Patents by Inventor Iman Soltani Bozchalooi
Iman Soltani Bozchalooi 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: 12165067Abstract: Systems and methods for anomaly detection in accordance with embodiments of the invention are illustrated. One embodiment includes a method for training a system for detecting anomalous samples. The method draws data samples from a data distribution of true samples and an anomaly distribution and draws a latent sample from a latent space. The method further includes steps for training a generator to generate data samples based on the drawn data samples and the latent sample, and training a cyclic discriminator to distinguish between true data samples and reconstructed samples. A reconstructed sample is generated by the generator based on an encoding of a data sample. The method identifies a set of one or more true pairs, a set of one or more anomalous pairs, and a set of one or more generated pairs. The method trains a joint discriminator to distinguish true pairs from anomalous and generated pairs.Type: GrantFiled: June 25, 2020Date of Patent: December 10, 2024Assignees: The Board of Trustees of the Leland Stanford Junior University, Ford Global Technologies, LLCInventors: Ziyi Yang, Eric Felix Darve, Iman Soltani Bozchalooi
-
Publication number: 20240237897Abstract: This disclosure provides a wearable device implemented as a headset such as a virtual reality (VR) headset comprising at least a screen, a gaze tracker, and either one or both the anterior segment or retinal optical coherence tomography and fundus imaging modalities. In some embodiments, the disclosed headset can display a movie on the screen to catch/hold the attention of a patient, and meanwhile capture ocular images of the patient using the ophthalmic imaging modalities in a fully-automated manner. While capturing ophthalmic images, the movie on the screen can cause the patient's gaze to move in various directions in a controllable manner. The gaze tracker can track the movements of the pupils of the patient. The tracked pupil positions can be used to reposition the ophthalmic imaging modalities to refocus and capture images of different regions of the fundus/retina, which allows a widefield-of-view image of the fundus/retina to be reconstructed.Type: ApplicationFiled: April 11, 2022Publication date: July 18, 2024Applicant: The Regents of the University of CaliforniaInventors: Iman Soltani Bozchalooi, Parisa Emami-Naeini
-
Publication number: 20240127568Abstract: This disclosure provides a precision-positioning/quality control system capable of measuring the exact position of any given mechanical component/part of any size or shape used during an assembly process. In one aspect, a process for performing high-accuracy localization and positioning of a rigid object is disclosed. This process can begin by receiving a full image of the object. The full image is then processed by a deep-learning module to identify a set of regions of interest on the object. Next, the identified regions in the set of regions of interest are subsequently processed to identify a number of surface points within each identified region and accurately estimate their positions. After sequentially processing all the regions of interest, the process subsequently generates an accurate position estimation for the object based on the combined set of identified high-precision surface points for the set of regions of interest.Type: ApplicationFiled: February 10, 2022Publication date: April 18, 2024Applicant: The Regents of the University of CaliforniaInventor: Iman Soltani Bozchalooi
-
Patent number: 11829131Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to train a neural network included in a memory augmented neural network based on one or more images and corresponding ground truth in a training dataset by transforming the one or more images to generate a plurality of one-hundred or more variations of the one or more images including variations in the ground truth and process the variations of the one or more images and store feature points corresponding to each variation of the one or more images in memory associated with the memory augmented neural network. The instructions can include further instructions to process an image acquired by a vehicle sensor with the memory augmented neural network, including comparing a feature variance set for the image acquired by the vehicle sensor to the stored processing parameters for each variation of the one or more images, to obtain an output result.Type: GrantFiled: October 29, 2020Date of Patent: November 28, 2023Assignee: Ford Global Technologies, LLCInventors: Iman Soltani Bozchalooi, Francois Charette, Dimitar Petrov Filev, Ryan Burke, Devesh Upadhyay
-
Patent number: 11423571Abstract: A method includes detecting, for each of a plurality of images, a plurality of key points, where each of the plurality of images represents an object of an assembly system. The method includes generating, for each of the plurality of images, a correspondence between the plurality of key points, and generating, for each of the plurality of images, a reference region based on the correspondence between the plurality of key points. The method includes identifying, for each of the plurality of images, a reference key point among the plurality of key points based on the reference region, and determining a pose of the object based on the reference key point of each of the plurality of images and a reference pose of the object.Type: GrantFiled: November 13, 2020Date of Patent: August 23, 2022Assignee: Ford Global Technologies, LLCInventors: Iman Soltani Bozchalooi, Alireza Rahimpour, Devesh Upadhyay
-
Publication number: 20220156970Abstract: A method includes detecting, for each of a plurality of images, a plurality of key points, where each of the plurality of images represents an object of an assembly system. The method includes generating, for each of the plurality of images, a correspondence between the plurality of key points, and generating, for each of the plurality of images, a reference region based on the correspondence between the plurality of key points. The method includes identifying, for each of the plurality of images, a reference key point among the plurality of key points based on the reference region, and determining a pose of the object based on the reference key point of each of the plurality of images and a reference pose of the object.Type: ApplicationFiled: November 13, 2020Publication date: May 19, 2022Applicant: Ford Global Technologies, LLCInventors: Iman Soltani Bozchalooi, Alireza Rahimpour, Devesh Upadhyay
