Patents by Inventor Cheng-Chieh Yang
Cheng-Chieh Yang 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: 20240134807Abstract: The invention relates to a logic control device of a serial peripheral interface, a master-slave system and a master-slave switchover method therefor. The logic control device is connected between N masters and M slaves, and define master-slave connection relationships between each of the masters and each of the slaves. Each of the master-slave connection relationship is that each of the masters and each of the slaves transmit information one-to-one at the same time, and includes connecting the logic control device between the masters and the slaves to form the master-slave system as well as the master-slave switchover method therefor.Type: ApplicationFiled: October 19, 2022Publication date: April 25, 2024Inventors: CHUN CHIEH WANG, CHENG YU WANG, JIN KAI YANG
-
Publication number: 20240078695Abstract: In various examples, surface profile estimation and bump detection may be performed based on a three-dimensional (3D) point cloud. The 3D point cloud may be filtered in view of a portion of an environment including drivable free-space, and within a threshold height to factor out other objects or obstacles other than a driving surface and protuberances thereon. The 3D point cloud may be analyzed—e.g., using a sliding window of bounding shapes along a longitudinal or other heading direction—to determine one-dimensional (1D) signal profiles corresponding to heights along the driving surface. The profile itself may be used by a vehicle—e.g., an autonomous or semi-autonomous vehicle—to help in navigating the environment, and/or the profile may be used to detect bumps, humps, and/or other protuberances along the driving surface, in addition to a location, orientation, and geometry thereof.Type: ApplicationFiled: November 8, 2023Publication date: March 7, 2024Inventors: Minwoo Park, Yue Wu, Michael Grabner, Cheng-Chieh Yang
-
Publication number: 20240059295Abstract: In various examples, systems and methods are disclosed that detect hazards on a roadway by identifying discontinuities between pixels on a depth map. For example, two synchronized stereo cameras mounted on an ego-machine may generate images that may be used extract depth or disparity information. Because a hazard's height may cause an occlusion of the driving surface behind the hazard from a perspective of a camera(s), a discontinuity in disparity values may indicate the presence of a hazard. For example, the system may analyze pairs of pixels on the depth map and, when the system determines that a disparity between a pair of pixels satisfies a disparity threshold, the system may identify the pixel nearest the ego-machine as a hazard pixel.Type: ApplicationFiled: October 31, 2023Publication date: February 22, 2024Inventors: Minwoo Park, Yue Wu, Cheng-Chieh Yang
-
Publication number: 20240062657Abstract: In various examples, a sequential deep neural network (DNN) may be trained using ground truth data generated by correlating (e.g., by cross-sensor fusion) sensor data with image data representative of a sequences of images. In deployment, the sequential DNN may leverage the sensor correlation to compute various predictions using image data alone. The predictions may include velocities, in world space, of objects in fields of view of an ego-vehicle, current and future locations of the objects in image space, and/or a time-to-collision (TTC) between the objects and the ego-vehicle. These predictions may be used as part of a perception system for understanding and reacting to a current physical environment of the ego-vehicle.Type: ApplicationFiled: October 20, 2023Publication date: February 22, 2024Inventors: Yue Wu, Pekka Janis, Xin Tong, Cheng-Chieh Yang, Minwoo Park, David Nister
-
Patent number: 11900629Abstract: In various examples, surface profile estimation and bump detection may be performed based on a three-dimensional (3D) point cloud. The 3D point cloud may be filtered in view of a portion of an environment including drivable free-space, and within a threshold height to factor out other objects or obstacles other than a driving surface and protuberances thereon. The 3D point cloud may be analyzed—e.g., using a sliding window of bounding shapes along a longitudinal or other heading direction—to determine one-dimensional (1D) signal profiles corresponding to heights along the driving surface. The profile itself may be used by a vehicle—e.g., an autonomous or semi-autonomous vehicle—to help in navigating the environment, and/or the profile may be used to detect bumps, humps, and/or other protuberances along the driving surface, in addition to a location, orientation, and geometry thereof.Type: GrantFiled: February 27, 2023Date of Patent: February 13, 2024Assignee: NVIDIA CorporationInventors: Minwoo Park, Yue Wu, Michael Grabner, Cheng-Chieh Yang
-
Patent number: 11854401Abstract: In various examples, a sequential deep neural network (DNN) may be trained using ground truth data generated by correlating (e.g., by cross-sensor fusion) sensor data with image data representative of a sequences of images. In deployment, the sequential DNN may leverage the sensor correlation to compute various predictions using image data alone. The predictions may include velocities, in world space, of objects in fields of view of an ego-vehicle, current and future locations of the objects in image space, and/or a time-to-collision (TTC) between the objects and the ego-vehicle. These predictions may be used as part of a perception system for understanding and reacting to a current physical environment of the ego-vehicle.Type: GrantFiled: December 16, 2022Date of Patent: December 26, 2023Assignee: NVIDIA CorporationInventors: Yue Wu, Pekka Janis, Xin Tong, Cheng-Chieh Yang, Minwoo Park, David Nister
-
Patent number: 11840238Abstract: In various examples, systems and methods are disclosed that detect hazards on a roadway by identifying discontinuities between pixels on a depth map. For example, two synchronized stereo cameras mounted on an ego-machine may generate images that may be used extract depth or disparity information. Because a hazard's height may cause an occlusion of the driving surface behind the hazard from a perspective of a camera(s), a discontinuity in disparity values may indicate the presence of a hazard. For example, the system may analyze pairs of pixels on the depth map and, when the system determines that a disparity between a pair of pixels satisfies a disparity threshold, the system may identify the pixel nearest the ego-machine as a hazard pixel.Type: GrantFiled: November 29, 2021Date of Patent: December 12, 2023Assignee: NVIDIA CorporationInventors: Minwoo Park, Yue Wu, Cheng-Chieh Yang
-
Publication number: 20230351638Abstract: In various examples, system and methods for stereo disparity based hazard detection for autonomous machine applications are presented. Example embodiments may assist an ego-machine in detecting hazards within its path of travel. The systems and methods may use disparity between a stereo pair of images to generate a baseline path disparity model and further identify hazards from detected disparities that deviate from that path disparity model. A disparity map for the image pair is constructed in which each pixel represents a disparity for a corresponding element of the image captured. Blockwise division may be optionally used to subdivide the disparity map into a plurality of smaller disparity maps, each corresponding to a block of pixels of the disparity map. A V-space disparity map, where a first axis corresponds to disparity values and the second axis corresponds to pixel rows, may be used to simplify estimation of the path disparity model.Type: ApplicationFiled: April 29, 2022Publication date: November 2, 2023Inventors: Yue WU, Liwen Lin, Cheng-Chieh Yang, Gang Pan
-
Publication number: 20230253706Abstract: An antenna structure includes a feeding radiation element, a first radiation element, a second radiation element, a third radiation element, a fourth radiation element, a fifth radiation element, and a switch circuit. The feeding radiation element has a feeding point. The second radiation element is coupled through the first radiation element to the feeding radiation element. The third radiation element is coupled to the second radiation element. The fourth radiation element is coupled to the second radiation element. The fourth radiation element and the third radiation element extend in different directions. The fifth radiation element has a tuning point, and is coupled to the feeding radiation element. The feeding radiation element is disposed between the first radiation element and the fifth radiation element. The switch circuit selectively couples the tuning point to a ground voltage.Type: ApplicationFiled: March 21, 2022Publication date: August 10, 2023Inventors: Cheng-Chieh YANG, Chih-Ming CHEN, Po-Yu CHEN
-
Publication number: 20230230273Abstract: In various examples, surface profile estimation and bump detection may be performed based on a three-dimensional (3D) point cloud. The 3D point cloud may be filtered in view of a portion of an environment including drivable free-space, and within a threshold height to factor out other objects or obstacles other than a driving surface and protuberances thereon. The 3D point cloud may be analyzed—e.g., using a sliding window of bounding shapes along a longitudinal or other heading direction—to determine one-dimensional (1D) signal profiles corresponding to heights along the driving surface. The profile itself may be used by a vehicle—e.g., an autonomous or semi-autonomous vehicle—to help in navigating the environment, and/or the profile may be used to detect bumps, humps, and/or other protuberances along the driving surface, in addition to a location, orientation, and geometry thereof.Type: ApplicationFiled: February 27, 2023Publication date: July 20, 2023Inventors: Minwoo Park, Yue Wu, Michael Grabner, Cheng-Chieh Yang
