Patents by Inventor Neda Cvijetic
Neda Cvijetic 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: 12248319Abstract: In various examples, systems and methods are disclosed that preserve rich spatial information from an input resolution of a machine learning model to regress on lines in an input image. The machine learning model may be trained to predict, in deployment, distances for each pixel of the input image at an input resolution to a line pixel determined to correspond to a line in the input image. The machine learning model may further be trained to predict angles and label classes of the line. An embedding algorithm may be used to train the machine learning model to predict clusters of line pixels that each correspond to a respective line in the input image. In deployment, the predictions of the machine learning model may be used as an aid for understanding the surrounding environment—e.g., for updating a world model—in a variety of autonomous machine applications.Type: GrantFiled: June 23, 2023Date of Patent: March 11, 2025Assignee: NVIDIA CorporationInventors: Minwoo Park, Xiaolin Lin, Hae-Jong Seo, David Nister, Neda Cvijetic
-
Publication number: 20240339035Abstract: In various examples, a path perception ensemble is used to produce a more accurate and reliable understanding of a driving surface and/or a path there through. For example, an analysis of a plurality of path perception inputs provides testability and reliability for accurate and redundant lane mapping and/or path planning in real-time or near real-time. By incorporating a plurality of separate path perception computations, a means of metricizing path perception correctness, quality, and reliability is provided by analyzing whether and how much the individual path perception signals agree or disagree. By implementing this approach—where individual path perception inputs fail in almost independent ways—a system failure is less statistically likely. In addition, with diversity and redundancy in path perception, comfortable lane keeping on high curvature roads, under severe road conditions, and/or at complex intersections, as well as autonomous negotiation of turns at intersections, may be enabled.Type: ApplicationFiled: June 17, 2024Publication date: October 10, 2024Inventors: Davide Marco Onofrio, Hae-Jong Seo, David Nister, Minwoo Park, Neda Cvijetic
-
Patent number: 12051332Abstract: In various examples, a path perception ensemble is used to produce a more accurate and reliable understanding of a driving surface and/or a path there through. For example, an analysis of a plurality of path perception inputs provides testability and reliability for accurate and redundant lane mapping and/or path planning in real-time or near real-time. By incorporating a plurality of separate path perception computations, a means of metricizing path perception correctness, quality, and reliability is provided by analyzing whether and how much the individual path perception signals agree or disagree. By implementing this approach—where individual path perception inputs fail in almost independent ways—a system failure is less statistically likely. In addition, with diversity and redundancy in path perception, comfortable lane keeping on high curvature roads, under severe road conditions, and/or at complex intersections.Type: GrantFiled: September 8, 2022Date of Patent: July 30, 2024Assignee: NVIDIA CorporationInventors: Davide Marco Onofrio, Hae-Jong Seo, David Nister, Minwoo Park, Neda Cvijetic
-
Publication number: 20240230339Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to generate potential paths for the vehicle to navigate an intersection in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as heat maps corresponding to key points associated with the intersection, vector fields corresponding to directionality, heading, and offsets with respect to lanes, intensity maps corresponding to widths of lanes, and/or classifications corresponding to line segments of the intersection. The outputs may be decoded and/or otherwise post-processed to reconstruct an intersection—or key points corresponding thereto—and to determine proposed or potential paths for navigating the vehicle through the intersection.Type: ApplicationFiled: March 25, 2024Publication date: July 11, 2024Inventors: Trung Pham, Hang Dou, Berta Rodriguez Hervas, Minwoo Park, Neda Cvijetic, David Nister
-
Patent number: 12013244Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to generate potential paths for the vehicle to navigate an intersection in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as heat maps corresponding to key points associated with the intersection, vector fields corresponding to directionality, heading, and offsets with respect to lanes, intensity maps corresponding to widths of lanes, and/or classifications corresponding to line segments of the intersection. The outputs may be decoded and/or otherwise post-processed to reconstruct an intersection—or key points corresponding thereto—and to determine proposed or potential paths for navigating the vehicle through the intersection.Type: GrantFiled: April 14, 2020Date of Patent: June 18, 2024Assignee: NVIDIA CorporationInventors: Trung Pham, Hang Dou, Berta Rodriguez Hervas, Minwoo Park, Neda Cvijetic, David Nister
