more spatial domains. In an aspect, an on-board computer of a host vehicle receives, from a camera sensor of the host vehicle, a plurality of camera frames, receives, from a radar sensor of the host vehicle, a plurality of radar frames, performs a camera feature extraction process on a first camera frame of the plurality of camera frames to generate a first camera feature map, performs a radar feature extraction process on a first radar frame of the plurality of radar frames to generate a first radar feature map, converts the first camera feature map and/or the first radar feature map to a common spatial domain, and concatenates the first radar feature map and the first camera feature map to generate a first concatenated feature map in the common spatial domain.Type: ApplicationFiled: November 27, 2019Publication date: June 4, 2020Inventors: Radhika Dilip GOWAIKAR, Ravi Teja SUKHAVASI, Daniel Hendricus Franciscus FONTIJNE, Bence MAJOR, Amin ANSARI, Teck Yian LIM, Sundar SUBRAMANIAN, Xinzhou WU
-
Publication number: 20200175286Abstract: Methods of processing vehicle sensor information for object detection may include capturing generating a feature map based on captured sensor information, associating with each pixel of the feature map a prior box having a set of two or more width priors and a set of two or more height priors, determining a confidence value of each height prior and each width prior, outputting an indication of a detected object based on a highest confidence height prior and a highest confidence width prior, and performing a vehicle operation based on the output indication of a detected object. Embodiments may include determining for each pixel of the feature map one or more prior boxes having a center value, a size value, and a set of orientation priors, determining a confidence value for each orientation prior, and outputting an indication of the orientation of a detected object based on the highest confidence orientation.Type: ApplicationFiled: December 2, 2019Publication date: June 4, 2020Inventors: Bence MAJOR, Daniel Hendricus Franciscus FONTIJNE, Ravi Teja SUKHAVASI, Amin ANSARI
-
Patent number: 10630962Abstract: A method performed by an apparatus is described. The method includes receiving a set of image frames including at least one object. The method also includes receiving a camera position for each image frame. The method further includes associating the at least one object between image frames based on one or more object points and the received camera position for each image frame to produce two-dimensional (2D) object location data. The method additionally includes estimating three-dimensional (3D) pose data of the at least one object based on the 2D object location data. The method also includes refining the 3D pose data based on a shape constraint.Type: GrantFiled: June 13, 2017Date of Patent: April 21, 2020Assignee: QUALCOMM IncorporatedInventors: Onkar Jayant Dabeer, Gerhard Reitmayr, Ravi Teja Sukhavasi, Kiran Somasundaram, Radhika Dilip Gowaikar
-
Patent number: 10548124Abstract: Methods, apparatuses, systems, and devices are described for wireless communication. In one method, a control format indicator value for a frame may be received over a physical carrier in a shared spectrum. Based on the control format indicator value, a number of subframes of the frame to be used by a base station for downlink transmissions over the physical carrier may be determined. The control format indicator value may indicate an end of transmission, if data is to be transmitted during the frame, a number of subframes to be used for transmission, or whether the current subframe is the final subframe used for transmission. In some cases, a user equipment (UE) may use the control format indicator value to determine a sleep schedule. Further, ACK/NACK transmissions by a UE may be scheduled based on the control format indicator value.Type: GrantFiled: July 25, 2017Date of Patent: January 28, 2020Assignee: QUALCOMM IncorporatedInventors: Wanshi Chen, Hao Xu, Peter Gaal, Tao Luo, Srinivas Yerramalli, Tingfang Ji, Aleksandar Damnjanovic, Yongbin Wei, Naga Bhushan, Durga Prasad Malladi, Ravi Teja Sukhavasi
-
Patent number: 10476615Abstract: The present disclosure, for example, relates to one or more techniques for scaling the bandwidth of a carrier. Available sub-channels of an unlicensed radio frequency spectrum band may be determined, and the available sub-channels may be included in the carrier. The available sub-channels may be adjacent or non-adjacent sub-channels. The bandwidth of the carrier may be determined according to which sub-channels are included in the carrier. In this way, the bandwidth of the carrier may be scaled according to the available sub-channels in the unlicensed radio frequency spectrum band.Type: GrantFiled: April 24, 2015Date of Patent: November 12, 2019Assignee: QUALCOMM IncorporatedInventors: Srinivas Yerramalli, Tao Luo, Ravi Teja Sukhavasi, Makesh Pravin John Wilson, Kiran Kumar Somasundaram, Onkar Dabeer, Durga Prasad Malladi, Naga Bhushan, Yongbin Wei, Peter Gaal, Wanshi Chen, Hao Xu, Aleksandar Damnjanovic
-
Patent number: 10477409Abstract: Methods and apparatus for wireless communication are described. A method may include receiving at a user equipment (UE) a number of allocated interlaces for an uplink transmission over a shared spectrum, each of which may include a plurality of non-contiguous resource blocks (RB) of the shared spectrum. In some cases, the number of allocated interlaces is unsupported by joint interlace precoding hardware of the UE and the allocated interlaces may be partitioned into subsets of interlaces which may be a size supported by the joint interlace precoding hardware. Reference signals may be generated for the RBs of the allocated interlaces according to a reference signal sequence based on an ordering of the RBs for the allocated interlaces within the shared spectrum.Type: GrantFiled: November 16, 2018Date of Patent: November 12, 2019Assignee: QUALCOMM IncorporatedInventors: Srinivas Yerramalli, Tao Luo, Durga Prasad Malladi, Naga Bhushan, Yongbin Wei, Peter Gaal, Wanshi Chen, Aleksandar Damnjanovic, Tingfang Ji, Ravi Teja Sukhavasi