-
Publication number: 20230178893Abstract: A communication device includes an RF (Radio Frequency) module, an antenna structure, a first switch element, a second switch element, a plurality of first impedance elements, and a plurality of second impedance elements. The antenna structure is coupled to the RF module. The antenna structure includes a first radiation element and a second radiation element. The first switch element is coupled to the first radiation element. The first switch element is switchable between the first impedance elements. The second switch element is coupled to the second radiation element. The second switch element is switchable between the second impedance elements.Type: ApplicationFiled: January 24, 2022Publication date: June 8, 2023Inventors: Cheng-Chieh YANG, Yi Shien CHEN
-
Patent number: 11657532Abstract: In various examples, surface profile estimation and bump detection may be performed based on a three-dimensional (3D) point cloud. The 3D point cloud may be filtered in view of a portion of an environment including drivable free-space, and within a threshold height to factor out other objects or obstacles other than a driving surface and protuberances thereon. The 3D point cloud may be analyzed—e.g., using a sliding window of bounding shapes along a longitudinal or other heading direction—to determine one-dimensional (1D) signal profiles corresponding to heights along the driving surface. The profile itself may be used by a vehicle—e.g., an autonomous or semi-autonomous vehicle—to help in navigating the environment, and/or the profile may be used to detect bumps, humps, and/or other protuberances along the driving surface, in addition to a location, orientation, and geometry thereof.Type: GrantFiled: November 24, 2020Date of Patent: May 23, 2023Assignee: NVIDIA CorporationInventors: Minwoo Park, Yue Wu, Michael Grabner, Cheng-Chieh Yang
-
Publication number: 20230122119Abstract: In various examples, a sequential deep neural network (DNN) may be trained using ground truth data generated by correlating (e.g., by cross-sensor fusion) sensor data with image data representative of a sequences of images. In deployment, the sequential DNN may leverage the sensor correlation to compute various predictions using image data alone. The predictions may include velocities, in world space, of objects in fields of view of an ego-vehicle, current and future locations of the objects in image space, and/or a time-to-collision (TTC) between the objects and the ego-vehicle. These predictions may be used as part of a perception system for understanding and reacting to a current physical environment of the ego-vehicle.Type: ApplicationFiled: December 16, 2022Publication date: April 20, 2023Inventors: Yue Wu, Pekka Janis, Xin Tong, Cheng-Chieh Yang, Minwoo Park, David Nister
-
Patent number: 11579629Abstract: In various examples, a sequential deep neural network (DNN) may be trained using ground truth data generated by correlating (e.g., by cross-sensor fusion) sensor data with image data representative of a sequences of images. In deployment, the sequential DNN may leverage the sensor correlation to compute various predictions using image data alone. The predictions may include velocities, in world space, of objects in fields of view of an ego-vehicle, current and future locations of the objects in image space, and/or a time-to-collision (TTC) between the objects and the ego-vehicle. These predictions may be used as part of a perception system for understanding and reacting to a current physical environment of the ego-vehicle.Type: GrantFiled: July 17, 2019Date of Patent: February 14, 2023Assignee: NVIDIA CorporationInventors: Yue Wu, Pekka Janis, Xin Tong, Cheng-Chieh Yang, Minwoo Park, David Nister
-
Publication number: 20220340149Abstract: In various examples, an end-to-end perception evaluation system for autonomous and semi-autonomous machine applications may be implemented to evaluate how the accuracy or precision of outputs of machine learning models—such as deep neural networks (DNNs)—impact downstream performance of the machine when relied upon. For example, decisions computed by the system using ground truth output types may be compared to decisions computed by the system using the perception outputs. As a result, discrepancies in downstream decision making of the system between the ground truth information and the perception information may be evaluated to either aid in updating or retraining of the machine learning model or aid in generating more accurate or precise ground truth information.Type: ApplicationFiled: April 21, 2022Publication date: October 27, 2022Inventors: David Nister, Cheng-Chieh Yang, Yue Wu
