Beijing Baidu Netcom Science Technology Co., Ltd

Beijing Goldwind Science & Creation Windpower Equipment Co., Ltd.

Boe Technology Group Co., Ltd.

Chinese Academy of Sciences

Hefei Xinsheng Optoelectronics Technology Co., Ltd.

Beijing Baidu Netcom Science and Technology Co., Ltd.

Apollo Intelligent Driving Technology (beijing) Co., Ltd.

Xinjiang Goldwind Science & Technology Co., Ltd.

Tsinghua University

Hefei Boe Optoelectronics Technology Co., Ltd.

Goldwind Science & Technology Co., Ltd.

Liang Peng

Guowei Wan

Yanhui Li

Shiyu Song

Yao Zhou

Shenhua Hou

Yuzhe He

Li Yu

Long Cheng

Zengguang Hou

Wendong Ding

Weixin Lu

Xiaoliang Xie

Guibin Bian

Deyong Wang

Weiqun Wang

Jian Wang

Hong Wang

Dong Wang

Jun Li

Yang Xia

Wei Gao

Min Tan

Qiong Yang

Wenjie Liu

Tong Wang

Pengfei Yuan

Chengqian Liu

Sai Zhang

Renlan Cai

Quan Wen Zhang

Liang Xiao

Yunqi Zhang

Daeyoung Choi

Xiaotao Li

Xunze Zhang

Zengli Liu

Daowu Huang

Wenhao Yu

Sangsoo Park

Yucheng Zhang

Likun Liu

Xu Liang

Long Peng

Xiangyu Fu

Yangyang Dai

Baofu Hu

Yingying Qin

Bin Lan

Longlong Duan

Zhiyuan Dong

Yanrui Shen

Weihua Fang

Liumin Yu

Congqi Zheng

Yefa Li

Mianen Chen

Deguo He

Beifan Ma

Xintao Bao

Lincong Luo

A method of processing an image, a method of training a multi-task processing model, and an electronic device, which relate to a field of an automatic driving technology, in particular to a field of high-definition map technology. The method of processing an image includes: processing a to-be-processed image to obtain a feature point of the to-be-processed image, a feature point descriptor map of the to-be-processed image, and a dense descriptor map of the to-be-processed image; determining a pair of matched feature points between the to-be-processed image and a reference image based on the feature point and the feature point descriptor map; and determining a pair of matched pixels between the to-be-processed image and the reference image based on the dense descriptor map.

Method of processing image, method of training model, and electronic device

A positioning method based on a lane line and a feature point, an electronic device, and a storage medium, which relate to fields of computer, automatic driving, intelligent transportation, computer vision. The method may include: determining first real-time measurement residuals according to first sensor information of a movable object detected, the first real-time measurement residuals including a first inertial measurement unit measurement residual, a first lane line measurement residual and a first non-lane line measurement residual; updating a state vector of the movable object according to a kinematic model of an inertial measurement unit and the first real-time measurement residuals; and determining a pose of the movable object at a time instant corresponding to the updated state vector according to a pose vector in the updated state vector.

Positioning method based on lane line and feature point, electronic device, and storage medium

The present disclosure relates to a stator support and a stator. The stator support is applied to a large-diameter electric motor. The stator support includes a stator shaft, coaxially connectable to a fixing shaft of the electric motor; a supporting assembly, coaxially arranged at an outer circumference of the stator shaft; a stator ring, connectable to a stator iron core of the electric motor, in which the stator ring includes two or more stator ring segments continuously distributed in a circumferential direction of its own, each of the stator ring segments is in a sector shape, and the two or more stator ring segments are coaxially arranged at an outer circumference of the supporting assembly.

