CN113589323A - Road obstacle identification method based on height vector field - Google Patents

Road obstacle identification method based on height vector field Download PDF

Info

Publication number
CN113589323A
CN113589323A CN202110799372.5A CN202110799372A CN113589323A CN 113589323 A CN113589323 A CN 113589323A CN 202110799372 A CN202110799372 A CN 202110799372A CN 113589323 A CN113589323 A CN 113589323A
Authority
CN
China
Prior art keywords
laser radar
axis
point
processor
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110799372.5A
Other languages
Chinese (zh)
Inventor
刘瑜
黄鑫
邹振超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Sci Tech University ZSTU
Zhejiang University of Science and Technology ZUST
Original Assignee
Zhejiang Sci Tech University ZSTU
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Sci Tech University ZSTU filed Critical Zhejiang Sci Tech University ZSTU
Priority to CN202110799372.5A priority Critical patent/CN113589323A/en
Publication of CN113589323A publication Critical patent/CN113589323A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/08—Systems determining position data of a target for measuring distance only

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Electromagnetism (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

A method for recognizing road obstacles based on a height vector field is disclosed, wherein a laser radar is arranged in the front upper part of a helmet, a loudspeaker is arranged at the same time, a controller is arranged in the helmet and comprises a processor and a vibrator connected with the processor, the processor is connected with the laser radar and the loudspeaker, a sensor coordinate system XYZ is established at the central position of the laser radar, the X axis points to the front lower part, the Y axis points to the left side, the Z axis points to the front upper part, a world coordinate system XYZ is established at the same time, the Y axis is superposed with the Y axis, the X axis points to the right front, and the Z axis points to the vertical upper part, the processor is used for realizing the method for recognizing the road obstacles and comprises the following steps: the processor reads the data f output by the laser radark(i, j) and converting into a point [ X ] in a world coordinate systemij k，Yij k，Zij k]‑1(ii) a Calculating a height field vector (Δ Z)ij k，ωij k) Establishing a height vector field of the environment, screening out data of the position of the obstacle, and extracting obstacle information; and carrying out obstacle prompting.