-
Publication number: 20220301186Abstract: In various examples, an ego-machine may analyze sensor data to identify and track features in the sensor data using. Geometry of the tracked features may be used to analyze motion flow to determine whether the motion flow violates one or more geometrical constraints. As such, tracked features may be identified as dynamic features when the motion flow corresponding to the tracked features violates the one or more static constraints for static features. Tracked features that are determined to be dynamic features may be clustered together according to their location and feature track. Once features have been clustered together, the system may calculate a detection bounding shape for the clustered features. The bounding shape information may then be used by the ego-machine for path planning, control decisions, obstacle avoidance, and/or other operations.Type: ApplicationFiled: February 23, 2022Publication date: September 22, 2022Inventors: David Nister, Soohwan Kim, Yue Wu, Minwoo Park, Cheng-Chieh Yang
-
Publication number: 20220250624Abstract: In various examples, systems and methods are disclosed that detect hazards on a roadway by identifying discontinuities between pixels on a depth map. For example, two synchronized stereo cameras mounted on an ego-machine may generate images that may be used extract depth or disparity information. Because a hazard's height may cause an occlusion of the driving surface behind the hazard from a perspective of a camera(s), a discontinuity in disparity values may indicate the presence of a hazard. For example, the system may analyze pairs of pixels on the depth map and, when the system determines that a disparity between a pair of pixels satisfies a disparity threshold, the system may identify the pixel nearest the ego-machine as a hazard pixel.Type: ApplicationFiled: November 29, 2021Publication date: August 11, 2022Inventors: Minwoo Park, Yue Wu, Cheng-Chieh Yang
-
Patent number: 11387576Abstract: An antenna system includes a first antenna element, a second antenna element, and a circuit region. The first antenna element includes a first nonconductive support element and a first main radiation element. The first main radiation element is disposed on the first nonconductive support element. The second antenna element includes a second nonconductive support element and a second main radiation element. The second main radiation element is disposed on the second nonconductive support element. The second main radiation element is at least partially perpendicular to the first main radiation element. The circuit region is positioned between the first antenna element and the second antenna element.Type: GrantFiled: February 4, 2021Date of Patent: July 12, 2022Assignee: WISTRON CORP.Inventors: Chien Hsun Chen, Cheng-Chieh Yang
-
Publication number: 20220209429Abstract: An antenna system includes a first antenna element, a second antenna element, and a circuit region. The first antenna element includes a first nonconductive support element and a first main radiation element. The first main radiation element is disposed on the first nonconductive support element. The second antenna element includes a second nonconductive support element and a second main radiation element. The second main radiation element is disposed on the second nonconductive support element. The second main radiation element is at least partially perpendicular to the first main radiation element. The circuit region is positioned between the first antenna element and the second antenna element.Type: ApplicationFiled: February 4, 2021Publication date: June 30, 2022Inventors: Chien Hsun CHEN, Cheng-Chieh YANG
-
Publication number: 20220166142Abstract: An antenna structure includes a feeding radiation element, a first radiation element, a second radiation element, a nonconductive support element, and an accessory element. The feeding radiation element has a feeding point. The first radiation element includes a branch portion and a widening portion. The feeding radiation element is coupled through the first radiation element to a ground voltage. The second radiation element is coupled to the feeding radiation element and the first radiation element. The nonconductive support element carries the feeding radiation element, the first radiation element, and the second radiation element. The accessory element includes a nonconductive housing and an internal metal element. The branch portion and widening portion of the first radiation element are disposed on the nonconductive housing of the accessory element.Type: ApplicationFiled: December 29, 2020Publication date: May 26, 2022Inventors: Cheng-Chieh YANG, Chih-Ming CHEN