Stator support for large-diameter electric motor and stator

A high-definition map creation method includes: obtaining point cloud data collected with respect to a target region, the point cloud data including K frames of point clouds and an initial pose of each frame of point cloud, K being an integer greater than 1; associating the K frames of point clouds with each other in accordance with the initial pose to obtain a first point cloud relation graph of the K frames of point clouds; performing point cloud registration on the K frames of point clouds in accordance with the first point cloud relation graph and the initial pose to obtain a target relative pose of each frame of point cloud in the K frames of point clouds; and splicing the K frames of point clouds in accordance with the target relative pose to obtain a point cloud map of the target region.

High-definition map creation method and device, and electronic device

Exemplary positioning method and apparatus, a device, a system, a medium and a self-driving vehicle are provided. The positioning method includes determining, according to the current frame of point cloud data collected by a to-be-positioned terminal in a travelling environment, the current key point in the current frame of point cloud data and a point cloud distribution feature of the current key point; selecting, according to point cloud distribution features associated with reference key points in a global positioning map and the point cloud distribution feature of the current key point, a target key point matching the current key point from the reference key points; and determining, according to reference pose data associated with the target key point, the current pose data of the to-be-positioned terminal.

Positioning method and apparatus, device, system, medium and self-driving vehicle

A method of processing data for an autonomous vehicle, an electronic device, a storage medium, and an autonomous vehicle are provided. The method includes: acquiring sensor data for the autonomous vehicle, wherein the sensor data includes inertial measurement data, LiDAR data, and visual image data; determining a first constraint factor for the inertial measurement data according to the inertial measurement data and the visual image data; determining a second constraint factor for the LiDAR data according to the inertial measurement data and the LiDAR data; determining a third constraint factor for the visual image data according to the inertial measurement data, the visual image data and the LiDAR data; and processing the sensor data based on the first constraint factor, the second constraint factor and the third constraint factor, so as to obtain positioning data for positioning the autonomous vehicle.

Method of processing data for autonomous vehicle, electronic device, storage medium and autonomous vehicle

The present disclosure relates to a method for assembling a large-diameter electric motor, the method includes: a preparing step: providing two or more stator segments for forming a stator and two or more rotor support segments for forming a rotor support; a splicing step: splicing the two or more stator segments and the two or more rotor support segments in a predetermined manner to form the stator and the rotor support that are coaxially assembled, respectively, and maintaining a predetermined gap between the stator and the rotor support in a radial direction; and an assembling step: inserting a plurality of magnetic pole modules into the predetermined gap, and assembling the plurality of magnetic pole modules to a mounting surface of the rotor support.

Method for assembling large-diameter electric motor

The disclosure relates to an electric machine and an assembling method for an electric machine. The electric machine includes: a shaft assembly including a first shaft, a second shaft coaxially disposed within an inner circumference of the first shaft, and a bearing disposed between the first shaft and the second shaft; a first revolving body coaxially connected to the first shaft, wherein the first revolving body includes an annular first adapter bracket, and a tubular structural portion extending in an axial direction is disposed at an inner circumference of the first adapter bracket; a second revolving body coaxially connected to the second shaft and disposed around an outer circumference of the first revolving body; and a guiding assembly disposed between the tubular structural portion and the first shaft to restrict a movement of the first revolving body relative to the first shaft in a circumferential direction and a radial direction.

Electric machine and assembling method for electric machine

Disclosed is a device with a stator and a rotor, the device comprising: a stator; a rotor, wherein an air gap is provided between the rotor and the stator; and an air gap protection device fixedly connected to the stator, wherein the radial distance between the air gap protection device and the rotor is less than the radial distance between the stator and the rotor, and the air gap protection device rotates relative to the rotor when in contact with the rotor. By arranging the air gap protection device fixedly connected to the stator, the air gap protection device can rotate relative to the rotor when in contact with the rotor, and the radial distance between the air gap protection device and the rotor is less than the radial distance between the stator and the rotor.