-
Publication number: 20240127454Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersection contention areas in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as signed distance functions—that may correspond to locations of boundaries delineating intersection contention areas. The signed distance functions may be decoded and/or post-processed to determine instance segmentation masks representing locations and classifications of intersection areas or regions. The locations of the intersections areas or regions may be generated in image-space and converted to world-space coordinates to aid an autonomous or semi-autonomous vehicle in navigating intersections according to rules of the road, traffic priority considerations, and/or the like.Type: ApplicationFiled: December 20, 2023Publication date: April 18, 2024Inventors: Trung Pham, Berta Rodriguez Hervas, Minwoo Park, David Nister, Neda Cvijetic
-
Publication number: 20240116538Abstract: In various examples, sensor data may be collected using one or more sensors of an ego-vehicle to generate a representation of an environment surrounding the ego-vehicle. The representation may include lanes of the roadway and object locations within the lanes. The representation of the environment may be provided as input to a longitudinal speed profile identifier, which may project a plurality of longitudinal speed profile candidates onto a target lane. Each of the plurality of longitudinal speed profiles candidates may be evaluated one or more times based on one or more sets of criteria. Using scores from the evaluation, a target gap and a particular longitudinal speed profile from the longitudinal speed profile candidates may be selected. Once the longitudinal speed profile for a target gap has been determined, the system may execute a lane change maneuver according to the longitudinal speed profile.Type: ApplicationFiled: December 19, 2023Publication date: April 11, 2024Inventors: Zhenyi Zhang, Yizhou Wang, David Nister, Neda Cvijetic
-
Publication number: 20240111025Abstract: In various examples, a deep neural network (DNN) may be used to detect and classify animate objects and/or parts of an environment. The DNN may be trained using camera-to-LiDAR cross injection to generate reliable ground truth data for LiDAR range images. For example, annotations generated in the image domain may be propagated to the LiDAR domain to increase the accuracy of the ground truth data in the LiDAR domain—e.g., without requiring manual annotation in the LiDAR domain. Once trained, the DNN may output instance segmentation masks, class segmentation masks, and/or bounding shape proposals corresponding to two-dimensional (2D) LiDAR range images, and the outputs may be fused together to project the outputs into three-dimensional (3D) LiDAR point clouds. This 2D and/or 3D information output by the DNN may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.Type: ApplicationFiled: December 6, 2023Publication date: April 4, 2024Inventors: Tilman Wekel, Sangmin Oh, David Nister, Joachim Pehserl, Neda Cvijetic, Ibrahim Eden
-
Publication number: 20240101118Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersections in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as bounding box coordinates for intersections, intersection coverage maps corresponding to the bounding boxes, intersection attributes, distances to intersections, and/or distance coverage maps associated with the intersections. The outputs may be decoded and/or post-processed to determine final locations of, distances to, and/or attributes of the detected intersections.Type: ApplicationFiled: December 12, 2023Publication date: March 28, 2024Inventors: Sayed Mehdi Sajjadi Mohammadabadi, Berta Rodriguez Hervas, Hang Dou, Igor Tryndin, David Nister, Minwoo Park, Neda Cvijetic, Junghyun Kwon, Trung Pham
-
Patent number: 11928822Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersection contention areas in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as signed distance functions—that may correspond to locations of boundaries delineating intersection contention areas. The signed distance functions may be decoded and/or post-processed to determine instance segmentation masks representing locations and classifications of intersection areas or regions. The locations of the intersections areas or regions may be generated in image-space and converted to world-space coordinates to aid an autonomous or semi-autonomous vehicle in navigating intersections according to rules of the road, traffic priority considerations, and/or the like.Type: GrantFiled: July 13, 2022Date of Patent: March 12, 2024Assignee: NVIDIA CorporationInventors: Trung Pham, Berta Rodriguez Hervas, Minwoo Park, David Nister, Neda Cvijetic
-
