公开(公告)号：US20250022222A1

公开(公告)日：2025-01-16

申请号：US18770446

申请日：2024-07-11

Applicant: Tongji University

Inventor： Bin He ,  Gang Li ,  Feng Li ,  Yulong Ding ,  Bin Cheng ,  Zhongpan Zhu ,  Zhipeng Wang

IPC: G06T17/00 ,  G06T5/20 ,  G06T5/70 ,  G06V10/44

Abstract: A method for constructing a structural semantic map under an underground weak-light and low-texture environment is provided. The method includes: fusing traditional methods with a parameter line detection and verification model of structural semantics of a Transformer; and establishing a geometric primitive half-plane search method guided by the direction of structural information. The method also includes establishing a neighborhood greedy expansion algorithm based on a geometric primitive model; and optimizing geometric primitive poses and boundaries one by one. The method further includes fusing a point cloud map with structural information, and establishing a semantic map with geometric structure primitives.

公开(公告)号：US12125142B2

公开(公告)日：2024-10-22

申请号：US17808117

申请日：2022-06-22

Applicant: TONGJI UNIVERSITY

Inventor： Bin He ,  Gang Li ,  Runjie Shen ,  Bin Cheng ,  Zhipeng Wang ,  Ping Lu ,  Zhongpan Zhu ,  Yanmin Zhou ,  Qiqi Zhu

IPC: G06T17/05 ,  B64C39/02 ,  B64U20/87 ,  B64U101/30 ,  G01C21/16 ,  G01S17/86 ,  G01S17/89 ,  G05D1/00 ,  G06T7/73 ,  G06T19/20

CPC classification number: G06T17/05 ,  B64C39/024 ,  B64U20/87 ,  G01C21/165 ,  G01S17/86 ,  G01S17/89 ,  G05D1/106 ,  G06T7/74 ,  G06T7/75 ,  G06T19/20 ,  B64U2101/30 ,  G06T2207/10028 ,  G06T2207/10032 ,  G06T2207/30181 ,  G06T2219/2016

Abstract: The method includes: obtaining point cloud information collected by a depth camera, laser information collected by a lidar, and motion information of an unmanned aerial vehicle (UAV); generating a raster map based on the laser information, and obtaining pose information of the UAV based on the motion information; obtaining a map model through fusing the point cloud information, the raster map, and the pose information by a Bayesian fusion method; and correcting a latest map model by feature matching based on a previous map model.

公开(公告)号：US11847920B2

公开(公告)日：2023-12-19

申请号：US17450577

申请日：2021-10-12

Applicant: Tongji University

Inventor： Bin He ,  Gang Li ,  Zhipeng Wang ,  Yanmin Zhou ,  Ping Lu ,  Zhongpan Zhu ,  Yang Shen

IPC: G08G5/00 ,  B64C39/02 ,  B64U101/00

CPC classification number: G08G5/003 ,  B64C39/024 ,  G08G5/0069 ,  B64U2101/00

Abstract: A system and a method are provided for feasibility evaluation of UAV Digital Twin based on Vicon motion capture system is disclosed, which establishes a mission feasibility evaluation model according to flight history data of a target UAV acquired by the UAV Digital Twin system. The mission feasibility evaluation model includes a UAV trajectory prediction module and a mission feasibility determination module. The UAV trajectory prediction module acquires real-time position and attitude information of the target UAV according to the Vicon motion capture system, and predicts target flight trajectory of the target UAV according to the real-time position and attitude information. The mission feasibility determination module compares the position difference between an end point of the target flight trajectory and preset designated mission point to evaluate feasibility of target mission of the target UAV.

公开(公告)号：US20220383484A1

公开(公告)日：2022-12-01

申请号：US17580935

申请日：2022-01-21

Applicant: Tongji University

Inventor： Bin He ,  Gang Li ,  Runjie Shen ,  Zhongpan Zhu ,  Zhipeng Wang ,  Jie Chen ,  Xudong Wang

IPC: G06T7/00 ,  G06T7/70 ,  G06T5/00 ,  G06T7/20 ,  G05D1/10 ,  G01M5/00

Abstract: Tunnel defect detecting method and system using unmanned aerial vehicle (UAV) are provided, and the UAV is equipped with a light-emitting diode (LED) module, a camera, a laser radar, an ultrasonic distance meter and an inertial measurement unit (IMU). The method includes: collecting images in a tunnel based on the LED module and the camera to obtain a training image set; training by using the training image set to obtain a defect detecting model, collecting real-time tunnel images, detecting suspected defects to the real-time tunnel images by the defect detecting model, obtaining pose information of the UAV based on the camera, the laser radar, the ultrasonic distance meter and the IMU to control the UAV to hover. The method can realize accurate pose estimation and defect detection in the tunnel with no GPS signals and highly symmetrical inside.

公开(公告)号：US20240161638A1

公开(公告)日：2024-05-16

申请号：US18387562

申请日：2023-11-07

Applicant: Tongji University

Inventor： Gang Li ,  Bin He ,  Runjie Shen

IPC: G08G5/04 ,  B64U20/30 ,  G01C21/20 ,  G08G5/00

CPC classification number: G08G5/045 ,  B64U20/30 ,  G01C21/20 ,  G08G5/0069 ,  B64U2101/70

Abstract: The present disclosure relates to a detection method and system for an underground space by joint use of fixed sensors and unmanned aerial vehicle (UAV) movement detection. The detection system includes underground space sensor nodes and an underground space UAV. The underground space sensor nodes are configured to perform fixed monitoring based on an adaptive optimal layout strategy for an underground structural space. The underground space UAV is configured to calculate a first virtual force, and realize movement detection by means of a virtual force-guided path planning algorithm. The underground space UAV is configured to calculate the first virtual force based on the electronic telescopic anti-collision bars, a second virtual force based on a static perception probability and a third virtual force based on structural evolution knowledge, and realize a fixed node-guided UAV flight detection mode by means of the virtual force-guided path planning algorithm.

公开(公告)号：US12112645B2

公开(公告)日：2024-10-08

申请号：US17870592

申请日：2022-07-21

Applicant: TONGJI UNIVERSITY

Inventor： Bin He ,  Gang Li ,  Runjie Shen ,  Yanmin Zhou ,  Jie Chen ,  Shuping Song

IPC: G08G5/00 ,  B64C39/02

CPC classification number: G08G5/006 ,  B64C39/024 ,  B64U2201/10

Abstract: Disclosed is an unmanned aerial vehicle (UAV) positioning method based on a millimeter-wave radar, including a calibration stage and a positioning stage. The calibration stage includes: acquiring ground coordinates of the unmanned aerial vehicle; and extracting feature points from radar point cloud data and get the ground coordinates of the feature points. The positioning stage includes: acquiring radar point cloud data of a current frame and pre-processing; acquiring UAV motion data and fuse the data with radar point cloud data; extracting characteristic line segment from radar point cloud data; registering the characteristic line segment of the current frame with the characteristic line segment of the previous frame, and finding matching feature points and newly added feature points; and obtaining the ground coordinates of UAV and the ground coordinates of newly added feature points based on the ground coordinates of matched feature points on the map.