公开(公告)号：US20230356728A1

公开(公告)日：2023-11-09

申请号：US18144651

申请日：2023-05-08

Applicant: NVIDIA Corporation

Inventor： Anshul Jain ,  Ratin Kumar ,  Feng Hu ,  Niranjan Avadhanam ,  Atousa Torabi ,  Hairong Jiang ,  Ram Ganapathi ,  Taek Kim

IPC: B60W30/18 ,  B60W50/00 ,  B60W40/08 ,  G06V40/19 ,  G05B13/02 ,  G05D1/00 ,  G06F18/25 ,  G06V10/141 ,  G06V20/59

CPC classification number: B60W50/0098 ,  B60W30/18 ,  B60W40/08 ,  G05B13/027 ,  G05D1/0061 ,  G06F18/251 ,  G06V10/141 ,  G06V20/597 ,  G06V40/19 ,  B60W2040/0836 ,  B60W2540/26 ,  H04N23/71

Abstract: Approaches for an advanced AI-assisted vehicle can utilize an extensive suite of sensors inside and outside the vehicle, providing information to a computing platform running one or more neural networks. The neural networks can perform functions such as facial recognition, eye tracking, gesture recognition, head position, and gaze tracking to monitor the condition and safety of the driver and passengers. The system also identifies and tracks body pose and signals of people inside and outside the vehicle to understand their intent and actions. The system can track driver gaze to identify objects the driver might not see, such as cross-traffic and approaching cyclists. The system can provide notification of potential hazards, advice, and warnings. The system can also take corrective action, which may include controlling one or more vehicle subsystems, or when necessary, autonomously controlling the entire vehicle. The system can work with vehicle systems for enhanced analytics and recommendations.

公开(公告)号：US11769495B2

公开(公告)日：2023-09-26

申请号：US18067217

申请日：2022-12-16

Applicant: NVIDIA Corporation

Inventor： Shubhadeep Das ,  Sumit Bhattacharya ,  Ratin Kumar

IPC: G10L15/22 ,  G10L15/18 ,  G10L13/02 ,  G10L15/30

CPC classification number: G10L15/1815 ,  G10L13/02 ,  G10L15/22 ,  G10L15/30

Abstract: In various examples, systems and methods of the present disclosure combine open and closed dialog systems into an intelligent dialog management system. A text query may be processed by a natural language understanding model trained to associate the text query with a domain tag, intent classification, and/or input slots. Using the domain tag, the natural language understanding model may identify information in the text query corresponding to input slots needed for answering the text query. The text query and related information may then be passed to a dialog manager to direct the text query to the proper domain dialog system. Responses retrieved from the domain dialog system may be provided to the user via text output and/or via a text to speech component of the dialog management system.

公开(公告)号：US10459873B2

公开(公告)日：2019-10-29

申请号：US13754256

申请日：2013-01-30

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters ,  Ratin Kumar ,  Lieven Leroy

IPC: G06F15/00 ,  G06F1/20 ,  G06F1/3215 ,  G06F1/3234

Abstract: The invention provides a method for adaptively adjusting a framerate of a graphic processing unit (GPU). For example, when the GPU workload is high and the temperature of the GPU is close to high temperature, the framerate can be decreased to reduce the workload; when the GPU workload is low, the framerate can be permitted to increase to raise the workload. By the present invention, the GPU is permitted to operate at maximum temperature. The method comprises the steps of: (a) receiving an execution parameter associated with at least one GPU; (b) comparing if the execution parameter is greater than a first reference value; and (c) in the event the execution parameter is greater than the first reference value, increasing a sleep time and power-gating the at least one GPU based on the sleep time to adjust the framerate.

公开(公告)号：US09870375B2

公开(公告)日：2018-01-16

申请号：US14137633

申请日：2013-12-20

Applicant: NVIDIA Corporation

Inventor： David Wyatt ,  Ratin Kumar ,  Timothy Bornemisza

IPC: G06F17/30 ,  G06T3/40 ,  H04N19/132 ,  H04N19/156 ,  H04N19/184 ,  H04N19/436

CPC classification number: G06F17/30247 ,  G06T3/40 ,  H04N19/132 ,  H04N19/156 ,  H04N19/184 ,  H04N19/436

Abstract: Various embodiments relating to reducing memory bandwidth consumed by a continuous scan display screen are provided. In one embodiment, scoring criteria are applied to a reference image of a first image format having a first bit depth to generate an image conversion score. The scoring criteria are based on a histogram of one or more characteristics of the reference image. If the image conversion score is greater than a threshold value, then the reference image is converted to a modified image of a second image format having a second bit depth less than the first bit depth, and the modified image is scanned onto the continuous scan display screen. If the image conversion score is less than the threshold value, then the reference image is scanned onto the continuous scan display screen.

公开(公告)号：US20240404296A1

公开(公告)日：2024-12-05

申请号：US18327643

申请日：2023-06-01

Applicant: NVIDIA Corporation

Inventor： Shagan Sah ,  Niranjan Avadhanam ,  Rajath Shetty ,  Ratin Kumar ,  Yile Chen

IPC: G06V20/58 ,  G06T7/20 ,  G06T7/50 ,  G06V10/764 ,  G06V20/59 ,  G08B13/196

Abstract: In various examples, low power proximity based threat detection using optical flow for vehicle systems and applications are provided. Some embodiments may use a tiered framework that uses sensor fusion techniques to detect and track the movement of a threat candidate, and perform a threat classification and/or intent prediction as the threat candidate approaches approach. Relative depth indications from optical flow, computed using data from image sensors, can be used to initially segment and track a moving object over a sequence of image frames. Additional sensors and processing may be brought online when a moving object becomes close enough to be considered a higher risk threat candidate. A threat response system may generate a risk score based on a predicted intent of a threat candidate, and when the risk score exceeds a certain threshold, then the threat response system may respond accordingly based on the threat classification and/or risk score.

公开(公告)号：US20230297074A1

公开(公告)日：2023-09-21

申请号：US17697566

申请日：2022-03-17

Applicant: Nvidia Corporation

Inventor： Christopher Jason Paxton ,  Shagan Sah ,  Ratin Kumar ,  Dieter Fox

IPC: G05B19/4155 ,  B25J13/00 ,  B25J9/16 ,  B25J13/08

CPC classification number: G05B19/4155 ,  B25J13/003 ,  B25J9/1661 ,  B25J13/08 ,  G05B2219/50391 ,  G05B2219/40269

Abstract: Approaches provide for performance of a complex (e.g., compound) task that may involve multiple discrete tasks not obvious from an instruction to perform the complex task. A set of conditions for an environment can be determined using captured image data, and the instruction analyzed to determine a set of final conditions to exist in the environment after performance of the instruction. These initial and end conditions are used to determine a sequence of discrete tasks to be performed to cause a robot or automated device to perform the instruction. This can involve use of a symbolic or visual planner in at least some embodiments, as well as a search of possible sequences of actions available for the robot or automated device. A robot can be caused to perform the sequence of discrete tasks, and feedback provided such that the sequence of tasks can be modified as appropriate.

公开(公告)号：US20220319503A1

公开(公告)日：2022-10-06

申请号：US17218751

申请日：2021-03-31

Applicant: NVIDIA Corporation

Inventor： Shubhadeep Das ,  Sumit Bhattacharya ,  Ratin Kumar

IPC: G10L15/18 ,  G10L13/02 ,  G10L15/22 ,  G10L15/30

Abstract: In various examples, systems and methods of the present disclosure combine open and closed dialog systems into an intelligent dialog management system. A text query may be processed by a natural language understanding model trained to associate the text query with a domain tag, intent classification, and/or input slots. Using the domain tag, the natural language understanding model may identify information in the text query corresponding to input slots needed for answering the text query. The text query and related information may then be passed to a dialog manager to direct the text query to the proper domain dialog system. Responses retrieved from the domain dialog system may be provided to the user via text output and/or via a text to speech component of the dialog management system.