Description

Road obstacle identification method based on height vector field
Technical Field
The patent relates to a road obstacle identification method based on a height vector field, and belongs to the technical field of artificial intelligence and environmental perception.
Background
The laser radar is well applied to the field of automatic driving of automobiles, and helps the automobiles to identify the obstacle condition of the driving environment. The laser radar is based on the laser ranging principle, measures the distance between a sensor and an object, and can rotate for a certain angle in the horizontal and vertical directions to realize 3D detection. Because the laser ranging has the advantages of high ranging precision, high detection speed and high resolution, the automobile driving environment can be accurately modeled, and a data basis is provided for intelligent algorithms such as intelligent navigation, safe obstacle avoidance and the like. Be different from car autopilot's service environment, the road surface environment that the smart machine that provides road navigation for vision disorder personnel faces is more complicated, and is more unstructured, except bellied barrier, still may sunken step, and such road conditions all can bring danger for vision disorder personnel.
Disclosure of Invention
Aiming at the problems, the patent provides a road obstacle identification method based on a height vector field in order to meet the road navigation requirement of vision-impaired people when going out, establishes the height vector field of a road based on laser detection points on a traveling road, has an altitude change amplitude attribute and an altitude change direction attribute, and can quickly judge the road obstacle condition.
The technical scheme adopted by the patent for solving the technical problem is as follows:
the beneficial effect of this patent mainly shows: the height vector field is established for the road in the traveling direction, the height change amplitude attribute and the height change direction attribute are provided, the road obstacle condition can be rapidly judged, voice and vibration prompt is carried out, and the traveling safety of visually-impaired people is guaranteed.
Drawings
FIG. 1 is a schematic view of the appearance and coordinate system of the present invention;
FIG. 2 is a schematic illustration of the depressed region identification calculation of the present invention;
FIG. 3 is a schematic diagram of raised obstacle identification calculation of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings:
referring to fig. 1 to 3, in order to help visually-handicapped persons to travel autonomously and to judge the obstacle situation on a traveling road in real time, a road obstacle identification method based on a height vector field is provided. The laser radar 2 is arranged at the front upper part of the helmet 1, the detection direction of the laser radar 2 is arranged at the front lower part, and the situation of the ground in front is detected. The helmet 1 can protect the head of a user in an accidental situation on the one hand and can also be provided with electronic equipment on the other hand.
The two sides of the helmet 1 are provided with the loudspeakers 5 for voice broadcasting, so that voice broadcasting and danger warning can be performed; the helmet 1 side set up interface 3 and the switch button 4 that charges, interface 3 that charges can connect the outside power of using that charges.
The helmet 1 is internally provided with a controller, and the controller comprises a processor for performing centralized control and a vibrator which is connected with the processor and consists of a flat motor, and is used for performing danger prompt. The charging circuit is connected with the charging interface 3, the output of the charging circuit is connected with a rechargeable battery, the output of the rechargeable battery is connected with a power circuit, and the power circuit outputs power required by the controller and other modules. The processor is connected with the laser radar 2, the switch key 4 and the loudspeaker 5 to realize centralized control; the switch key 4 is used for starting or closing the controller.
For data calculation, a sensor coordinate system XYZ is established at the central position of the laser radar 2, the X axis points to the detection central direction of the laser radar 2 and forms an included angle beta with the horizontal direction, the Y axis points to the left side, the Z axis points to the front upper side, a world coordinate system XYZ is established simultaneously, the Y axis coincides with the Y axis, the X axis points to the front, and the Z axis points to the vertical upper side.
The output data f of the laser radar 2k(i，j)＝{(dk ij，αiJ · θ) }, where k is 0, 1, 2., a detection sequence number, αiThe angle of the laser radar 2 detected in the vertical direction is represented by i, i is a data serial number in the vertical direction, i is 0, 1, 2.. N-1, N is a line number of the laser radar 2, j is a data serial number in the horizontal direction, j is 0, 1, 2.. and θ is a detection angle increment of the laser radar 2 in the horizontal direction. Superior foodOptionally, the lidar 2 is configured as a Velodyne VLP16 lidar, N is 16, α0To alpha15In the order-15 °, 1 °, -13 °, 3 °, -11 °, 5 °, -9 °, 7 °, -7 °, 9 °, -5 °, 11 °, -3 °, 13 °, -1 °, 15 °, θ ═ 0.1 °, since the detection range in the horizontal direction of the VLP16 is 360 °, the value range of j is only 120 °, i.e., j ═ 0, 1, 2.. 1200.
The processor is used for realizing a road obstacle identification method, and the road obstacle identification method comprises the following steps:
(1) every fixed period delta T, the processor reads the output data f of the laser radar 2k(i，j)＝{(dk ij，αiJ θ) is converted into a point [ x ] in the sensor coordinate systemij k，yij k，zij k]-1＝[dij k·cosαi·sin(j·θ-θ0)，dij k·cosαi·cos(j·θ-θ0)，dij k·sinαi]Wherein theta0A detection angle of j ═ 0; using coordinate conversion method to convert point [ x ]ij k，yij k，zij k]-1Conversion to points in the world coordinate system
Figure BSA0000247438710000031
The laser radar 2 acquires the distances between the object reflection point and the laser radar 2 at different angles and directions, and the distances need to be converted into coordinates under a sensor coordinate system and further converted into coordinates under a world coordinate system, so that convenience is brought to subsequent data processing.
(2) At point [ X ]ij k，Yij k，Zij k]-1And in the formed set, searching for obstacles and extracting obstacle information: distance D, orientation δ, width W, height H. Point [ X ]ij k，Yij k，Zij k]-1Is a laser detection point on the surface of an object,point [ X ]ij k，Yij k，Zij k]-1The set of components is in the form of a point cloud, which is a set of detected points on the surface of the object. The method comprises the following specific steps:
(2a) search point [ X ]ij k，Yij k，Zij k]-1Adjacent point in positive X-axis direction [ Xmn k，Ymn k，Zmn k]-1I.e. alpham＞αiAt the same time [ (X)mn k-Xij k)2+(Ymn k-Yij k)2]1/2Minimum, where m is 0, 1, 2.. N-1, N is 0, 1, 2.. Δ X is calculatedij k＝Xmn k-Xij k，ΔZij k＝Zmn k-Zij kIf Δ Xij kWhen the value is 0, point [ X ]ij k，Yij k，Zij k]-1To a neighboring point [ X ]mn k，Ymn k，Zmn k]-1Angle of vector (d) to the X-axis
Figure BSA0000247438710000041
Otherwise
Figure BSA0000247438710000042
Then point [ X ]ij k，Yij k，Zij k]-1Has a height field vector of (Δ Z)ij k，ωij k)；
First, the direction of the user's walking is the positive direction toward the X-axis, so when calculating the height vector field, the current point [ X ] is selectedij k，Yij k，Zij k]-1With a nearest neighbor point [ X ] having a larger detection angle in the vertical directionmn k，Ymn k，Zmn k]-1And (6) performing calculation. First, the variation DeltaX in the X-axis and Y-axis directions is calculatedij kAnd Δ Zij kThen calculate the point [ X ]ij k，Yij k，Zij k]-1To a neighboring point [ X ]mn k，Ymn k，Zmn k]-1Angle omega between the vector of (A) and the X-axisij k. Calculate ωij kWhen considering various conditions, Δ Xij k＝0，ΔXij k< 0 and Δ Xij kCase > 0. Finally formed as a vector (Δ Z)ij k，ωij k) To describe the height vector field of the road's obstacle situation, each datum having a magnitude and a direction.
(2b) When ω isij k< T omega, point [ X ]ij k，Yij k，ΔZij k]-1Store in data link list L0(ii) a When ω isij k> T omega, point [ X [)ij k，Yij k，ΔZij k]-1Store in data link list L1T omega is an angle threshold;
by vector (Δ Z)ij k，ωij k) Angle of (W) to (W)ij kAs conditions for screening for obstacles, at ωij kThe place where the absolute value is too large is the position of the raised obstacle or the recessed area. On flat ground, Δ Zij kSmall fluctuations kept around the 0 value; in the downward recessed area, such as the downward step, as shown in fig. 2, the following features are provided: the absolute value of the Z coordinate is obviously increased, the vector points downwards, and the included angle omega is formedij kIs a negative value; at the location of a raised obstacle, such as an upright wall surface, as shown in fig. 3, the following features are provided: first, the X coordinate does not increase or increase slightly, even decreases slightly; secondly, the Z coordinate changes obviously, the vector points upwards, and the included angle omega is formedij kPositive values.
(2c) After traversing all the points, if the data link list L0If not, then calculate the parameters of the recessed area: distance D ═ MinX (L)0) Azimuth δ is arctan (AvergeY (L)0)/AvergeX(L0) Width W ═ MaxY (L) >)0)-MinY(L0) Height H ═ average Δ Z (L)0)；
If the data link list L1If not, calculating a convex obstacle parameter: distance D ═ MinX (L)1) Azimuth δ is arctan (AvergeY (L)1)/AvergeX(L1) Width W ═ MaxY (L) >)1)-MinY(L1) Is prepared by mixing L1Data Δ Z in (1)ij kThe i is subjected to integral summation to obtain
Figure BSA0000247438710000051
Height H ═ Max { Δ Z j k0, 1, 2, wherein Max is a calculation formula for calculating the maximum value;
MinX and MinY are respectively an X coordinate and a Y coordinate minimum value formula in the calculation data chain table, MaxY is a Y coordinate maximum value formula in the calculation data chain table, and avergeX, avergeY and Averge delta Z are X coordinate, Y coordinate and delta Z mean values in the calculation data chain table.
On the calculation of the height H parameter, there is a difference between the concave area and the convex obstacle: the morphological feature of the concave region is mainly concentrated on the edge of the concave region, and therefore, the Δ Z of the edge point is usedij kAs the height H parameter of the recessed region; for the raised barrier, the detection points are distributed from bottom to top along the vertical surface or the inclined surface, and the Δ Z needs to be adjustedij kThe height H can be obtained by adding up in the vertical direction. Therefore, first L1Data Δ Z in (1)ij kSumming the data with the same j, namely summing the data with the same detection angle in the horizontal direction to obtain delta Zj kAnd then taking the maximum value as the height H parameter of the obstacle.
(3) If an obstacle is found, the processor alerts the user via the vibrator and broadcasts obstacle information via the speaker 5.
Through vibration and sound prompt and early warning, the travel safety of the user can be effectively guaranteed.

