Patents by Inventor Wei Chai
Wei Chai 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: 12272082Abstract: The disclosed method includes acquiring sample models and marking sample feature points; selecting target feature points and regional points on bones; transforming the target feature points and the regional points, and registering the target feature points with the sample feature points; formulating a strategy for assigning impact factors to the sample models, linearly combining all sample models to construct an initial model, and determining initial feature points corresponding to the target feature points in the initial model; adjusting the strategy according to the distance between initial feature points and the target feature points, selecting the strategy corresponding to the minimum distance as an optimal strategy, and determining an optimal initial model; determining a matching point corresponding to each regional point in the optimal initial model, and calculating a transformation relationship; and transmitting all points of the optimal initial model according to the transformation relationship to obtType: GrantFiled: March 13, 2024Date of Patent: April 8, 2025Assignees: Vostro Medical Technology (Tianjin) Co., Ltd, The Fourth Medical Center of PLA General HospitalInventors: Mingjun Fu, Wei Chai, Yuan Zhang, Mingmin Ren, Guoqing Yu, Linshuai He, Mingcheng Shen, Zhongwei Wang, Chengcheng Shang
-
Patent number: 12221118Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing knowledge distillation for autonomous vehicles. One of the methods includes obtaining sensor data characterizing an environment, wherein the sensor data has been captured by one or more sensors on-board a vehicle in the environment; processing, for each of one or more surrounding agents in the environment, a network input generated from the sensor data using a neural network to generate an agent discomfort prediction that characterizes a level of discomfort of the agent; combining the one or more agent discomfort predictions to generate an aggregated discomfort score; and providing the aggregated discomfort score to a path planning system of the vehicle in order to generate a future path of the vehicle.Type: GrantFiled: September 4, 2020Date of Patent: February 11, 2025Assignee: Waymo LLCInventors: Minfa Wang, Kai Ding, Haoyu Chen, Wei Chai, Maher Mneimneh
-
Publication number: 20240420353Abstract: The disclosed method includes acquiring sample models and marking sample feature points; selecting target feature points and regional points on bones; transforming the target feature points and the regional points, and registering the target feature points with the sample feature points; formulating a strategy for assigning impact factors to the sample models, linearly combining all sample models to construct an initial model, and determining initial feature points corresponding to the target feature points in the initial model; adjusting the strategy according to the distance between initial feature points and the target feature points, selecting the strategy corresponding to the minimum distance as an optimal strategy, and determining an optimal initial model; determining a matching point corresponding to each regional point in the optimal initial model, and calculating a transformation relationship; and transmitting all points of the optimal initial model according to the transformation relationship to obtType: ApplicationFiled: March 13, 2024Publication date: December 19, 2024Inventors: Mingjun Fu, Wei Chai, Mingmin Ren, Guoqing Yu, Linshuai He, Mingcheng Shen, Zhongwei Wang, Chengcheng Shang
-
Publication number: 20240403031Abstract: The present disclosure provides an application development platform and associated software development kits (“SDKs”) that provide comprehensive services for generation, deployment, and management of machine-learned models used by computer applications such as, for example, mobile applications executed by a mobile computing device. In particular, the application development platform and SDKs can provide or otherwise leverage a unified, cross-platform application programming interface (“API”) that enables access to all of the different machine learning services needed for full machine learning functionality within the application. In such fashion, developers can have access to a single SDK for all machine learning services.Type: ApplicationFiled: August 16, 2024Publication date: December 5, 2024Inventors: Wei Chai, Pannag Sanketi, Ibrahim Elbouchikhi, Sachin Kotwani, Wesley Robert Tarle
-
Patent number: 12093675Abstract: Provided is an application development platform and associated software development kits (“SDKs”) that provide comprehensive services for generation, deployment, and management of machine-learned models used by computer applications such as, for example, mobile applications executed by a mobile computing device. In particular, the application development platform and SDKs can provide or otherwise leverage a unified, cross-platform application programming interface (“API”) that enables access to all of the different machine learning services needed for full machine learning functionality within the application. In such fashion, developers can have access to a single SDK for all machine learning services.Type: GrantFiled: August 21, 2018Date of Patent: September 17, 2024Assignee: GOOGLE LLCInventors: Wei Chai, Pannag Sanketi, Ibrahim Elbouchikhi, Sachin Kotwani, Wesley Robert Tarle
-
Publication number: 20240278802Abstract: Data representing a set of predicted trajectories and a planned trajectory for an autonomous vehicle is obtained. A predictability score for the planned trajectory can be determined based on a comparison of the planned trajectory to the set of predicted trajectories for the autonomous vehicle. The predictability score indicates a level of predictability of the planned trajectory. A determination can be made, based at least on the predictability score, whether to initiate travel with the autonomous vehicle along the planned trajectory. In response to determining to initiate travel with the autonomous vehicle along the planned trajectory, a control system can be directed to maneuver the autonomous vehicle along the planned trajectory.Type: ApplicationFiled: December 21, 2023Publication date: August 22, 2024Inventors: Khaled Refaat, Haoyu Chen, Wei Chai, Alisha Saxena
