Patents by Inventor Zhongxuan LIU
Zhongxuan LIU 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: 20240123617Abstract: Apparatus, systems, articles of manufacture, and methods for robot movement are disclosed. An example robot movement apparatus includes a sequence generator to generate a sequence of context variable vectors and policy variable vectors. The context variable vectors are related to a movement target, and the policy variable vectors are related to a movement trajectory. The example apparatus includes a calculator to calculate an upper policy and a loss function based on the sequence. The upper policy is indicative of a robot movement, and the loss function is indicative of a degree to which a movement target is met. The example apparatus also includes a comparator to determine if the loss function satisfies a threshold and an actuator to cause the robot to perform the robot movement of the upper policy when the loss function satisfies the threshold.Type: ApplicationFiled: October 23, 2023Publication date: April 18, 2024Inventors: Zhongxuan Liu, Zhe Weng
-
Patent number: 11948333Abstract: A disparity image fusion method for multiband stereo cameras belongs to the field of image processing and computer vision. The method obtains pixel disparity confidence information by using the intermediate output of binocular disparity estimation. The confidence information can be used to judge the disparity credibility of the position and assist disparity fusion. The confidence acquisition process makes full use of the intermediate output of calculation, and can be conveniently embedded into the traditional disparity estimation process, with high calculation efficiency and simple and easy operation. In the disparity image fusion method for multiband stereo cameras proposed by the method, the disparity diagrams participating in the fusion are obtained according to the binocular images of the corresponding bands, which makes full use of the information of each band and simultaneously avoiding introducing uncertainty and errors.Type: GrantFiled: March 5, 2020Date of Patent: April 2, 2024Assignees: DALIAN UNIVERSITY OF TECHNOLOGY, PENG CHENG LABORATORYInventors: Wei Zhong, Hong Zhang, Haojie Li, Zhihui Wang, Risheng Liu, Xin Fan, Zhongxuan Luo, Shengquan Li
-
Patent number: 11859973Abstract: Embodiments described herein provide a processing apparatus comprising compute logic to train a convolutional neural network (CNN) to perform autonomous re-localization for a service robot or mobile device. In one embodiment the apparatus comprises an image processor to process visual data received via a sensor and a general purpose graphics processing engine perform camera pose estimation for image data and generate a transformation matrix to transform positions of camera pose estimations to positions within a human readable map of the location. The images and transformed positions are uses to train the CNN to perform re-localization.Type: GrantFiled: September 3, 2021Date of Patent: January 2, 2024Assignee: Intel CorporationInventor: Zhongxuan Liu
-
Patent number: 11850752Abstract: Apparatus, systems, articles of manufacture, and methods for robot movement are disclosed. An example robot movement apparatus includes a sequence generator to generate a sequence of context variable vectors and policy variable vectors. The context variable vectors are related to a movement target, and the policy variable vectors are related to a movement trajectory. The example apparatus includes a calculator to calculate an upper policy and a loss function based on the sequence. The upper policy is indicative of a robot movement, and the loss function is indicative of a degree to which a movement target is met. The example apparatus also includes a comparator to determine if the loss function satisfies a threshold and an actuator to cause the robot to perform the robot movement of the upper policy when the loss function satisfies the threshold.Type: GrantFiled: September 28, 2018Date of Patent: December 26, 2023Assignee: Intel CorporationInventors: Zhongxuan Liu, Zhe Weng
-
Patent number: 11494641Abstract: A system and method of teaching a neural network through reinforcement learning methodology. The system includes a machine-readable medium having one or more processors that perform a motion task to produce a first result corresponding to navigating a device during a first episode and performing an interaction task during that same episode. After completion of the first episode a processor calculates a Q value change based on the first task result and the second task result. The processor then modifies parameters based on the Q value change such that during subsequent episode iterations the motion task and interactive task are improved and a smooth and continuous transition occurs between these two tasks.Type: GrantFiled: December 27, 2017Date of Patent: November 8, 2022Assignee: Intel CorporationInventors: Hu Tiger Chen, Zhongxuan Liu, Yimin Zhang, Haibing Ren, Jiankun Hu
-
