知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.016 seconds)

    Automatic navigation using deep reinforcement learning
    2.
    发明授权
    Automatic navigation using deep reinforcement learning 有权

    公开(公告)号：US11613249B2

    公开(公告)日：2023-03-28

    申请号：US15944563

    申请日：2018-04-03

    Applicant: Ford Global Technologies, LLC

    Inventor： Kaushik Balakrishnan ,  Praveen Narayanan ,  Mohsen Lakehal-ayat

    IPC: B60W30/06 ,  G05D1/02 ,  G05D1/00

    Abstract: A method for training an autonomous vehicle to reach a target location. The method includes detecting the state of an autonomous vehicle in a simulated environment, and using a neural network to navigate the vehicle from an initial location to a target destination. During the training phase, a second neural network may reward the first neural network for a desired action taken by the autonomous vehicle, and may penalize the first neural network for an undesired action taken by the autonomous vehicle. A corresponding system and computer program product are also disclosed and claimed herein.

    JOINT AUTOMATIC SPEECH RECOGNITION AND TEXT TO SPEECH CONVERSION USING ADVERSARIAL NEURAL NETWORKS
    3.
    发明申请
    JOINT AUTOMATIC SPEECH RECOGNITION AND TEXT TO SPEECH CONVERSION USING ADVERSARIAL NEURAL NETWORKS 有权

    公开(公告)号：US20220005457A1

    公开(公告)日：2022-01-06

    申请号：US16919315

    申请日：2020-07-02

    Applicant: Ford Global Technologies, LLC

    Inventor： Kaushik Balakrishnan ,  Praveen Narayanan ,  Francois Charette

    IPC: G10L13/047 ,  G10L15/16

    Abstract: An end-to-end deep-learning-based system that can solve both ASR and TTS problems jointly using unpaired text and audio samples is disclosed herein. An adversarially-trained approach is used to generate a more robust independent TTS neural network and an ASR neural network that can be deployed individually or simultaneously. The process for training the neural networks includes generating an audio sample from a text sample using the TTS neural network, then feeding the generated audio sample into the ASR neural network to regenerate the text. The difference between the regenerated text and the original text is used as a first loss for training the neural networks. A similar process is used for an audio sample. The difference between the regenerated audio and the original audio is used as a second loss. Text and audio discriminators are similarly used on the output of the neural network to generate additional losses for training.

    VIsion-Based Robot Navigation By Coupling Deep Reinforcement Learning And A Path Planning Algorithm
    4.
    发明申请
    VIsion-Based Robot Navigation By Coupling Deep Reinforcement Learning And A Path Planning Algorithm 有权

    公开(公告)号：US20220214692A1

    公开(公告)日：2022-07-07

    申请号：US17141433

    申请日：2021-01-05

    Applicant: Ford Global Technologies, LLC

    Inventor： Punarjay Chakravarty ,  Kaushik Balakrishnan ,  Shubham Shrivastava

    IPC: G05D1/02 ,  B25J9/16

    Abstract: Present embodiments use deep reinforcement learning (DRL) algorithms and use one or more path planning approaches to create a path using a deep learning approach using a reinforcement learning algorithm, trained using traditional learning algorithms such as A-Star. The reinforcement learning algorithm takes in a forward-facing camera operative as part of a computer vision system for a robot, and utilizes training the algorithm to train the robot to traverse from point A to point B in an operating environment using a sequence of waypoints as a breadcrumb trail. The system trains the robot to learn the path section by section by the waypoints, which prevents requiring the robot to solve the entire path. At test/deploy time, A-star is not used, and the robot navigates the entire start to goal path without any intermediate waypoints

    Joint automatic speech recognition and text to speech conversion using adversarial neural networks
    7.
    发明授权
    Joint automatic speech recognition and text to speech conversion using adversarial neural networks 有权

    公开(公告)号：US11574622B2

    公开(公告)日：2023-02-07

    申请号：US16919315

    申请日：2020-07-02

    Applicant: Ford Global Technologies, LLC

    Inventor： Kaushik Balakrishnan ,  Praveen Narayanan ,  Francois Charette

    IPC: G10L15/16 ,  G10L13/047

    Abstract: An end-to-end deep-learning-based system that can solve both ASR and TTS problems jointly using unpaired text and audio samples is disclosed herein. An adversarially-trained approach is used to generate a more robust independent TTS neural network and an ASR neural network that can be deployed individually or simultaneously. The process for training the neural networks includes generating an audio sample from a text sample using the TTS neural network, then feeding the generated audio sample into the ASR neural network to regenerate the text. The difference between the regenerated text and the original text is used as a first loss for training the neural networks. A similar process is used for an audio sample. The difference between the regenerated audio and the original audio is used as a second loss. Text and audio discriminators are similarly used on the output of the neural network to generate additional losses for training.

    MODEL-BASED REINFORCEMENT LEARNING
    9.
    发明公开
    MODEL-BASED REINFORCEMENT LEARNING 审中-公开

    公开(公告)号：US20240320505A1

    公开(公告)日：2024-09-26

    申请号：US18188024

    申请日：2023-03-22

    Applicant: Ford Global Technologies, LLC

    Inventor： Kaushik Balakrishnan ,  Neeloy Chakraborty ,  Devesh Upadhyay

    IPC: G06N3/092

    CPC classification number: G06N3/092

    Abstract: A computer that includes a processor and a memory, the memory including instructions executable by the processor to train an agent neural network to input a first state and output a first action, input the first action to an environment and determine a second state and a reward. Koopman model neural network can be trained based on the first state, the first action and the second state to determine a fake state. The agent neural network can be re-trained and the Koopman model neural network can be re-trained based on reinforcement learning including the first state, the first action, the second state, the fake state, and the reward.

Patent Agency Ranking