-
Patent number: 11989755Abstract: Systems and methods of evaluating information in a computer network environment are provided. A data processing system can obtain or receive a content placement criterion, such as a keyword, associated with a content item and can determine a quality metric of the content placement criterion. The data processing system can identify a candidate content placement criterion and expand placement criteria associated with the content item to include the content placement criterion and the candidate content placement criterion based at least in part on an evaluation of the quality metric of the content placement criterion. The data processing system can expand placement criteria based in part on a throttling parameter. The data processing system can identify a correlation between a document and the placement criteria to identify appropriate content items for the document.Type: GrantFiled: August 1, 2022Date of Patent: May 21, 2024Assignee: Google LLCInventors: Gaofeng Zhao, Yingwei Cui, Hui Tan, Bahman Rabii, Wei Chai
-
Patent number: 11977382Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. The high-priority agents can be identified based on a set of mutual importance scores in which each mutual importance score indicates an estimated mutual relevance between the vehicle and a different agent from a set of agents on planning decisions of the other. The mutual importance scores can be calculated based on importance scores assessed from the perspectives of both the vehicle and the agents.Type: GrantFiled: May 15, 2023Date of Patent: May 7, 2024Assignee: Waymo LLCInventors: Kai Ding, Minfa Wang, Haoyu Chen, Khaled Refaat, Stephane Ross, Wei Chai
-
Publication number: 20240017039Abstract: A vein detection device including a light source operating at a wavelength for penetrating skin of a patient, a stereo camera operating at the wavelength, a communication interface configured to connect to a mobile device, and a processor. The processor configured to control the light source to illuminate a region of the skin, control the stereo camera to capture an image in the illuminated region, process the captured image to detect a vein of the patient illuminated by the light source, reconstruct a three dimensional image of the detected vein, and transmit the three dimensional image of the detected vein to the mobile device via the communication interface.Type: ApplicationFiled: December 3, 2021Publication date: January 18, 2024Applicant: B. Braun Melsungen AGInventors: Jo Ann Hang, Jien Wei Chai
-
Patent number: 11851081Abstract: Data representing a set of predicted trajectories and a planned trajectory for an autonomous vehicle is obtained. A predictability score for the planned trajectory can be determined based on a comparison of the planned trajectory to the set of predicted trajectories for the autonomous vehicle. The predictability score indicates a level of predictability of the planned trajectory. A determination can be made, based at least on the predictability score, whether to initiate travel with the autonomous vehicle along the planned trajectory. In response to determining to initiate travel with the autonomous vehicle along the planned trajectory, a control system can be directed to maneuver the autonomous vehicle along the planned trajectory.Type: GrantFiled: December 1, 2020Date of Patent: December 26, 2023Assignee: Waymo LLCInventors: Khaled Refaat, Haoyu Chen, Wei Chai, Alisha Saxena
-
Publication number: 20230288929Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. The high-priority agents can be identified based on a set of mutual importance scores in which each mutual importance score indicates an estimated mutual relevance between the vehicle and a different agent from a set of agents on planning decisions of the other. The mutual importance scores can be calculated based on importance scores assessed from the perspectives of both the vehicle and the agents.Type: ApplicationFiled: May 15, 2023Publication date: September 14, 2023Inventors: Kai Ding, Minfa Wang, Haoyu Chen, Khaled Refaat, Stephane Ross, Wei Chai
-
Publication number: 20230280753Abstract: Methods, systems, and apparatus for predicting future trajectories of agents in an environment. In one aspect, a system comprises one or more computers configured to receive a data set comprising multiple training examples. The training examples include scene data comprising respective agent data for multiple agents and a ground truth trajectory for a target agent that represents ground truth motion of the target agent after a corresponding time point. The one or more computers obtain data identifying one or more of the multiple agents as non-causal agents for each training example. A non-causal agent is an agent whose states do not cause the ground truth trajectory for the target agent to change. The one or more computers generate a respective modified training example from each of the multiple training examples.Type: ApplicationFiled: March 7, 2023Publication date: September 7, 2023Inventors: Benjamin James Caine, Khaled Refaat, Benjamin Sapp, Scott Morgan Ettinger, Wei Chai, Rebecca Dawn Roelofs, Liting Sun
-
Patent number: 11687077Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. The high-priority agents can be identified based on a set of mutual importance scores in which each mutual importance score indicates an estimated mutual relevance between the vehicle and a different agent from a set of agents on planning decisions of the other. The mutual importance scores can be calculated based on importance scores assessed from the perspectives of both the vehicle and the agents.Type: GrantFiled: August 7, 2020Date of Patent: June 27, 2023Assignee: Waymo LLCInventors: Kai Ding, Minfa Wang, Haoyu Chen, Khaled Refaat, Stephane Ross, Wei Chai
-