Patent number: 11921502Abstract: In various examples, systems and methods are disclosed that preserve rich spatial information from an input resolution of a machine learning model to regress on lines in an input image. The machine learning model may be trained to predict, in deployment, distances for each pixel of the input image at an input resolution to a line pixel determined to correspond to a line in the input image. The machine learning model may further be trained to predict angles and label classes of the line. An embedding algorithm may be used to train the machine learning model to predict clusters of line pixels that each correspond to a respective line in the input image. In deployment, the predictions of the machine learning model may be used as an aid for understanding the surrounding environment—e.g., for updating a world model—in a variety of autonomous machine applications.Type: GrantFiled: January 6, 2023Date of Patent: March 5, 2024Assignee: NVIDIA CorporationInventors: Minwoo Park, Xiaolin Lin, Hae-Jong Seo, David Nister, Neda Cvijetic
-
Patent number: 11906660Abstract: In various examples, a deep neural network (DNN) may be used to detect and classify animate objects and/or parts of an environment. The DNN may be trained using camera-to-LiDAR cross injection to generate reliable ground truth data for LiDAR range images. For example, annotations generated in the image domain may be propagated to the LiDAR domain to increase the accuracy of the ground truth data in the LiDAR domain—e.g., without requiring manual annotation in the LiDAR domain. Once trained, the DNN may output instance segmentation masks, class segmentation masks, and/or bounding shape proposals corresponding to two-dimensional (2D) LiDAR range images, and the outputs may be fused together to project the outputs into three-dimensional (3D) LiDAR point clouds. This 2D and/or 3D information output by the DNN may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.Type: GrantFiled: August 28, 2020Date of Patent: February 20, 2024Assignee: NVIDIA CorporationInventors: Tilman Wekel, Sangmin Oh, David Nister, Joachim Pehserl, Neda Cvijetic, Ibrahim Eden
-
Patent number: 11897471Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersections in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as bounding box coordinates for intersections, intersection coverage maps corresponding to the bounding boxes, intersection attributes, distances to intersections, and/or distance coverage maps associated with the intersections. The outputs may be decoded and/or post-processed to determine final locations of, distances to, and/or attributes of the detected intersections.Type: GrantFiled: January 31, 2023Date of Patent: February 13, 2024Assignee: NVIDIA CorporationInventors: Sayed Mehdi Sajjadi Mohammadabadi, Berta Rodriguez Hervas, Hang Dou, Igor Tryndin, David Nister, Minwoo Park, Neda Cvijetic, Junghyun Kwon, Trung Pham
-
Patent number: 11884294Abstract: In various examples, sensor data may be collected using one or more sensors of an ego-vehicle to generate a representation of an environment surrounding the ego-vehicle. The representation may include lanes of the roadway and object locations within the lanes. The representation of the environment may be provided as input to a longitudinal speed profile identifier, which may project a plurality of longitudinal speed profile candidates onto a target lane. Each of the plurality of longitudinal speed profiles candidates may be evaluated one or more times based on one or more sets of criteria. Using scores from the evaluation, a target gap and a particular longitudinal speed profile from the longitudinal speed profile candidates may be selected. Once the longitudinal speed profile for a target gap has been determined, the system may execute a lane change maneuver according to the longitudinal speed profile.Type: GrantFiled: December 22, 2020Date of Patent: January 30, 2024Assignee: NVIDIA CorporationInventors: Zhenyi Zhang, Yizhou Wang, David Nister, Neda Cvijetic
-
Publication number: 20230357076Abstract: An end-to-end system for data generation, map creation using the generated data, and localization to the created map is disclosed. Mapstreams—or streams of sensor data, perception outputs from deep neural networks (DNNs), and/or relative trajectory data—corresponding to any number of drives by any number of vehicles may be generated and uploaded to the cloud. The mapstreams may be used to generate map data—and ultimately a fused high definition (HD) map—that represents data generated over a plurality of drives. When localizing to the fused HD map, individual localization results may be generated based on comparisons of real-time data from a sensor modality to map data corresponding to the same sensor modality. This process may be repeated for any number of sensor modalities and the results may be fused together to determine a final fused localization result.Type: ApplicationFiled: May 2, 2023Publication date: November 9, 2023Inventors: Michael Kroepfl, Amir Akbarzadeh, Ruchi Bhargava, Viabhav Thukral, Neda Cvijetic, Vadim Cugunovs, David Nister, Birgit Henke, Ibrahim Eden, Youding Zhu, Michael Grabner, Ivana Stojanovic, Yu Sheng, Jeffrey Liu, Enliang Zheng, Jordan Marr, Andrew Carley