Claims (1)

1. The method for identifying the road obstacle based on the height vector field comprises the steps that a laser radar is arranged on the front upper portion of a helmet, the detection direction of the laser radar is arranged on the front lower portion, loudspeakers for voice broadcasting are arranged on two sides of the helmet, a charging interface and a switch button are arranged on the side face of the helmet, a controller is arranged inside the helmet, the controller comprises a processor for performing centralized control, a vibrator which is connected with the processor and consists of a flat motor, and a charging circuit connected with the charging interface, the output of the charging circuit is connected with a charging battery, the output of the charging battery is connected with a power circuit, the power circuit outputs power required by the controller and other modules, and the laser radar, the switch button and the loudspeakers are connected with the processor; the laser radar is used for detecting the condition of the ground in front, a sensor coordinate system XYZ is established at the center position, the X axis points to the detection center direction of the laser radar, a beta included angle is formed between the X axis and the horizontal direction, the Y axis points to the left side, the Z axis points to the front upper side, a world coordinate system XYZ is established simultaneously, the Y axis and the Y axis are superposed, the X axis points to the right front side, the Z axis points to the vertical upper side, and the laser radar outputs data fk(i，j)＝{(dk ij，αiJ · θ) }, where k is 0, 1, 2., a detection sequence number, αiFor the detection angle of the laser radar in the vertical direction, i is a data serial number in the vertical direction, i is 0, 1, 2.. N-1, N is the line number of the laser radar, j is a data serial number in the horizontal direction, j is 0, 1, 2.. and θ is a detection angle increment of the laser radar in the horizontal direction, and the detection angle increment is characterized in that: the processor is used for realizing a road obstacle identification method, and the road obstacle identification method comprises the following steps:
(1) every fixed period delta T, the processor reads the laser radar output data fk(i，j)＝{(dk ij，αiJ θ) into a sensor coordinate systemPoint of lower [ x ]ij k，yij k，zij k]-1＝[dij k·cosαi·sin(j·θ-θ0)，dij k·cosαi·cos(j·θ-θ0)，dij k·sinαi]Wherein theta0A detection angle of j ═ 0; using coordinate conversion method to convert point [ x ]ij k，yij k，zij k]-1Conversion to points in the world coordinate system
Figure FSA0000247438700000011
(2) At point [ X ]ij k，Yij k，Zij k]-1And in the formed set, searching for obstacles and extracting obstacle information: distance D, azimuth delta, width W and height H, and the method comprises the following specific steps:
(2a) search point [ X ]ij k，Yij k，Zij k]-1Adjacent point in positive X-axis direction [ Xmn k，Ymn k，Zmn k]-1I.e. alpham＞αiAt the same time [ (X)mn k-Xij k)2+(Ymn k-Yij k)2]1/2Minimum, where m is 0, 1, 2.. N-1, N is 0, 1, 2.. Δ X is calculatedij k＝Xmn k-Xij k，ΔZij k＝Zmn k-Zij kIf Δ Xij kWhen the value is 0, point [ X ]ij k，Yij k，Zij k]-1To a neighboring point [ X ]mn k，Ymn k，Zmn k]-1Angle of vector (d) to the X-axis
Figure FSA0000247438700000021
Otherwise
Figure FSA0000247438700000022
Then point [ X ]ij k，Yij k，Zij k]-1Has a height field vector of (Δ Z)ij k，ωij k)；
(2b) When ω isij k< T omega, point [ X ]ij k，Yij k，ΔZij k]-1Store in data link list L0(ii) a When ω isij k> T omega, point [ X [)ij k，Yij k，ΔZij k]-1Store in data link list L1T omega is an angle threshold;
(2c) after traversing all the points, if the data link list L0If not, then calculate the parameters of the recessed area: distance D ═ MinX (L)0) Azimuth δ is arctan (AvergeY (L)0)/AvergeX(L0) Width W ═ MaxY (L) >)0)-MinY(L0) Height H ═ average Δ Z (L)0)；
If the data link list L1If not, calculating a convex obstacle parameter: distance D ═ MinX (L)1) Azimuth δ is arctan (AvergeY (L)1)/AvergeX(L1) Width W ═ MaxY (L) >)1)-MinY(L1) Is prepared by mixing L1Data Δ Z in (1)ij kThe i is subjected to integral summation to obtain
Figure FSA0000247438700000023
Height H ═ Max { Δ Zj k0, 1, 2, wherein Max is a calculation formula for calculating the maximum value;
MinX and MinY are respectively an X coordinate and a Y coordinate minimum value formula in the calculation data chain table, MaxY is a Y coordinate maximum value formula in the calculation data chain table, and avergeX, avergeY and Averge delta Z are X coordinate, Y coordinate and delta Z mean values in the calculation data chain table.
(3) If an obstacle is found, the processor alerts the user through the vibrator and broadcasts obstacle information through the speaker.
CN202110799372.5A 2021-07-07 2021-07-07 Road obstacle identification method based on height vector field Pending CN113589323A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110799372.5A CN113589323A (en) 2021-07-07 2021-07-07 Road obstacle identification method based on height vector field

