公开(公告)号：US20230162539A1

公开(公告)日：2023-05-25

申请号：US18145557

申请日：2022-12-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Dong LI ,  Bin WANG ,  Wulong LIU ,  Yuzheng ZHUANG

IPC: G07C5/02 ,  B60W50/06 ,  G06N7/01

CPC classification number: G07C5/02 ,  B60W50/06 ,  G06N7/01 ,  B60W2050/0018

Abstract: The present disclosure relates to driving decision-making methods, apparatuses, and chips. One example method includes building a Monte Carlo tree based on a current driving environment state, where the Monte Carlo tree includes a root node and N-1 non-root nodes, each node represents one driving environment state, and a driving environment state represented by any non-root node is predicted by a stochastic model of driving environments. Based on at least one of an access count or a value function of each node in the Monte Carlo tree, a node sequence that starts from the root node and ends at a leaf node is determined, and a driving action sequence is determined based on a driving action corresponding to each node in the node sequence.

公开(公告)号：US20190318245A1

公开(公告)日：2019-10-17

申请号：US16452290

申请日：2019-06-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Fenglong SONG ,  Wulong LIU ,  Xijun XUE ,  Huimin ZHANG

IPC: G06N3/08 ,  G06N3/063 ,  G06F9/50

Abstract: This application provides a method, a terminal-side device, and a cloud-side device for data processing and a terminal-cloud collaboration system. The method includes: sending, by the terminal-side device, a request message to the cloud-side device; receiving, by the terminal-side device, a second neural network model that is obtained by compressing a first neural network model and that is sent by the cloud-side device, where the first neural network model is a neural network model on the cloud-side device that is used to process the cognitive computing task, and a hardware resource required when the second neural network model runs on the terminal-side device is within an available hardware resource capability range of the terminal-side device; and processing, by the terminal-side device, the cognitive computing task based on the second neural network model.

公开(公告)号：US20220080972A1

公开(公告)日：2022-03-17

申请号：US17532640

申请日：2021-11-22

Applicant: Huawei Technologies Co., Ltd.

Inventor： Chen CHEN ,  Jun QIAN ,  Wulong LIU

IPC: B60W30/18 ,  B60W30/12 ,  B60W30/16 ,  B60W40/04 ,  B60W60/00 ,  G06V20/58

Abstract: An autonomous lane change method and apparatus, and a storage medium are provided. The method includes: calculating a local neighbor feature and a global statistical feature of an autonomous vehicle at a current moment based on travel information of the autonomous vehicle at the current moment and motion information of obstacles in lanes within a sensing range of the autonomous vehicle (S1101); obtaining a target action indication based on the local neighbor feature, the global statistical feature, and a current control policy (S1102); and executing the target action according to the target action indication (S1103). It can be learned that, on the basis of the local neighbor feature, the global statistical feature is further introduced into the current control policy to obtain the target action indication. Therefore, the target action obtained by combining local and global road obstacle information is a globally optimal decision action.

公开(公告)号：US20210174209A1

公开(公告)日：2021-06-10

申请号：US17181810

申请日：2021-02-22

Applicant: Huawei Technologies Co., Ltd. ,  Tsinghua University

Inventor： Yuzheng ZHUANG ,  Siyuan LI ,  Rui WANG ,  Wulong LIU ,  Chongjie ZHANG

IPC: G06N3/08 ,  G06N3/04 ,  G06F16/23

Abstract: A neural network obtaining method and a related device are provided. The method may be applied to a scenario in which reinforcement learning is performed on a neural network in the artificial intelligence field. After obtaining a first task, a server obtains a first success rate of completing the first task by using a first neural network. When the first success rate is less than a preset threshold, the server generates a second neural network and a new skill. The server trains, based on a simulated environment corresponding to the first task, the second neural network by using a reinforcement learning algorithm, until a second success rate of completing the first task by using the second neural network is greater than or equal to the preset threshold. The server stores the trained second neural network and the new skill.

公开(公告)号：US20220366266A1

公开(公告)日：2022-11-17

申请号：US17877063

申请日：2022-07-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hangyu MAO ,  Wulong LIU ,  Jianye HAO

IPC: G06N3/08 ,  H04L45/02 ,  G06F17/16

Abstract: An agent training method includes: obtaining environment information of a first agent and environment information of a second agent; generating first information based on the environment information of the first agent and the environment information of the second agent; and training the first agent by using the first information, so that the first agent outputs individual cognition information and neighborhood cognition information. The neighborhood cognition information of the first agent is consistent with neighborhood cognition information of the second agent.