Publication number: 20220058828Abstract: Embodiments described herein provide a processing apparatus comprising compute logic to train a convolutional neural network (CNN) to perform autonomous re-localization for a service robot or mobile device. In one embodiment the apparatus comprises an image processor to process visual data received via a sensor and a general purpose graphics processing engine perform camera pose estimation for image data and generate a transformation matrix to transform positions of camera pose estimations to positions within a human readable map of the location. The images and transformed positions are uses to train the CNN to perform re-localization.Type: ApplicationFiled: September 3, 2021Publication date: February 24, 2022Inventor: Zhongxuan LIU
-
Publication number: 20210308863Abstract: Apparatus, systems, articles of manufacture, and methods for robot movement are disclosed. An example robot movement apparatus includes a sequence generator to generate a sequence of context variable vectors and policy variable vectors. The context variable vectors are related to a movement target, and the policy variable vectors are related to a movement trajectory. The example apparatus includes a calculator to calculate an upper policy and a loss function based on the sequence. The upper policy is indicative of a robot movement, and the loss function is indicative of a degree to which a movement target is met. The example apparatus also includes a comparator to determine if the loss function satisfies a threshold and an actuator to cause the robot to perform the robot movement of the upper policy when the loss function satisfies the threshold.Type: ApplicationFiled: September 28, 2018Publication date: October 7, 2021Inventors: Zhongxuan LIU, Zhe WENG
-
Patent number: 11132816Abstract: A processing apparatus comprising compute logic to train a convolutional neural network (CNN) to perform autonomous re-localization for a service robot or mobile device. An apparatus comprises an image processor to process visual data received via a sensor and a general purpose graphics processing engine perform camera pose estimation for image data and generate a transformation matrix to transform positions of camera pose estimations to positions within a human readable map of the location. The images and transformed positions are uses to train the CNN to perform re-localization.Type: GrantFiled: December 21, 2016Date of Patent: September 28, 2021Assignee: Intel CorporationInventor: Zhongxuan Liu
-
Publication number: 20200226463Abstract: A system and method of teaching a neural network through reinforcement learning methodology. The system includes a machine-readable medium having one or more processors that perform a motion task to produce a first result corresponding to navigating a device during a first episode and performing an interaction task during that same episode. After completion of the first episode a processor calculates a Q value change based on the first task result and the second task result. The processor then modifies parameters based on the Q value change such that during subsequent episode iterations the motion task and interactive task are improved and a smooth and continuous transition occurs between these two tasks.Type: ApplicationFiled: December 27, 2017Publication date: July 16, 2020Inventors: Hu Tiger Chen, Zhongxuan Liu, Yimin Zhang, Haibing Ren, Jianhun Hu
-
Publication number: 20200082567Abstract: A processing apparatus comprising compute logic to train a convolutional neural network (CNN) to perform autonomous re-localization for a service robot or mobile device. An apparatus comprises an image processor to process visual data received via a sensor and a general purpose graphics processing engine perform camera pose estimation for image data and generate a transformation matrix to transform positions of camera pose estimations to positions within a human readable map of the location. The images and transformed positions are uses to train the CNN to perform re-localization.Type: ApplicationFiled: December 21, 2016Publication date: March 12, 2020Inventor: Zhongxuan Liu
-
Publication number: 20200082262Abstract: An apparatus for facilitating accurate camera re-localization in autonomous machines includes an image capturing device to capture an image of an object, selection/comparison logic to select a middle layer from a plurality of convolutional network (CNN) layers, processing/training logic to process superiority of one or more original keyframes of the image with one or more layer-based keyframes associated with the middle layer, and execution/outputting logic to output a first result based on the one or more original keyframes if one of the one or more original keyframes is superior than the one or more layer-based keyframes. A method, a machine-readable medium, a system, an apparatus, a computing device, and a communications device of the embodiments are also described.Type: ApplicationFiled: December 21, 2016Publication date: March 12, 2020Applicant: Intel CorporationInventors: Zhongxuan LIU, Liwei MA
-
Publication number: 20180293756Abstract: Methods, apparatus, and system to obtain a pose from image regression in a trained convolutional neural network (“CNN”), to refine the CNN pose based on inertial measurements from an inertial measurement unit, and to infer a pose of a camera which took the image based on the refined CNN pose.Type: ApplicationFiled: November 18, 2016Publication date: October 11, 2018Inventors: Zhongxuan LIU, Liwei MA