公开(公告)号：US20210358188A1

公开(公告)日：2021-11-18

申请号：US17318871

申请日：2021-05-12

Applicant: NVIDIA Corporation

Inventor： Rev Lebaredian ,  Simon Yuen ,  Santanu Dutta ,  Jonathan Michael Cohen ,  Ratin Kumar

IPC: G06T13/00 ,  H04L12/58 ,  G10L13/08

Abstract: In various examples, a virtually animated and interactive agent may be rendered for visual and audible communication with one or more users with an application. For example, a conversational artificial intelligence (AI) assistant may be rendered and displayed for visual communication in addition to audible communication with end-users. As such, the AI assistant may leverage the visual domain—in addition to the audible domain—to more clearly communicate with users, including interacting with a virtual environment in which the AI assistant is rendered. Similarly, the AI assistant may leverage audio, video, and/or text inputs from a user to determine a request, mood, gesture, and/or posture of a user for more accurately responding to and interacting with the user.

公开(公告)号：US09582065B2

公开(公告)日：2017-02-28

申请号：US13975148

申请日：2013-08-23

Applicant: NVIDIA Corporation

Inventor： Ratin Kumar ,  Timothy Bornemisza

IPC: G06F1/32 ,  G09G5/36

CPC classification number: G06F1/3234 ,  G06F1/3218 ,  G06F1/3265 ,  G09G5/36 ,  G09G2320/103 ,  G09G2330/021 ,  G09G2340/0428 ,  G09G2350/00 ,  Y02D10/153

Abstract: Various embodiments relating to reducing memory bandwidth consumed by a continuous scan display screen are provided. In one embodiment, an indication of a static image period of a continuous scan display screen is determined. A reference image of a first image format having a first bit depth is converted into a modified image of a second image format having a second bit depth that is less than the first bit depth. During the static image period, the modified image is scanned onto the continuous scan display screen.

Abstract translation: 提供了与减少连续扫描显示屏幕消耗的存储器带宽有关的各种实施例。 在一个实施例中，确定连续扫描显示屏幕的静态图像周期的指示。 具有第一位深度的第一图像格式的参考图像被转换成具有小于第一位深度的第二位深度的第二图像格式的修改图像。 在静态图像期间，修改后的图像被扫描到连续扫描显示屏幕上。

公开(公告)号：US20140092103A1

公开(公告)日：2014-04-03

申请号：US13754256

申请日：2013-01-30

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters ,  Ratin Kumar ,  Lieven Leroy

IPC: G06F15/00

CPC classification number: G06F15/00 ,  G06F1/206 ,  G06F1/3215 ,  G06F1/325

Abstract: The invention provides a method for adaptively adjusting a framerate of a graphic processing unit (GPU). For example, when the GPU workload is high and the temperature of the GPU is close to high temperature, the framerate can be decreased to reduce the workload; when the GPU workload is low, the framerate can be permitted to increase to raise the workload. By the present invention, the GPU is permitted to operate at maximum temperature. The method comprises the steps of: (a) receiving an execution parameter associated with at least one GPU; (b) comparing if the execution parameter is greater than a first reference value; and (c) in the event the execution parameter is greater than the first reference value, increasing a sleep time and power-gating the at least one GPU based on the sleep time to adjust the framerate.

Abstract translation: 本发明提供一种用于自适应地调整图形处理单元（GPU）的帧率的方法。 例如，当GPU工作负载高并且GPU的温度接近高温时，可以减小帧率以减少工作量; 当GPU工作负载低时，可以允许帧率增加以提高工作负载。 通过本发明，允许GPU在最高温度下工作。 该方法包括以下步骤：（a）接收与至少一个GPU相关联的执行参数; （b）比较执行参数是否大于第一参考值; 以及（c）在所述执行参数大于所述第一参考值的情况下，基于所述睡眠时间增加睡眠时间并对所述至少一个GPU进行选通以调整所述帧率。