Device with stator and rotor, and wind generating set

The present disclosure provides a vehicle positioning method, an apparatus and an autonomous driving vehicle, relating to autonomous driving in the technical field of artificial intelligence, which can be applied to high-definition positioning of the autonomous driving vehicle, the method including: if there is no high-definition map in a vehicle, acquiring intermediate pose information of the vehicle based on a global navigation satellite system and/or an inertial measurement unit in the vehicle, and determining the intermediate pose information as global positioning information; acquiring local positioning information; performing fusion processing to the global pose information and the local pose information to obtain fused pose information; performing compensation processing to the fused pose information according to the global attitude angle information and the local attitude angle information to obtain a position of the vehicle.

Vehicle positioning method, apparatus and autonomous driving vehicle

A magnetic pole module and a rotor for a permanent magnet generator are provided. The magnetic pole module includes a base plate having a first surface and a second surface arranged opposite to each other, the base plate has a first center line extending in the first direction and a second center line extending in the second direction, the first direction is intersected with the second direction, the first center line is parallel to the central axis of the permanent magnet generator; at least one pair of magnetic steel components is fixed on the base plate, and each pair of magnetic steel components is symmetrically arranged on the first surface with respect to the second center line, each magnetic steel component includes multiple magnetic steels arranged side by side along a side of the first direction from the second center line and arranged at a predetermined angle in the second direction.

Magnetic pole module and rotor for permanent magnet generator

A method, an electronic device and a readable storage medium for point cloud data processing, which may be used for autonomous driving, are disclosed. The feature vectors of respective points in the first point cloud data and second point cloud data are pre-learned, and thus the feature vectors of the first key points may be determined directly based on the learnt second feature vectors of respective first neighboring points of the respective first key points in the first point cloud data, and the feature vectors of the candidate key points may be determined directly based on the learnt third feature vectors of the respective second neighboring points of respective candidate key points in the second point cloud data corresponding to the first key points.

Method, apparatus, electronic device and readable storage medium for point cloud data processing

A rotor support, a rotor, a motor, and a wind turbine are provided. The rotor support includes a magnetic yoke and a reinforcement portion provided on a first side surface of the magnetic yoke; a second side surface of the magnetic yoke is configured to operably dispose a magnet of a rotor; the reinforcement portion covers each magnetic circuit area, which can generate a partial magnetic circuit, of the first side surface; the sum of the radial thicknesses of the reinforcement portion and the magnetic yoke overlapped is greater than a preset thickness, and the radial thickness of the magnetic yoke is less than the preset thickness.

Rotor support, rotor, motor, and wind turbine

A method, an apparatus, a computer storage medium and a terminal for implementing autonomous driving decision-making are disclosed. Image information is processed by the probabilistic object detection to obtain a probabilistic object detection result set containing multiple probabilistic object detection result. An uncertainty in the object detection process is estimated by the probabilistic object detection results contained in the set of the probabilistic object detection result. An environmental state information set is generated from the probabilistic object detection results in the probabilistic object detection result set and the perceptual information, then an optional action set considering the uncertainty is generated using a preset decision-making method, and an action for vehicle driving control is determined according to the optional action set and the environmental state information set.

Method, apparatus, computer storage medium and terminal for implementing autonomous driving decision-making

The present disclosure provides a point cloud data processing method, apparatus, electronic device and computer readable storage medium, which relates to computer vision technology and may be used for autonomous driving. A specific implementation solution is as follows: obtaining a first feature vector of each point in first point cloud data, and determining at least one first key point in the points in the first point cloud data according to the first feature vectors of respective points; according to the and a preset first conversion parameter between second point cloud data and the first point cloud data, obtaining second key points of the second point cloud data corresponding to the first key points in the at least one first key point, as candidate matching points; according to the first point cloud data, the second point cloud data and a preset search radius, determining at least one first neighboring point of the and at least one second neighboring point of the candidate matching point corresponding to the at least one first key point; determining a matching point with which the at least one first key point is registered, according to the at least one first neighboring point of the at least one first key point and the at least one second neighboring point of the candidate matching points.

Point cloud data processing method, apparatus, electronic device and computer readable storage medium

Growing community of inventors

Beijing, China

Liang Peng