-
公开(公告)号：US20230314147A1
公开(公告)日：2023-10-05
申请号：US18021532
申请日：2020-09-29
Applicant: NEC Corporation
Inventor： Aayush AGGARWAL , Ryota HIGA , HIroaki INOTSUME
IPC: G01C21/34
CPC classification number: G01C21/3446
Abstract: An object of the present disclosure is to provide a path generation method that can generate a set of paths from any start nodes to any goal nodes with the distribution given by the user. A path generator (06) includes a path finder (13) generates a plurality paths based on a plurality of weights between nodes, the nodes being included in a map, a weight generator (12) generates the plurality of weights defined between the nodes based on a predetermined distribution.
-
公开(公告)号：US20230030599A1
公开(公告)日：2023-02-02
申请号：US17791066
申请日：2020-01-20
Applicant: NEC Corporation
Inventor： Ryota HIGA
Abstract: An input unit 81 receives an input of information on a container to be loaded, loading status of a freight car, and a container arrival prediction. A loading position determination unit 82 determines a loading position of the container to be loaded on a freight car based on a policy function, which is trained based on a past loading result or a loading plan, that calculates a selection probability of the loading position of the container assumed for the loading status of the freight car and a value function that calculates a value for the loading status of the freight car. And the loading position determination unit 82 determines the loading position of the container based on the value function calculated based on the container arrival prediction and the policy function.
-
Patent Agency Ranking
公开(公告)号：US20210042584A1
公开(公告)日：2021-02-11
申请号：US16965823
申请日：2018-01-30
Applicant: NEC CORPORATION
Inventor： Ryota HIGA , Itaru NISHIOKA
Abstract: An information processing device (2000) includes an acquisition unit (2020) and a learning unit (2040). The acquisition unit (2020) acquires one or more pieces of action data. The action data are data each piece of which associates a state vector representing a state of an environment with an action that is performed in a state represented by the state vector. The learning unit (2040) generates a policy function P and a reward function r through imitation learning using the acquired action data. The reward function r outputs, when given a state vector S as input, a reward r(S) that is acquired in a state represented by the state vector S. The policy function accepts, as input, an output r(S) of the reward function upon input of a state vector S and outputs an action a=P(r(S)) to be performed in a state represented by the state vector S.
-
14.发明申请公开(公告)号：US20250053179A1
公开(公告)日：2025-02-13
申请号：US18720936
申请日：2022-12-13
Inventor： Ryota HIGA , Shinji NAKADAI , Ken HITSU
Abstract: A pathfinding apparatus acquires vehicle information, map information, obstacle information. The vehicle information includes a current location and a goal location for multiple vehicles. The map information includes a map of a target space. The obstacle information includes history of locations of one or more moving obstacles. The pathfinding apparatus generates one or more obstacle path for each moving obstacle during a target time window, and generates multiple candidate path sets each of which includes a vehicle path during the target time window for each vehicle. The vehicle path is conflict-free with the other vehicle paths and the obstacle paths. The pathfinding apparatus evaluates the candidate path sets through a heuristic search of continuations of the vehicles paths in the candidate path sets, selects one of the candidate path sets based their evaluations, and outputs the selected candidate path set.
-
15.发明申请公开(公告)号：US20220318029A1
公开(公告)日：2022-10-06
申请号：US17425832
申请日：2019-02-01
Applicant: NEC Corporation
Inventor： Ryota HIGA , Junya KATO
Abstract: An operation support apparatus (100) includes a storage unit (110) configured to store time-series data (111) obtained by measuring states of a target system controlled according to a plurality of operations performed by an operator, and operation information (112), the operation information (112) being a set of at least one of the plurality of operations and a time, a specification unit (120) configured to specify a plurality of change points in a change trend of the states from the time-series data (111), and specify each of a plurality of time windows as one of a plurality of operating modes in the target system, the plurality of time windows being separated at at least one of the plurality of change points, and an operation-set generation unit (130) configured to extract, for each of the plurality of time windows, a set of operations performed at a time included in that time window from the operation information (112), generate an operating-mode operation set (113) in which the operating modes corresponding to the respective time windows are associated with the extracted set of operations, and stores the generated operating-mode operation set (113) in the storage unit (110).
-
公开(公告)号：US20220036122A1
公开(公告)日：2022-02-03
申请号：US17278701
申请日：2018-09-27
Applicant: NEC Corporation
Inventor： Ryota HIGA
Abstract: An object of the present disclosure is to utilize a model adapted to a predetermined system and efficiently adapt the model to another system with an environment or an agent similar to those of the predetermined system. An information processing apparatus (1) according to the present disclosure includes a generation unit (11) configured to correct a first model adapted to a first system operated based on a first condition including a specific environment and a specific agent using a correction model to thereby generate a second model, and an adaptation unit (12) configured to adapt the second model to a second system operated based on a second condition, the second condition being partially different from the first condition.
-
公开(公告)号：US20210201138A1
公开(公告)日：2021-07-01
申请号：US17057394
申请日：2018-05-25
Applicant: NEC Corporation
Inventor： Ryota HIGA
Abstract: A model setting unit 81 sets, as a problem setting to be targeted in reinforcement learning, a model in which a policy for determining an action to be taken in an environmental state is associated with a Boltzmann distribution representing a probability distribution of a prescribed state, and a reward function for determining a reward obtainable from an environmental state and an action selected in the state is associated with a physical equation representing a physical quantity corresponding to an energy. A parameter estimation unit 82 estimates parameters of the physical equation by performing the reinforcement learning using learning data including the state based on the set model.
-
-
-
-
-
-
Search Results
17
records
(took 0.015 seconds)