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110799372.5A CN113589323A (en) 2021-07-07 2021-07-07 Road obstacle identification method based on height vector field

Publications (1)

Publication Number Publication Date
CN113589323A true CN113589323A (en) 2021-11-02

Family

ID=78247533

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110799372.5A Pending CN113589323A (en) 2021-07-07 2021-07-07 Road obstacle identification method based on height vector field

Country Status (1)

Country Link
CN (1) CN113589323A (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101266132A (en) * 2008-04-30 2008-09-17 西安工业大学 Running disorder detection method based on MPFG movement vector
CN102194217A (en) * 2010-03-05 2011-09-21 索尼公司 Information processing apparatus, information processing method, and imaging apparatus including optical microscope
CN105718888A (en) * 2016-01-22 2016-06-29 北京中科慧眼科技有限公司 Obstacle prewarning method and obstacle prewarning device
US20170225680A1 (en) * 2015-05-12 2017-08-10 SZ DJI Technology Co., Ltd Apparatus and methods for obstacle detection
WO2018058937A1 (en) * 2016-09-30 2018-04-05 深圳市镭神智能系统有限公司 Head-mount blind guiding device
CN108663681A (en) * 2018-05-16 2018-10-16 华南理工大学 Mobile Robotics Navigation method based on binocular camera Yu two-dimensional laser radar
CN109144072A (en) * 2018-09-30 2019-01-04 亿嘉和科技股份有限公司 A kind of intelligent robot barrier-avoiding method based on three-dimensional laser
KR101998298B1 (en) * 2018-12-14 2019-07-09 위고코리아 주식회사 Vehicle Autonomous Driving Method Using Camera and LiDAR Sensor
CN112784799A (en) * 2021-02-01 2021-05-11 三一机器人科技有限公司 AGV (automatic guided vehicle) backward pallet and obstacle identification method and device and AGV
CN112799098A (en) * 2020-12-08 2021-05-14 深兰科技（上海）有限公司 Radar blind area monitoring method and device, electronic equipment and storage medium
CN112870033A (en) * 2021-01-20 2021-06-01 江西理工大学南昌校区 Intelligent blind guiding helmet system for unstructured road and navigation method

