Patents by Inventor Gregory P. Linkowski
Gregory P. Linkowski 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: 11975710Abstract: A vehicle can be detected approaching a limited operation zone of a travel area. It can be determined that the vehicle is able to execute wireless commands from a computer. The object can be identified within the limited operation zone. Based on identifying the object within the limited operation zone, the vehicle can be controlled by providing a control command via wireless communications, the control command including whether the vehicle is permitted to enter the limited operation zone.Type: GrantFiled: March 24, 2021Date of Patent: May 7, 2024Assignee: Ford Global Technologies, LLCInventors: Gregory P. Linkowski, Mario A. Santillo
-
Publication number: 20230315120Abstract: A method for calibrating a map of an autonomous robot, a trajectory of the autonomous robot, or a combination thereof includes obtaining localization data from a localization sensor of the autonomous robot and determining whether a calibration condition of the autonomous robot is satisfied based on the localization data. The method includes, in response to the calibration condition being satisfied: determining a master position coordinate of the autonomous robot based on a plurality of radio frequency (RF) signals broadcasted by a plurality of RF tags, converting the master position coordinate to a local position coordinate of the autonomous robot, and selectively updating the map, the trajectory, or a combination thereof based on the local position coordinate of the autonomous robot.Type: ApplicationFiled: April 1, 2022Publication date: October 5, 2023Applicant: Ford Global Technologies, LLCInventors: Gregory P. Linkowski, Meghna Menon, Shankar Narayan Mohan, Ling Zhu, Songan Zhang
-
Publication number: 20230251662Abstract: A method for controlling a human driven vehicle (HDV) includes identifying HDV indicia of a fiducial marker disposed on the HDV based on localization data obtained from the plurality of localization sensors, determining a pose of the HDV based on the localization data, where the pose of the HDV includes a location and an orientation of the HDV, and defining a bounding region of the HDV based on the HDV indicia and the pose of the HDV. The method includes determining a location-based characteristic of the one or more autonomous devices, where the location-based characteristic includes a location of the one or more autonomous devices, a trajectory of the one or more autonomous devices, or a combination thereof, selectively generating a notification based on the location-based characteristic and the bounding region, and broadcasting the notification to the HDV in response to generating the notification.Type: ApplicationFiled: February 4, 2022Publication date: August 10, 2023Applicant: Ford Global Technologies, LLCInventors: Meghna Menon, Gregory P. Linkowski, Yifan Chen, Geoffrey Horowitz, Sarah Garrow
-
Publication number: 20230195123Abstract: A method for controlling a plurality of autonomous mobile robots (AMRs) in a manufacturing environment having an intersection includes obtaining a plurality of routes associated with the plurality of AMRs, velocity information associated with the plurality of AMRs, and priority information associated with the plurality of AMRs, and determining a plurality of arrival times associated with the plurality of AMRs based on the velocity information and the plurality of routes. The method includes generating a plurality of intersection reservations based on the plurality of arrival times and the priority information, where each intersection reservation from among the plurality of intersection reservations corresponds to an AMR from among the plurality of AMRs, and controlling a movement of the plurality of AMRs through the intersection based on the plurality of intersection reservations.Type: ApplicationFiled: December 22, 2021Publication date: June 22, 2023Applicant: Ford Global Technologies, LLCInventors: Yifan Chen, Gregory P. Linkowski, Meghna Menon, Sarah Garrow, Geoffrey Horowitz
-
Publication number: 20230195139Abstract: A system for reconfiguring a factory having equipment at different workstations throughout the factory and a plurality of sensors disposed throughout the factory includes a factory configuration module configured to store a plurality of predetermined factory configurations and a plurality of mobile transporters configured to engage and transport the equipment to the different workstations throughout the factory based on the predetermined factory configurations and dynamic inputs, where the dynamic inputs include a status of the equipment, a status of the plurality of mobile transporters, sensor data output by the plurality of sensors, or a combination thereof.Type: ApplicationFiled: September 28, 2022Publication date: June 22, 2023Applicant: Ford Global Technologies, LLCInventors: Kenneth Yesh, Anthony Mario D'Amato, Shankar Narayan Mohan, Mario Anthony Santillo, Gregory P. Linkowski, Meghna Menon
-
Publication number: 20230195119Abstract: A method includes identifying a set of intermediate grids of a grid map of the manufacturing environment based on a location of the first AMR and a destination grid of the grid map and appending temporal information to the set of intermediate grids based on a mobility characteristic of the first AMR. The method includes generating a first reservation based on the set of intermediate grids and the temporal information of the set of intermediate grids, determining a state of the first reservation based on priority information associated with the plurality of AMRs and one or more additional reservations associated with the one or more additional AMRs from among the plurality of AMRs, and assigning the first reservation to the first AMR in response to the first reservation being in an available state.Type: ApplicationFiled: December 22, 2021Publication date: June 22, 2023Applicant: Ford Global Technologies, LLCInventors: Geoffrey Horowitz, Gregory P. Linkowski, Meghna Menon, Sarah Garrow, Yifan Chen
-
Publication number: 20220358333Abstract: This disclosure describes systems, methods, and devices related to automatic annotation. A device may capture data associated with an image comprising an object. The device may acquire input data associated with the object. The device may estimate a plurality of points within a frame of the image, wherein the plurality of point constitute a 3D bounding to around the object. The device may transform the plurality of points to two or more 2D points. The device may construct a bounding box that encapsulates the object using the two or more 2D points. The device may create a segmentation mask of the object using morphological techniques. The device may perform annotation based on the segmentation mask.Type: ApplicationFiled: May 7, 2021Publication date: November 10, 2022Applicant: Ford Global Technologies, LLCInventors: Geoffrey Horowitz, Meghna Menon, Ling Zhu, Gregory P. Linkowski
-
Publication number: 20220339788Abstract: A method includes generating a workspace model having one or more digital robots, one or more digital sensors, and a digital transport system. The method includes simulating, for a task of the one or more digital robots, a sensor operation of the one or more digital sensors within the workspace model based on sensor characteristics of the one or more digital sensors. The method includes identifying, for the task of the one or more digital robots, an undetectable area within the workspace model based on the simulated sensor operation. The method includes selectively positioning, by a transport system, a set of sensors from among the one or more sensors based on the undetectable areas associated with the task.Type: ApplicationFiled: April 15, 2021Publication date: October 27, 2022Applicant: Ford Global Technologies, LLCInventors: Gregory P. Linkowski, Ling Zhu, Meghna Menon, Geoffrey Horowitz, Mario Anthony Santillo
-
Patent number: 11460862Abstract: A system and method for reconfiguring a factory having equipment at different workstations throughout the factory includes a plurality of mobile transporters configured to engage and transport the equipment to the different workstations throughout the factory. Each mobile transporter includes a transmitter, a receiver, at least one proximity sensor, and an engagement mechanism for engaging the equipment. A factory configuration module includes a 3D model of the factory and a plurality of predetermined factory configurations. A supervisory control module is in communication with the plurality of mobile transporters, the equipment, and the factory configuration module. The plurality of mobile transporters are configured to receive instructions from the supervisory control module to engage and reposition the equipment throughout the factory based on the predetermined factory configurations and dynamic inputs.Type: GrantFiled: February 3, 2020Date of Patent: October 4, 2022Assignee: Ford Global Technologies, LLCInventors: Kenneth Yesh, Anthony Mario D'Amato, Shankar Narayan Mohan, Mario Anthony Santillo, Gregory P. Linkowski, Meghna Menon
-
Publication number: 20220306092Abstract: A vehicle can be detected approaching a limited operation zone of a travel area. It can be determined that the vehicle is able to execute wireless commands from a computer. The object can be identified within the limited operation zone. Based on identifying the object within the limited operation zone, the vehicle can be controlled by providing a control command via wireless communications, the control command including whether the vehicle is permitted to enter the limited operation zone.Type: ApplicationFiled: March 24, 2021Publication date: September 29, 2022Applicant: Ford Global Technologies, LLCInventors: Gregory P. Linkowski, Mario A. Santillo
-
Patent number: 11403437Abstract: A method includes generating a workspace model having a robot based on at least one of an environment parameter and a regulated space. The workspace model is a digital model of a workspace. The method includes simulating a sensor operation of a sensor within the workspace model based on sensor characteristics of the sensor. The method includes identifying an undetectable area within the workspace model having the robot based on the simulated sensor operation. The method includes determining whether the undetectable area satisfies one or more detection metrics. The method includes performing a sensor placement control in response to the undetectable area not satisfying the one or more detection metrics to obtain a sensor placement scheme of the workspace. The sensor placement scheme identifies an undetectable area within the workspace when applicable.Type: GrantFiled: March 25, 2020Date of Patent: August 2, 2022Assignee: Ford Global Technologies, LLCInventors: Gregory P. Linkowski, Ling Zhu, Mario Anthony Santillo
-
Publication number: 20220212349Abstract: A method includes generating a workspace model having one or more robots and a plurality of image sensors, defining a plurality of pose scenarios of the one or more robots, and defining sensor characteristics of the plurality of image sensors. The method includes, for each of the plurality of pose scenarios, simulating a sensor operation of the plurality of image sensors within the workspace model based on the sensor characteristics and identifying an undetectable area within the workspace model based on the simulated sensor operation. The method includes performing a sensor placement control based on the undetectable areas associated with each of the plurality of pose scenarios.Type: ApplicationFiled: January 7, 2021Publication date: July 7, 2022Applicant: Ford Global Technologies, LLCInventors: Ling Zhu, Meghna Menon, Mario Anthony Santillo, Gregory P. Linkowski
-
Publication number: 20210303745Abstract: A method includes generating a workspace model having a robot based on at least one of an environment parameter and a regulated space. The workspace model is a digital model of a workspace. The method includes simulating a sensor operation of a sensor within the workspace model based on sensor characteristics of the sensor. The method includes identifying an undetectable area within the workspace model having the robot based on the simulated sensor operation. The method includes determining whether the undetectable area satisfies one or more detection metrics. The method includes performing a sensor placement control in response to the undetectable area not satisfying the one or more detection metrics to obtain a sensor placement scheme of the workspace. The sensor placement scheme identifies an undetectable area within the workspace when applicable.Type: ApplicationFiled: March 25, 2020Publication date: September 30, 2021Applicant: Ford Global Technologies, LLCInventors: Gregory P. Linkowski, Ling Zhu, Mario Anthony Santillo
-
Publication number: 20210240202Abstract: A system and method for reconfiguring a factory having equipment at different workstations throughout the factory includes a plurality of mobile transporters configured to engage and transport the equipment to the different workstations throughout the factory. Each mobile transporter includes a transmitter, a receiver, at least one proximity sensor, and an engagement mechanism for engaging the equipment. A factory configuration module includes a 3D model of the factory and a plurality of predetermined factory configurations. A supervisory control module is in communication with the plurality of mobile transporters, the equipment, and the factory configuration module. The plurality of mobile transporters are configured to receive instructions from the supervisory control module to engage and reposition the equipment throughout the factory based on the predetermined factory configurations and dynamic inputs.Type: ApplicationFiled: February 3, 2020Publication date: August 5, 2021Applicant: Ford Global Technologies, LLCInventors: Kenneth Yesh, Anthony Mario D'Amato, Shankar Narayan Mohan, Mario Anthony Santillo, Gregory P. Linkowski, Meghna Menon
-
Publication number: 20210146546Abstract: A method for a human-robot collaborative operation includes having a robot perform at least one automated task within a workspace and generating a dynamic model of a workspace based on a static nominal model of the workspace and data from a plurality of sensors disposed throughout the workspace. The method further includes controlling operation of the robot based on the dynamic model and the human operation, and verifying completion of the human operation based on a task completion parameter associated with the human operation and on based on at least one of the dynamic model, the data from the plurality of sensors, and the at least one automated task performed by the robot.Type: ApplicationFiled: November 19, 2019Publication date: May 20, 2021Applicant: Ford Global Technologies, LLCInventors: Gregory P. Linkowski, Shankar Narayan Mohan