Patent number: 11430003Abstract: Systems and methods of evaluating information in a computer network environment are provided. A data processing system can obtain or receive a content placement criterion, such as a keyword, associated with a content item and can determine a quality metric of the content placement criterion. The data processing system can identify a candidate content placement criterion and expand placement criteria associated with the content item to include the content placement criterion and the candidate content placement criterion based at least in part on an evaluation of the quality metric of the content placement criterion. The data processing system can expand placement criteria based in part on a throttling parameter. The data processing system can identify a correlation between a document and the placement criteria to identify appropriate content items for the document.Type: GrantFiled: February 3, 2021Date of Patent: August 30, 2022Assignee: Google LLCInventors: Gaofeng Zhao, Yingwei Cui, Hui Tan, Bahman Rabii, Wei Chai
-
Publication number: 20220169278Abstract: Data representing a set of predicted trajectories and a planned trajectory for an autonomous vehicle is obtained. A predictability score for the planned trajectory can be determined based on a comparison of the planned trajectory to the set of predicted trajectories for the autonomous vehicle. The predictability score indicates a level of predictability of the planned trajectory. A determination can be made, based at least on the predictability score, whether to initiate travel with the autonomous vehicle along the planned trajectory. In response to determining to initiate travel with the autonomous vehicle along the planned trajectory, a control system can be directed to maneuver the autonomous vehicle along the planned trajectory.Type: ApplicationFiled: December 1, 2020Publication date: June 2, 2022Inventors: Khaled Refaat, Haoyu Chen, Wei Chai, Alisha Saxena
-
Publication number: 20220096242Abstract: An MTS medial tibial plateau patch, a modular MTS medial tibial plateau patch, and a minimally invasive replacement method thereof are disclosed. The MTS medial tibial plateau patch includes an articular surface provided with an arc-shaped recessed area and a bottom surface provided with 3 stand columns distributed triangularly, or two longitudinal keels having non-parallel distribution or two triangular keel wings, and the arc-shaped recessed area is well matched and in a sliding fit with a femoral condyle without an increase in impact in a joint, thus guaranteeing a stability of a prosthesis, realizing a concept of a minimally invasive surgery, and reducing damage to a normal tissue. The modular MTS medial tibial plateau patch includes a bone-trabecula metal tibial support and a liner made of VE high cross-linked polyethylene.Type: ApplicationFiled: April 15, 2019Publication date: March 31, 2022Inventors: Yan WANG, Wei CHAI
-
Publication number: 20220091837Abstract: The present disclosure provides an application development platform and associated software development kits (“SDKs”) that provide comprehensive services for generation, deployment, and management of machine-learned models used by computer applications such as, for example, mobile applications executed by a mobile computing device. In particular, the application development platform and SDKs can provide or otherwise leverage a unified, cross-platform application programming interface (“API”) that enables access to all of the different machine learning services needed for full machine learning functionality within the application. In such fashion, developers can have access to a single SDK for all machine learning services.Type: ApplicationFiled: August 21, 2018Publication date: March 24, 2022Inventors: Wei Chai, Pannag Sanketi, Ibrahim Elbouchikhi, Sachin Kotwani, Wesley Robert Tarle
-
Publication number: 20220073085Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing knowledge distillation for autonomous vehicles. One of the methods includes obtaining sensor data characterizing an environment, wherein the sensor data has been captured by one or more sensors on-board a vehicle in the environment; processing, for each of one or more surrounding agents in the environment, a network input generated from the sensor data using a neural network to generate an agent discomfort prediction that characterizes a level of discomfort of the agent; combining the one or more agent discomfort predictions to generate an aggregated discomfort score; and providing the aggregated discomfort score to a path planning system of the vehicle in order to generate a future path of the vehicle.Type: ApplicationFiled: September 4, 2020Publication date: March 10, 2022Inventors: Minfa Wang, Kai Ding, Haoyu Chen, Wei Chai, Maher Mneimneh
-
Publication number: 20220043446Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. The high-priority agents can be identified based on a set of mutual importance scores in which each mutual importance score indicates an estimated mutual relevance between the vehicle and a different agent from a set of agents on planning decisions of the other. The mutual importance scores can be calculated based on importance scores assessed from the perspectives of both the vehicle and the agents.Type: ApplicationFiled: August 7, 2020Publication date: February 10, 2022Inventors: Kai Ding, Minfa Wang, Haoyu Chen, Khaled Refaat, Stephane Ross, Wei Chai
-
Patent number: 10943259Abstract: Systems and methods of evaluating information in a computer network environment are provided. A data processing system can obtain or receive a content placement criterion, such as a keyword, associated with a content item and can determine a quality metric of the content placement criterion. The data processing system can identify a candidate content placement criterion and expand placement criteria associated with the content item to include the content placement criterion and the candidate content placement criterion based at least in part on an evaluation of the quality metric of the content placement criterion. The data processing system can expand placement criteria based in part on a throttling parameter. The data processing system can identify a correlation between a document and the placement criteria to identify appropriate content items for the document.Type: GrantFiled: April 19, 2019Date of Patent: March 9, 2021Assignee: Google LLCInventors: Gaofeng Zhao, Yingwei Cui, Hui Tan, Bahman Rabii, Wei Chai