Title:
METHOD OF SELECTION OF AN ACTION FOR AN OBJECT USING A NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2019/068236
Kind Code:
A1
Abstract:
A method, device and system of prediction of a state of an object in the environment using an action model of a neural network. In accordance with one aspect, a control system (115) for an object comprises a processor (102), a plurality of sensors (110) coupled to the processor (102) for sensing a current state of the object and an environment in which the object is located, and a first neural network (250) coupled to the processor (102). A plurality of predicted subsequent states of the object in the environment is obtained using an action model, a current state of the object in the environment and a plurality of actions. The action model maps a plurality of states of the object in the environment and a plurality of actions performed by the object for each state to predicted subsequent states of the object in the environment. An action that maximizes a value of a target is determined. The target is based at least on a reward for each of the predicted subsequent states. The determined action is performed.
Inventors:
YAO HENGSHUAI (CA)
CHEN HAO (CA)
NOSRATI SEYED MASOUD (CA)
YADMELLAT PEYMAN (CA)
ZHANG YUNFEI (CA)
CHEN HAO (CA)
NOSRATI SEYED MASOUD (CA)
YADMELLAT PEYMAN (CA)
ZHANG YUNFEI (CA)
Application Number:
PCT/CN2017/109552
Publication Date:
April 11, 2019
Filing Date:
November 06, 2017
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
B60W40/12; G06N3/02
Foreign References:
CN106080590A | 2016-11-09 | |||
US6493614B1 | 2002-12-10 | |||
CN103605285A | 2014-02-26 | |||
CN102289714A | 2011-12-21 | |||
CN106394555A | 2017-02-15 |
Download PDF: