专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2019241798A1 SELF-SUPERVISED ROBOTIC OBJECT INTERACTION 审中-公开
公开(公告)号：WO2019241798A1
公开(公告)日：2019-12-19
申请号：PCT/US2019/037548
申请日：2019-06-17
申请人： GOOGLE LLC
发明人： JANG, Eric Victor , LEVINE, Sergey Vladimir , DEVIN, Coline Manon
IPC分类号： B25J9/16
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an object representation neural network. One of the methods includes obtaining training sets of images, each training set comprising: (i) a before image of a before scene of the environment, (ii) an after image of an after scene of the environment after the robot has removed a particular object, and (iii) an object image of the particular object, and training the object representation neural network on the batch of training data, comprising determining an update to the object representation parameters that encourages the vector embedding of the particular object in each training set to be closer to a difference between (i) the vector embedding of the after scene in the training set and (ii) the vector embedding of the before scene in the training set.

2. 发明申请

WO2023278712A1 EFFICIENT HARDWARE ACCELERATOR CONFIGURATION EXPLORATION 审中-公开
公开(公告)号：WO2023278712A1
公开(公告)日：2023-01-05
申请号：PCT/US2022/035740
申请日：2022-06-30
申请人： GOOGLE LLC
发明人： YAZDANBAKHSH, Amir , LEVINE, Sergey Vladimir , KUMAR, Aviral
IPC分类号： G06N3/08 , G06N3/063 , G06N20/00 , G06F30/27 , G06F30/34 , G06N3/084 , G06N3/126 , G06N5/01
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a surrogate neural network configured to determine a predicted performance measure of a hardware accelerator having a target hardware configuration on a target application. The trained instance of the surrogate neural network can be used, in addition to or in place of hardware simulation, during a search process for determining hardware configurations for application-specific hardware accelerators, i.e., hardware accelerators on which one or more neural networks can be deployed to perform one or more target machine learning tasks.

3. 发明申请

WO2022251621A1 PIXEL-LEVEL VIDEO PREDICTION WITH IMPROVED PERFORMANCE AND EFFICIENCY 审中-公开
公开(公告)号：WO2022251621A1
公开(公告)日：2022-12-01
申请号：PCT/US2022/031326
申请日：2022-05-27
申请人： GOOGLE LLC
发明人： BABAEIZADEH, Mohammad , LEVINE, Sergey Vladimir , SAFFAR, Mohammad Taghi , NAIR, Suraj , FINN, Chelsea Breanna , ERHAN, Dumitru
IPC分类号： G06N3/04 , G06N3/08 , H04N19/42 , H04N19/503 , H04N19/59
摘要： One aspect provides a machine-learned video prediction model configured to receive and process one or more previous video frames to generate one or more predicted subsequent video frames, wherein the machine-learned video prediction model comprises a convolutional variational auto encoder, and wherein the convolutional variational auto encoder comprises an encoder portion comprising one or more encoding cells and a decoder portion comprising one or more decoding cells.

4. 发明申请

WO2019060626A1 USING SIMULATION AND DOMAIN ADAPTATION FOR ROBOTIC CONTROL 审中-公开
公开(公告)号：WO2019060626A1
公开(公告)日：2019-03-28
申请号：PCT/US2018/052069
申请日：2018-09-20
申请人： GOOGLE LLC
发明人： BOUSMALIS, Konstantinos , IRPAN, Alexander , WOHLHART, Paul , BAI, Yunfei , KALAKRISHNAN, Mrinal , IBARZ, Julian , LEVINE, Sergey Vladimir , KONOLIGE, Kurt , VANHOUCKE, Vincent O. , KELCEY, Matthew Laurance
IPC分类号： G06N3/00 , G06N3/04 , G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network that is used to control a robotic agent interacting with a real-world environment.

5. 发明申请

WO2018148574A1 AGENT NAVIGATION USING VISUAL INPUTS 审中-公开
公开(公告)号：WO2018148574A1
公开(公告)日：2018-08-16
申请号：PCT/US2018/017666
申请日：2018-02-09
申请人： GOOGLE LLC
发明人： SUKTHANKAR, Rahul , GUPTA, Saurabh , DAVIDSON, James Christopher , LEVINE, Sergey Vladimir , MALIK, Jitendra
IPC分类号： G06T7/00 , G05B13/02 , G06T1/40
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for navigation using visual inputs. One of the systems includes a mapping subsystem configured to, at each time step of a plurality of time steps, generate a characterization of an environment from an image of the environment at the time step, wherein the characterization comprises an environment map identifying locations in the environment having a particular characteristic, and wherein generating the characterization comprises, for each time step: obtaining the image of the environment at the time step, processing the image to generate a first initial characterization for the time step, obtaining a final characterization for a previous time step, processing the characterization for the previous time step to generate a second initial characterization for the time step, and combining the first initial characterization and the second initial characterization to generate a final characterization for the time step.

6. 发明申请

WO2018053246A1 CONTROL POLICIES FOR ROBOTIC AGENTS 审中-公开
标题翻译：机器人控制策略
公开(公告)号：WO2018053246A1
公开(公告)日：2018-03-22
申请号：PCT/US2017/051751
申请日：2017-09-15
申请人： GOOGLE LLC
发明人： FINN, Chelsea Breanna , LEVINE, Sergey Vladimir
IPC分类号： G06N3/04 , G06N3/00
摘要： A method includes: receiving data identifying, for each of one or more objects, a respective target location to which a robotic agent interacting with a real-world environment should move the object; causing the robotic agent to move the one or more objects to the one or more target locations by repeatedly performing the following: receiving a current image of a current state of the real-world environment; determining, from the current image, a next sequence of actions to be performed by the robotic agent using a next image prediction neural network that predicts future images based on a current action and an action to be performed by the robotic agent; and directing the robotic agent to perform the next sequence of actions.
摘要翻译：一种方法包括：接收为一个或多个对象中的每一个识别与真实世界环境交互的机器人代理应该移动该对象的相应目标位置的数据; 通过重复地执行以下操作使机器人代理将一个或多个对象移动到一个或多个目标位置：接收真实世界环境的当前状态的当前图像; 从当前图像确定要由机器人代理使用下一图像预测神经网络执行的下一个动作序列，该下一个图像预测神经网络基于当前动作和要由机器人代理执行的动作来预测未来图像; 并指示机器人代理执行下一个动作序列。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式