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101266132A (en) * 2008-04-30 2008-09-17 西安工业大学 Running disorder detection method based on MPFG movement vector
CN102194217A (en) * 2010-03-05 2011-09-21 索尼公司 Information processing apparatus, information processing method, and imaging apparatus including optical microscope
US20170225680A1 (en) * 2015-05-12 2017-08-10 SZ DJI Technology Co., Ltd Apparatus and methods for obstacle detection
CN105718888A (en) * 2016-01-22 2016-06-29 北京中科慧眼科技有限公司 Obstacle prewarning method and obstacle prewarning device
WO2018058937A1 (en) * 2016-09-30 2018-04-05 深圳市镭神智能系统有限公司 Head-mount blind guiding device
CN108663681A (en) * 2018-05-16 2018-10-16 华南理工大学 Mobile Robotics Navigation method based on binocular camera Yu two-dimensional laser radar
CN109144072A (en) * 2018-09-30 2019-01-04 亿嘉和科技股份有限公司 A kind of intelligent robot barrier-avoiding method based on three-dimensional laser
KR101998298B1 (en) * 2018-12-14 2019-07-09 위고코리아 주식회사 Vehicle Autonomous Driving Method Using Camera and LiDAR Sensor
CN112799098A (en) * 2020-12-08 2021-05-14 深兰科技（上海）有限公司 Radar blind area monitoring method and device, electronic equipment and storage medium
CN112870033A (en) * 2021-01-20 2021-06-01 江西理工大学南昌校区 Intelligent blind guiding helmet system for unstructured road and navigation method
CN112784799A (en) * 2021-02-01 2021-05-11 三一机器人科技有限公司 AGV (automatic guided vehicle) backward pallet and obstacle identification method and device and AGV

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张穗华;骆云志;王钤;张春华;邓博文;: "基于三维激光雷达的障碍物检测方法研究", 机电产品开发与创新, no. 06, 28 November 2016 (2016-11-28) *
黄兴;应群伟;: "应用激光雷达与相机信息融合的障碍物识别", 计算机测量与控制, no. 01, 25 January 2020 (2020-01-25) *

Similar Documents

Publication Publication Date Title
Zhang et al. Road-segmentation-based curb detection method for self-driving via a 3D-LiDAR sensor
US8209074B2 (en) Robot and method for controlling the same
KR101207903B1 (en) Apparatus and method for providing the obstacle information of autonomous mobile vehicle
KR101395089B1 (en) System and method for detecting obstacle applying to vehicle
JP6344638B2 (en) Object detection apparatus, mobile device control system, and object detection program
US20180267548A1 (en) Route determination device, vehicle control device, route determination method, and storage medium
US9121717B1 (en) Collision avoidance for vehicle control
JPH0830770A (en) Vehicle traveling lane picture processor
JP6315308B2 (en) Control object identification device, mobile device control system, and control object recognition program
JP7194640B2 (en) VEHICLE CONTROL DEVICE, VEHICLE CONTROL METHOD, AND PROGRAM
JPWO2016104265A1 (en) Moving body
CN106880474A (en) A kind of intelligent guiding walking stick for blind person
JP2006260098A (en) Obstacle detection unit
CN112677965A (en) Vehicle control device, vehicle control method, and storage medium
JPWO2017047282A1 (en) Image processing apparatus, object recognition apparatus, device control system, image processing method and program
Li et al. A new 3D LIDAR-based lane markings recognition approach
TWI680898B (en) Light reaching detection device and method for close obstacles
CN113589323A (en) Road obstacle identification method based on height vector field
CN113589321A (en) Intelligent navigation assistant for people with visual impairment
CN112947449A (en) Anti-falling device, robot and anti-falling method
CN113703002B (en) Road condition analysis method based on laser radar measurement data
CN110546058A (en) vehicle control system, vehicle control method, and program
CN114935340A (en) Indoor navigation robot, control system and method
US20220065650A1 (en) Universal Pointing and Interacting Device for the Guidance of the Blind and Visually Impaired
US20220194416A1 (en) Vehicle control device, vehicle control method, and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination