利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

4 records (took 0.009 seconds)

    PEER VEHICLE BEHAVIOR PREDICTION SYSTEM AND METHOD
    2.
    发明申请
    PEER VEHICLE BEHAVIOR PREDICTION SYSTEM AND METHOD 审中-公开

    公开(公告)号：WO2022008362A1

    公开(公告)日：2022-01-13

    申请号：PCT/EP2021/068288

    申请日：2021-07-02

    Applicant: KNORR-BREMSE SYSTEME FÜR NUTZFAHRZEUGE GMBH

    Inventor： KARZ, Gergely, Jakab ,  BOKA, Jeno ,  DUDAS, Zsolt ,  GYENIS, Tamás ,  LINDENMAIER, Laszlo ,  NEMETH, Huba ,  LÓRÁNT, Szabó ,  SZAPPANOS, Andras ,  SZÖLLOSI, Adam ,  VÖRÖS, Dániel ,  GYURKO, Zoltán

    IPC: G06K9/62 ,  G06K9/00

    Abstract: Peer vehicle behaviour prediction can be based on tail light recognition of that vehicle since intended behaviour of the peer vehicle is usually announced by a human driver or an automated driving system by activating tail lights correspondingly. In autonomous vehicle systems, there are multiple sensors that map the environment of the autonomous vehicle. These sensors include LiDARs, cameras, thermal cameras, ultrasonic sensors or others. Optical cameras provide a video stream of the environment. Vehicle tail light recognition can be treated as an application of video acquisition and thus is susceptible to spatial and temporal image recognition. Such spatial and temporal image recognition is susceptible to deep learning approaches. Disclosed is a control system for autonomous driving of a vehicle, comprising a sensor that is configured to detect changes in the illumination state of at least a first kind of indicator lights and a second kind of indicator lights of a peer vehicle, an artificial neural network having a split neural network architecture, configured to recognize the activation state of the indicator lights of the peer vehicle, the artificial neural network comprising at least one spatial features extraction artificial neural network cell configured to extract spatial features of an output of the sensor of the indicator lights of the peer vehicle, a first temporal features extraction artificial neural network cell configured to extract temporal features of the output of the spatial features extraction artificial neural network cell, a second temporal features extraction artificial neural network cell configured to extract temporal features of the output of the spatial features extraction artificial neural network cell, wherein the first temporal features extraction artificial neural network cell is configured to determine changes in the activation state of the first kind of the indicator lights and to classify the first kind of indicator light as active or inactive, and the second temporal features extraction artificial neural network cell is configured to determine changes in the activation state of the second kind of the indicator lights and to classify the second kind of indicator light as active or inactive.

    PEER VEHICLE CENTER LINE DETERMINATION SYSTEM AND METHOD
    3.
    发明申请
    PEER VEHICLE CENTER LINE DETERMINATION SYSTEM AND METHOD 审中-公开

    公开(公告)号：WO2022008267A1

    公开(公告)日：2022-01-13

    申请号：PCT/EP2021/067546

    申请日：2021-06-25

    Applicant: KNORR-BREMSE SYSTEME FÜR NUTZFAHRZEUGE GMBH

    Inventor： BOKA, Jeno ,  KARZ, Gergely, Jakab ,  DUDAS, Zsolt ,  GYENIS, Tamás ,  LINDENMAIER, Laszlo ,  NEMETH, Huba ,  LÓRÁNT, Szabó ,  SZAPPANOS, Andras ,  VÖRÖS, Dániel ,  SZÖLLOSI, Adam ,  GYURKÓ, Zoltán

    IPC: G06K9/00 ,  G06K9/46 ,  G08G1/16

    Abstract: Disclosed is a system and method for peer vehicle position determination by determining the peer vehicle's center line. Disclosed is a control system for autonomous driving of a vehicle, configured to determine the center line of a peer vehicle comprising a sensor that is configured to record a pair of one and another symmetrical features of the peer vehicle that are symmetrical to a virtual center line of the peer vehicle, an artificial neural network having a split neural network architecture, configured to recognize the pair of symmetrical features of the peer vehicle, from input information provided by the sensor, the artificial neural network comprising at least one spatial features extraction artificial neural network cell configured to extract the symmetrical features from the input information of the peer vehicle by the sensor, a first symmetrical feature detector artificial neural network cell configured to extract spatial features of one symmetrical feature of the output of the spatial features extraction artificial neural network cell, a second symmetrical feature detector artificial neural network cell configured to extract spatial features of the other symmetrical feature of the output of the spatial features extraction artificial neural network cell, wherein the center line of the peer vehicle is determined to be the average position between the extracted spatial features of the one symmetrical feature and the extracted spatial features of the other symmetrical feature.

Patent Agency Ranking