-
Publication number: 20230333553Abstract: In various examples, systems and methods are disclosed that preserve rich spatial information from an input resolution of a machine learning model to regress on lines in an input image. The machine learning model may be trained to predict, in deployment, distances for each pixel of the input image at an input resolution to a line pixel determined to correspond to a line in the input image. The machine learning model may further be trained to predict angles and label classes of the line. An embedding algorithm may be used to train the machine learning model to predict clusters of line pixels that each correspond to a respective line in the input image. In deployment, the predictions of the machine learning model may be used as an aid for understanding the surrounding environment—e.g., for updating a world model—in a variety of autonomous machine applications.Type: ApplicationFiled: June 23, 2023Publication date: October 19, 2023Inventors: Minwoo Park, Xiaoin Lin, Hae-Jong Seo, David Nister, Neda Cvijetic
-
Patent number: 11698272Abstract: An end-to-end system for data generation, map creation using the generated data, and localization to the created map is disclosed. Mapstreams—or streams of sensor data, perception outputs from deep neural networks (DNNs), and/or relative trajectory data—corresponding to any number of drives by any number of vehicles may be generated and uploaded to the cloud. The mapstreams may be used to generate map data—and ultimately a fused high definition (HD) map—that represents data generated over a plurality of drives. When localizing to the fused HD map, individual localization results may be generated based on comparisons of real-time data from a sensor modality to map data corresponding to the same sensor modality. This process may be repeated for any number of sensor modalities and the results may be fused together to determine a final fused localization result.Type: GrantFiled: August 31, 2020Date of Patent: July 11, 2023Assignee: NVIDIA CorporationInventors: Michael Kroepfl, Amir Akbarzadeh, Ruchi Bhargava, Vaibhav Thukral, Neda Cvijetic, Vadim Cugunovs, David Nister, Birgit Henke, Ibrahim Eden, Youding Zhu, Michael Grabner, Ivana Stojanovic, Yu Sheng, Jeffrey Liu, Enliang Zheng, Jordan Marr, Andrew Carley
-
Publication number: 20230166733Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersections in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as bounding box coordinates for intersections, intersection coverage maps corresponding to the bounding boxes, intersection attributes, distances to intersections, and/or distance coverage maps associated with the intersections. The outputs may be decoded and/or post-processed to determine final locations of, distances to, and/or attributes of the detected intersections.Type: ApplicationFiled: January 31, 2023Publication date: June 1, 2023Inventors: Sayed Mehdi Sajjadi Mohammadabadi, Berta Rodriguez Hervas, Hang Dou, Igor Tryndin, David Nister, Minwoo Park, Neda Cvijetic, Junghyun Kwon, Trung Pham
-
Publication number: 20230152801Abstract: In various examples, systems and methods are disclosed that preserve rich spatial information from an input resolution of a machine learning model to regress on lines in an input image. The machine learning model may be trained to predict, in deployment, distances for each pixel of the input image at an input resolution to a line pixel determined to correspond to a line in the input image. The machine learning model may further be trained to predict angles and label classes of the line. An embedding algorithm may be used to train the machine learning model to predict clusters of line pixels that each correspond to a respective line in the input image. In deployment, the predictions of the machine learning model may be used as an aid for understanding the surrounding environment - e.g., for updating a world model - in a variety of autonomous machine applications.Type: ApplicationFiled: January 6, 2023Publication date: May 18, 2023Inventors: Minwoo Park, Xiaolin Lin, Hae-Jong Seo, David Nister, Neda Cvijetic
-
Patent number: 11648945Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersections in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as bounding box coordinates for intersections, intersection coverage maps corresponding to the bounding boxes, intersection attributes, distances to intersections, and/or distance coverage maps associated with the intersections. The outputs may be decoded and/or post-processed to determine final locations of, distances to, and/or attributes of the detected intersections.Type: GrantFiled: March 10, 2020Date of Patent: May 16, 2023Assignee: NVIDIA CorporationInventors: Sayed Mehdi Sajjadi Mohammadabadi, Berta Rodriguez Hervas, Hang Dou, Igor Tryndin, David Nister, Minwoo Park, Neda Cvijetic, Junghyun Kwon, Trung Pham