-
Publication number: 20220137634Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to train a neural network included in a memory augmented neural network based on one or more images and corresponding ground truth in a training dataset by transforming the one or more images to generate a plurality of one-hundred or more variations of the one or more images including variations in the ground truth and process the variations of the one or more images and store feature points corresponding to each variation of the one or more images in memory associated with the memory augmented neural network. The instructions can include further instructions to process an image acquired by a vehicle sensor with the memory augmented neural network, including comparing a feature variance set for the image acquired by the vehicle sensor to the stored processing parameters for each variation of the one or more images, to obtain an output result.Type: ApplicationFiled: October 29, 2020Publication date: May 5, 2022Applicant: Ford Global Technologies, LLCInventors: Iman Soltani Bozchalooi, Francois Charette, Dimitar Petrov Filev, Ryan Burke, Devesh Upadhyay
-
Publication number: 20210397198Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive an image including a physical landmark, output a plurality of synthetic images, wherein each synthetic image is generated by simulating at least one ambient feature in the received image, generate respective feature vectors for each of the plurality of synthetic images, and actuate one or more vehicle components upon identifying the physical landmark in a second received image based on a similarity measure between the feature vectors of the synthetic images and a feature vector of the second received image, the similarity measure being one of a probability distribution difference or a statistical distance.Type: ApplicationFiled: June 18, 2020Publication date: December 23, 2021Applicant: Ford Global Technologies, LLCInventors: Iman Soltani Bozchalooi, Francois Charette, Praveen Narayanan, Ryan Burke, Devesh Upadhyay, Dimitar Petrov Filev
-
Patent number: 11126190Abstract: Example learning systems and methods are described. In one implementation, a machine learning system accesses data associated with a particular task and accesses data associated with an overall network. The machine learning system also accesses reward data. The machine learning system then operates on the data associated with a particular task, the data associated with an overall network, and the reward data to perform the particular task.Type: GrantFiled: February 13, 2019Date of Patent: September 21, 2021Assignee: FORD GLOBAL TECHNOLOGIES LLCInventor: Iman Soltani Bozchalooi
-
Patent number: 11069161Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine performance of a plurality of vehicle data sources used to operate a vehicle by evaluating each vehicle data source output data and train a deep neural network to determine reliability for each of the vehicle data sources based on the performance using reinforcement learning. The instructions can further include instructions to combine output data from the vehicle data sources based on the reliability including using the deep neural network to correlate output data from one or more vehicle data sources to the performance to determine how accurately the output data from each vehicle data source corresponds to vehicle performance and operate the vehicle based on combined output data.Type: GrantFiled: September 30, 2019Date of Patent: July 20, 2021Assignee: FORD GLOBAL TECHNOLOGIES, LLCInventors: Iman Soltani Bozchalooi, Francis Assadian, Lisa Scaria
-
Publication number: 20210097783Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine performance of a plurality of vehicle data sources used to operate a vehicle by evaluating each vehicle data source output data and train a deep neural network to determine reliability for each of the vehicle data sources based on the performance using reinforcement learning. The instructions can further include instructions to combine output data from the vehicle data sources based on the reliability including using the deep neural network to correlate output data from one or more vehicle data sources to the performance to determine how accurately the output data from each vehicle data source corresponds to vehicle performance and operate the vehicle based on combined output data.Type: ApplicationFiled: September 30, 2019Publication date: April 1, 2021Applicant: Ford Global Technologies, LLCInventors: Iman Soltani Bozchalooi, Francis Assadian, Lisa Scaria
-
Patent number: 10926416Abstract: An automation system includes a manipulation system including a manipulator for moving an object to a target location, a vision system for detecting landmarks on the object and the target location, and a learning and control module. The vision system is movable. The learning and control module is configured to control a movement of the manipulator and change a field of view of the vision system independent of the movement of the manipulator.Type: GrantFiled: November 21, 2018Date of Patent: February 23, 2021Assignee: Ford Global Technologies, LLCInventors: Iman Soltani Bozchalooi, Francis Assadian
-
Patent number: 10929714Abstract: A method of acquiring and processing visual data is provided, which includes: directing a light of a particular color to at least one of the plurality of landmarks on an object to illuminate the at least one of the plurality of landmarks; obtaining a first image of the object when the at least one of the plurality of landmarks on the object is illuminated; and extracting coordinates of the at least one of the plurality of landmarks from the first image.Type: GrantFiled: November 19, 2018Date of Patent: February 23, 2021Assignee: Ford Global Technologies, LLCInventors: Iman Soltani Bozchalooi, Francis Assadian
-
Publication number: 20200410285Abstract: Systems and methods for anomaly detection in accordance with embodiments of the invention are illustrated. One embodiment includes a method for training a system for detecting anomalous samples. The method draws data samples from a data distribution of true samples and an anomaly distribution and draws a latent sample from a latent space. The method further includes steps for training a generator to generate data samples based on the drawn data samples and the latent sample, and training a cyclic discriminator to distinguish between true data samples and reconstructed samples. A reconstructed sample is generated by the generator based on an encoding of a data sample. The method identifies a set of one or more true pairs, a set of one or more anomalous pairs, and a set of one or more generated pairs. The method trains a joint discriminator to distinguish true pairs from anomalous and generated pairs.Type: ApplicationFiled: June 25, 2020Publication date: December 31, 2020Applicants: The Board of Trustees of the Leland Stanford Junior University, Ford Global Technologies, LLCInventors: Ziyi Yang, Eric Felix Darve, Iman Soltani Bozchalooi
-
Publication number: 20200257302Abstract: Example learning systems and methods are described. In one implementation, a machine learning system accesses data associated with a particular task and accesses data associated with an overall network. The machine learning system also accesses reward data. The machine learning system then operates on the data associated with a particular task, the data associated with an overall network, and the reward data to perform the particular task.Type: ApplicationFiled: February 13, 2019Publication date: August 13, 2020Inventor: Iman Soltani Bozchalooi
-
Publication number: 20200160107Abstract: A method of acquiring and processing visual data is provided, which includes: directing a light of a particular color to at least one of the plurality of landmarks on an object to illuminate the at least one of the plurality of landmarks; obtaining a first image of the object when the at least one of the plurality of landmarks on the object is illuminated; and extracting coordinates of the at least one of the plurality of landmarks from the first imageType: ApplicationFiled: November 19, 2018Publication date: May 21, 2020Applicant: Ford Global Technologies, LLCInventors: Iman SOLTANI BOZCHALOOI, Francis ASSADIAN
-
Publication number: 20200156255Abstract: An automation system includes a manipulation system including a manipulator for moving an object to a target location, a vision system for detecting landmarks on the object and the target location, and a learning and control module. The vision system is movable. The learning and control module is configured to control a movement of the manipulator and change a field of view of the vision system independent of the movement of the manipulator.Type: ApplicationFiled: November 21, 2018Publication date: May 21, 2020Applicant: Ford Global Technologies, LLCInventors: Iman SOLTANI BOZCHALOOI, Francis ASSADIAN
-
Publication number: 20200156241Abstract: A control and learning module for controlling a robotic arm includes at least one learning module including at least one neural network. The at least one neural network is configured to receive and be trained by both state measurements based on measurements of current state and observation measurements based on observation data during an initial learning phase. The at least one learning module is further configured to be re-tuned by updated observation data for improved performance during an operations and secondary learning phase when the robotic arm is in normal operation and after the initial learning phase.Type: ApplicationFiled: November 21, 2018Publication date: May 21, 2020Applicant: Ford Global Technologies, LLCInventor: Iman SOLTANI BOZCHALOOI
-
Patent number: 10649072Abstract: A LiDAR device that transmits a single or multiple continuous or intermittent laser beams to the environment and detects the reflected light on one or more detectors. The LiDAR device may include a scanning mirrors array composed of a single or multiple moving mirrors capable of changing the direction of the transmitted light. The scanning mirrors array may also include sensors and actuators which can be used to precisely control or measure the position of the mirrors. The LiDAR device may also include a lens that focuses the light captured by the mirror(s) onto a single or a multitude of detectors. The device may include laser sources and detectors operating in various wavelengths. The LiDAR device may also include laser power modulation mechanisms at a single or multitude of frequencies to improve signal detection performance and remove any ambiguity in range calculation.Type: GrantFiled: May 10, 2017Date of Patent: May 12, 2020Assignee: Massachusetts Institute of TechnologyInventors: Iman Soltani Bozchalooi, Kamal Youcef-Toumi
-
Publication number: 20180329037Abstract: A LiDAR device that transmits a single or multiple continuous or intermittent laser beams to the environment and detects the reflected light on one or more detectors. The LiDAR device may include a scanning mirrors array composed of a single or multiple moving mirrors capable of changing the direction of the transmitted light. The scanning mirrors array may also include sensors and actuators which can be used to precisely control or measure the position of the mirrors. The LiDAR device may also include a lens that focuses the light captured by the mirror(s) onto a single or a multitude of detectors. The device may include laser sources and detectors operating in various wavelengths. The LiDAR device may also include laser power modulation mechanisms at a single or multitude of frequencies to improve signal detection performance and remove any ambiguity in range calculation.Type: ApplicationFiled: May 10, 2017Publication date: November 15, 2018Inventors: Iman Soltani Bozchalooi, Kamal Youcef-Toumi