Method for real-time position estimate correction of a movable object

    公开(公告)号:US12055643B2

    公开(公告)日:2024-08-06

    申请号:US18462886

    申请日:2023-09-07

    摘要: Aspects concern a method for correcting position estimates of a movable object. According to various embodiments, the method comprises establishing (1001) a hidden Markov model HMM, instance for a movable object and, for positioning times of a sequence of positioning times, receiving (1002) a position estimate from a positioning device of the movable object for a respective positioning time, determining (1003) a set of candidate path segments for the positioning time, determining (1004) likelihoods for the candidate path segments to correspond to the position estimate by application of the Viterbi algorithm to the HMM instance, expanding (1005) the HMM instance by the determined likelihoods for the candidate path segments for the positioning time and determining (1006) a corrected position estimate from a candidate path segment of the set of candidate path segments with the highest likelihood.

    METHOD AND DEVICE FOR CONTROLLING VEHICLES TO PERFORM

    公开(公告)号:US20240078488A1

    公开(公告)日:2024-03-07

    申请号:US18260851

    申请日:2022-05-12

    摘要: Aspects concern a method for controlling vehicles to perform transport tasks comprising supplying information about vehicles and information about transport tasks to a graph neural network by associating each vehicle with a vehicle graph node and each transport task with a transport task graph node, processing the vehicle and the transport graph by the neural network, wherein the neural network determines a feature for each graph node, determining, for each pair of a transport graph node and vehicle graph node, a weight representing a similarity between the features determined for the transport graph node and the vehicle graph node, selecting an assignment between the transport graph nodes and the vehicle graph nodes from a set of possible assignments, wherein the selected assignment maximizes the sum of the weights of the pairs and controlling each vehicle according to the selected assignment.

    METHOD FOR PREDICTING THE DESTINATION LOCATION OF A VEHICLE

    公开(公告)号:US20240077325A1

    公开(公告)日:2024-03-07

    申请号:US18486271

    申请日:2023-10-13

    摘要: Aspects concern a method for predicting the destination location of a vehicle, comprising processing a local preference graph of a user of the vehicle having nodes corresponding to locations visited before by the user by a first graph neural network, processing one or more of a spatial graph representing information about geographical proximity of locations, a temporal graph representing information about locations which have been visited one after another by users and the time between the visits of the locations and a preference graph representing information about locations which have been visited one after another and the frequency of visits of the locations by a second graph neural network, combining the result of the processing by the first graph neural network and the result of the processing by the second graph neural network by at least one neural network layer and using the output of the at least one neural network layer as prediction of the destination location.

    SYSTEM AND METHOD FOR PREDICTING DESTINATION LOCATION

    公开(公告)号:US20240044663A1

    公开(公告)日:2024-02-08

    申请号:US18256649

    申请日:2022-02-09

    IPC分类号: G01C21/36 G01C21/34

    摘要: A system for predicting a destination location may include one or more processors and a memory having instructions stored therein. The one or more processors may use at least one recurrent neural network to: process spatial data which may include a first set of information about origin locations and destination locations; process temporal data which may include a second set of information about times at the origin locations and the destination locations; determine hidden state data based on the spatial data and the temporal data, wherein the hidden state data may include data on origin-destination relationships; receive a current input data from a user, wherein the current input data may include an identity of the user and the current origin location of the user; and predict the destination location based on the hidden state data and the current input data.

    PROCESSING APPARATUS AND METHOD FOR TRAFFIC MANAGEMENT OF A NETWORK OF ROADS

    公开(公告)号:US20230368658A1

    公开(公告)日:2023-11-16

    申请号:US18028938

    申请日:2021-10-26

    IPC分类号: G08G1/01 G01C21/00

    摘要: A processing apparatus for traffic management of a network of roads is provided, to, generate, based on journey data sets, first count data indicative of a first count of the road users travelling on an incoming road leading to the intersection node, and second count data indicative of a second count of the road users travelling on an outgoing road of at least two outgoing roads, each outgoing road leading away from the intersection node, generate result data indicative of a result that is determined based on the first count and the second count, if the result satisfies a condition for restriction, generate restriction data indicative of a restriction of traffic from the incoming road to the outgoing road via the intersection node, and generate, based on an angular relationship between the outgoing road and the incoming road, type data indicative of a type of the restriction.

    METHOD AND SYSTEM FOR DEDUPLICATING POINT OF INTEREST DATABASES

    公开(公告)号:US20230306004A1

    公开(公告)日:2023-09-28

    申请号:US18036258

    申请日:2022-01-03

    摘要: An automated computer implemented method of deduplicating point of interest of computer implemented database including: standardizing data of a pair of records, wherein equivalent words with different spelling may be normalized to a single spelling; classifying the pair of records into a category of pre-defined address categories; carrying out a category specific determination of non-duplicate and failing to determine that the pair of records may be a category specific non-duplicate; tokenizing the data of the pair of records into a pair of tokenized records; determining that core words of the pair of records are linked by computing scores of cross information and distance; and determining whether the scores pass a pre-determined threshold. An aspect of the disclosure relates to an electronic data processing system, a data processing apparatus, a non-transitory computer-readable medium, and a computer executable code for deduplicating point of interest of computer implemented database.