METHODS AND ELECTRONIC DEVICES FOR DETECTING OBJECTS IN THE ENVIRONMENT OF AN UNMANNED VEHICLE Russian patent published in 2022 - IPC G08G1/123 G01S17/58 G01S17/42 G06T15/20 G06T17/10 

Abstract RU 2767831 C1

FIELD: unmanned vehicles.

SUBSTANCE: invention relates to unmanned vehicles. A method for detecting an object in the environment of an unmanned vehicle is proposed, while the method contains generating, using an electronic device, a cluster of points from a point cloud, and the point cloud represents the SDC environment, generating, by an electronic device using the first neural network, the first feature vector based on the cluster, and the first feature vector is associated with each point from the cluster and indicates the local context of this object in the SDC environment, generating, by an electronic device using the second NN, the second feature vectors for the corresponding points from the cluster based on a part of the point cloud, and this second feature vector of the corresponding point from the cluster indicates the local context of this object in the SDC environment and the global context of this object in the SDC environment, generation, by an electronic device using the first NN, the third feature vector for this object based on the second feature vectors of the cluster, and the third feature vector represents this object in the SDC environment and indicates both the local and global context of the object in the SDC environment, and generation, by an electronic device using a third NN bounding box around a given object using a third feature vector. Timely detection of objects is achieved.

EFFECT: expansion of the range of solutions to develop unmanned vehicles.

26 cl, 10 dwg

Similar patents RU2767831C1

Title Year Author Number
METHODS AND SYSTEMS FOR AUTOMATED DETERMINATION OF OBJECTS PRESENCE 2019
  • Katrenko Petr Vadimovich
  • Murashkin Vyacheslav Vladimirovich
RU2744012C1
METHOD (OPTIONS) AND SYSTEM FOR CALIBRATING SEVERAL LIDAR SENSORS 2019
  • Vojnov Andrej Sergeevich
RU2767949C2
METHODS AND SYSTEMS FOR DETERMINING THE PRESENCE OF DYNAMIC OBJECTS BY A COMPUTER 2019
  • Rykov Andrej Olegovich
  • Murashkin Vyacheslav Vladimirovich
  • Filatov Artem Andreevich
RU2767955C1
METHODS AND SYSTEMS FOR PROCESSING LIDAR SENSOR DATA 2020
  • Korobkin Mikhail Vladimirovich
  • Kovalenko Dmitrij Andreevich
  • Minin Andrej Anatolevich
RU2764708C1
METHODS AND SYSTEMS FOR PROCESSING LIDAR SENSOR DATA 2020
  • Korobkin Mikhail Vladimirovich
  • Kovalenko Dmitrij Andreevich
  • Minin Andrej Anatolevich
RU2775822C1
METHODS AND SYSTEMS FOR AUTOMATED DETECTION OF THE PRESENCE OF OBJECTS 2019
  • Yangel Boris Konstantinovich
  • Stebelev Maksim Ilich
RU2769921C2
METHOD AND SYSTEM FOR PREDICTING A MANOEUVRE OF THE OBJECT 2021
  • Fedorov Sergey Dmitrievich
  • Nedoluzhko Andrey Alekseevich
  • Melnichenko Daniil Vladimirovich
RU2778300C1
METHOD AND SYSTEM FOR DETERMINING DEGREE OF DETERIORATION OF LIDAR DATA 2021
  • Danilyuk Kirill Evgenevich
  • Tochilkin Dmitrij Sergeevich
RU2826476C1
METHOD AND SYSTEM FOR GENERATING THE REFERENCE PATH OF A SELF-DRIVING CAR (SDC) 2019
  • Gud Pavel Sergeevich
RU2746026C1
METHOD AND DEVICE FOR CONTROLLING AN UNMANNED VEHICLE 2021
  • Yaskevich Siarhei
  • Fiodarau Yauheni
RU2805539C2

RU 2 767 831 C1

Authors

Rykov Andrey Olegovich

Filatov Artem Andreevich

Dates

2022-03-22Published

2021-03-26Filed