CN116501043A - Unmanned integrated card semi-autonomous remote control obstacle avoidance control method, system and storage medium - Google Patents
Unmanned integrated card semi-autonomous remote control obstacle avoidance control method, system and storage medium Download PDFInfo
- Publication number
- CN116501043A CN116501043A CN202310411209.6A CN202310411209A CN116501043A CN 116501043 A CN116501043 A CN 116501043A CN 202310411209 A CN202310411209 A CN 202310411209A CN 116501043 A CN116501043 A CN 116501043A
- Authority
- CN
- China
- Prior art keywords
- unmanned
- remote control
- data information
- module
- card
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims abstract description 4
- 230000004927 fusion Effects 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000008439 repair process Effects 0.000 abstract description 4
- 238000011835 investigation Methods 0.000 abstract 1
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Optics & Photonics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a semi-autonomous remote control obstacle avoidance control method, a system and a storage medium for an unmanned integrated card, wherein the method comprises the following steps that S1, the unmanned integrated card is started, an on-board high-definition camera module and an on-board laser radar module are subjected to initialization detection and fault treatment, if the unmanned integrated card is normal, a step S2 is carried out, and if the unmanned integrated card is abnormal, fault investigation is prompted; s2, based on the vehicle-mounted high-definition camera module, acquiring image data information of the surrounding environment of the unmanned aerial vehicle and splicing the image data information to obtain integral image data information of the unmanned aerial vehicle, and based on the vehicle-mounted laser radar module, acquiring and splicing point cloud data information of the surrounding environment of the unmanned aerial vehicle to obtain integral point cloud data information of the unmanned aerial vehicle. The invention not only integrates the obstacle avoidance function of the automatic driving system, reduces the collision risk of manual control of the vehicle and reduces the cost of vehicle repair and maintenance of the automatic driving system, but also fully utilizes the functional module of the automatic driving system without increasing additional hardware cost.
Description
Technical Field
The invention relates to the technical field of unmanned integrated cards, in particular to a semi-autonomous remote control obstacle avoidance control method, a semi-autonomous remote control obstacle avoidance control system and a storage medium for an unmanned integrated card.
Background
With the continuous development of automatic driving automobiles, port logistics, which is one of the eight main stream scenes, is gradually developed, and the port logistics is a comprehensive multifunctional service provided by taking a port as a central node of the logistics. The port logistics activities are a part of the whole logistics system, and refer to services which take port storage services as main expression forms and integrate functions of storage, inland transportation, freight transportation agency, disassembly and assembly, loading and unloading, transportation, packaging, processing, information processing and the like.
At present, a plurality of open ports are developed for unmanned collection card test operation. The unmanned integrated card is a container transfer truck which comprises a sensing system formed by a laser radar and a high-definition camera, completes autonomous planning according to a set route and controls a vehicle to run between a shore bridge and a crane.
In the prior art, at present, in a port logistics system, an unmanned integrated card is required to move vehicles to cooperate with related work under various scenes such as development and debugging of automatic driving software, calibration of a sensing system and the like, and the unmanned integrated card is used for moving the vehicles in a manner of remote control of an unmanned room and a remote handle. The remote control transmitter is used for transmitting a remote control take-over signal, the remote control receiver is used for receiving the signal, converting the signal into a CAN signal and transmitting the CAN signal to the gateway, and analyzing the CAN signal into a control message matched with the integrated card chassis through the gateway so as to achieve the purpose of controlling the running of the vehicle. The existing remote control system technical scheme separates the remote control system from the automatic driving system, so that the unmanned integrated card only uses the remote control function defined by the whole vehicle in certain scenes needing remote control driving, and the automatic driving system does not participate in the remote control function.
Secondly, the existing remote control system technical scheme has great collision risk, because the unmanned truck is large, the visual field blind area range is wide, and the space for reserving vehicles for work at a port is small, the situation of collision with wheel cranes and containers easily occurs in the vehicle remote control process. Not only causes the damage of hardware, but also increases the burden of technicians.
Disclosure of Invention
In view of the defects in the prior art, the invention provides the unmanned integrated card semi-autonomous remote control obstacle avoidance control method, the unmanned integrated card semi-autonomous remote control obstacle avoidance control system and the storage medium, which not only integrate the obstacle avoidance function of an automatic driving system, reduce the collision risk of manual control of a vehicle and reduce the cost of vehicle repair and automatic driving system maintenance, but also fully utilize the functional module of the automatic driving system without increasing additional hardware cost.
In order to achieve the above object and other related objects, the present invention provides the following technical solutions:
an unmanned integrated card semi-autonomous remote control obstacle avoidance control method, comprising the following steps:
s1, starting an unmanned integrated card, carrying out initialization detection and fault processing on a vehicle-mounted high-definition camera module and a vehicle-mounted laser radar module, if the vehicle-mounted high-definition camera module and the vehicle-mounted laser radar module are normal, entering a step S2, and if the vehicle-mounted high-definition camera module and the vehicle-mounted laser radar module are abnormal, prompting fault detection;
s2, acquiring and splicing image data information of the surrounding environment of the unmanned aerial vehicle collector card in real time based on the vehicle-mounted high-definition camera module to obtain integral image data information of the unmanned aerial vehicle collector card, and acquiring and splicing point cloud data information of the surrounding environment of the unmanned aerial vehicle collector card based on the vehicle-mounted laser radar module to obtain integral point cloud data information of the unmanned aerial vehicle collector card;
s3, based on the overall image data information of the unmanned set card and the overall point cloud data information of the unmanned set card, carrying out data fusion processing by adopting a Dempster algorithm, and outputting fusion data information;
s4, inputting the fused data information into a neural network to train and learn an obstacle model, and obtaining data information of the obstacle;
s5, based on the data information of the obstacle, adopting RRT * The algorithm performs path optimization processing to obtain optimal path data information, and outputs control data information of the real-time coupling remote control system to the unmanned set cardControl data information of (a).
Further, in step S3, the Dempster algorithm includes:
s31, constructing an image semantic segmentation set A= { TA, TB, TC } based on the whole image data information of the unmanned set card, wherein TA represents color semantics, TB represents texture semantics, TC represents shape semantics, constructing a point cloud feature set B= { QA, QB, QC, QD } based on the whole point cloud data information of the unmanned set card, QA represents illumination intensity features, QB represents category label features, QC represents normal vector features, QD represents gray value features, and fusing the image semantic segmentation set A and the point cloud feature set B to obtain an identification frame set R= { TA, TB, TC, QA, QB, QC, QD };
s32, defining a corresponding mass function, m based on the identification frame set R 1 (TA)=k 1 ,m 2 (TB)=k 2 ,m 3 (TC)=k 3 ,
m 4 (QA)=k 4 ,m 5 (QB)=k 5 ,m 6 (QC)=k 6 ,
S33, based on the corresponding mass function, carrying out data fusion to obtain a fusion matrix L,
,
wherein L=TA n, TB n, TC n, QA n, QB n, QD n, h is a normalization factor;
s34, carrying out characteristic operation and analysis on the fusion matrix L, and outputting fusion data information.
Further, in step S33, the normalization factor h is:
further, in step S32,
m 1 (TA)+m 2 (TB)+m 3 (TC)+m 4 (QA)+m 5 (QB)+m 6 (QC)+m 7 (QD)=1。
further, the obstacle model includes feature matrix data information and obstacle type matrix data information of the obstacle.
Further, in step S5, the RRT * The algorithm comprises the following steps:
s51, acquiring data information of an obstacle, taking the current position of an unmanned set card as an initial node, and setting a preset step length and a preset traversal range;
s52, traversing the data information of the obstacle based on the preset step length and the preset traversal range to obtain a second node, wherein a connecting line between the second node and the initial node has no intersection point with the obstacle;
s53, based on the second node, according to the preset step length and the preset traversing range, obtaining a third node, and sequentially traversing until the second node exceeds the preset traversing range, wherein the obtained route track is the optimal path data information.
To achieve the above and other related objects, the present invention further provides an unmanned set card semi-autonomous remote control obstacle avoidance control system, the system comprising:
remote control system: the method comprises the steps of sending speed and direction signals, and enabling the remote control unmanned integrated card to run, wherein the remote control unmanned integrated card comprises a remote control transmitter and a remote control receiver;
and a perception module: sensing the surrounding environment of the unmanned integrated card by using the high-definition camera module and the laser radar module to obtain camera image data and radar point cloud data;
obstacle avoidance module: accessing sensor data of a sensing module, splicing high-definition camera image data to form 360 images of the unmanned integrated card, splicing laser radar point cloud data to form surrounding environment data of the unmanned integrated card, fusing the two sensing data, fully learning a sensing system, and obtaining accurate obstacle information;
and a planning module: according to signals of the remote control system and the obstacle avoidance module, a running track of the unmanned integrated card during remote control is pre-planned, the distance of the obstacle is judged, and a speed and direction signal is issued to the control system in time;
and the control module is used for: and analyzing the speed and direction signals of the planning module and forwarding the speed and direction signals to the chassis system.
Further, the remote control system comprises a remote control transmitter and a remote control receiver, wherein the remote control transmitter is connected with the remote control receiver through PWM waveform signals.
Further, the remote control system is connected with the planning module, the planning module is connected with the sensing module, the obstacle avoidance module and the control module, and the control module is connected with the chassis system.
To achieve the above and other related objects, the present invention also provides a computer-readable storage medium having stored thereon a computer program programmed or configured to perform the unmanned set card semi-autonomous remote obstacle avoidance control method of any one of the above.
The invention has the following positive effects:
1. the invention combines the obstacle avoidance function of the automatic driving system, reduces the collision risk of manual control of the vehicle, and reduces the cost of vehicle repair and maintenance of the automatic driving system.
2. The invention is based on the existing vehicle resources, fully utilizes the function module of the automatic driving system, and does not increase extra hardware cost.
3. According to the invention, complete data information is obtained through image data splicing and point cloud data splicing, and the complete data information is fused through a Dempster algorithm, so that the accuracy of identifying the obstacle is improved, and the driving path of the unmanned integrated card is planned by combining control data sent by a remote control system, so that the driving safety of the unmanned integrated card is further ensured.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of a system framework according to the present invention.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Example 1: as shown in fig. 1, a semi-autonomous remote control obstacle avoidance control method for an unmanned integrated circuit card includes:
s1, starting an unmanned integrated card, carrying out initialization detection and fault processing on a vehicle-mounted high-definition camera module and a vehicle-mounted laser radar module, if the vehicle-mounted high-definition camera module and the vehicle-mounted laser radar module are normal, entering a step S2, and if the vehicle-mounted high-definition camera module and the vehicle-mounted laser radar module are abnormal, prompting fault detection;
s2, acquiring and splicing image data information of the surrounding environment of the unmanned aerial vehicle collector card in real time based on the vehicle-mounted high-definition camera module to obtain integral image data information of the unmanned aerial vehicle collector card, and acquiring and splicing point cloud data information of the surrounding environment of the unmanned aerial vehicle collector card based on the vehicle-mounted laser radar module to obtain integral point cloud data information of the unmanned aerial vehicle collector card;
s3, based on the overall image data information of the unmanned set card and the overall point cloud data information of the unmanned set card, carrying out data fusion processing by adopting a Dempster algorithm, and outputting fusion data information;
s4, inputting the fused data information into a neural network to train and learn an obstacle model, and obtaining data information of the obstacle;
s5, based on the data information of the obstacle, adopting RRT * And carrying out path optimization processing by the algorithm to obtain optimal path data information, coupling control data information of the remote control system in real time, and outputting control data information of the unmanned set card.
In this embodiment, in step S3, the Dempster algorithm includes:
s31, constructing an image semantic segmentation set A= { TA, TB, TC } based on the whole image data information of the unmanned set card, wherein TA represents color semantics, TB represents texture semantics, TC represents shape semantics, constructing a point cloud feature set B= { QA, QB, QC, QD } based on the whole point cloud data information of the unmanned set card, QA represents illumination intensity features, QB represents category label features, QC represents normal vector features, QD represents gray value features, and fusing the image semantic segmentation set A and the point cloud feature set B to obtain an identification frame set R= { TA, TB, TC, QA, QB, QC, QD };
s32, defining a corresponding mass function, m based on the identification frame set R 1 (TA)=k 1 ,m 2 (TB)=k 2 ,m 3 (TC)=k 3 ,
m 4 (QA)=k 4 ,m 5 (QB)=k 5 ,m 6 (QC)=k 6 ,
S33, based on the corresponding mass function, carrying out data fusion to obtain a fusion matrix L,
,
wherein L=TA n, TB n, TC n, QA n, QB n, QD n, h is a normalization factor;
s34, carrying out characteristic operation and analysis on the fusion matrix L, and outputting fusion data information.
In this embodiment, in step S33, the normalization factor h is:
in the present embodiment, in step S32,
m 1 (TA)+m 2 (TB)+m 3 (TC)+m 4 (QA)+m 5 (QB)+m 6 (QC)+m 7 (QD)=1。
in this embodiment, the obstacle model includes feature matrix data information and obstacle type matrix data information of the obstacle.
In this embodiment, in step S5, the RRT * The algorithm comprises the following steps:
s51, acquiring data information of an obstacle, taking the current position of an unmanned set card as an initial node, and setting a preset step length and a preset traversal range;
s52, traversing the data information of the obstacle based on the preset step length and the preset traversal range to obtain a second node, wherein a connecting line between the second node and the initial node has no intersection point with the obstacle;
s53, based on the second node, according to the preset step length and the preset traversing range, obtaining a third node, and sequentially traversing until the second node exceeds the preset traversing range, wherein the obtained route track is the optimal path data information.
Example 2: the invention is further illustrated and described below based on an unmanned integrated card semi-autonomous remote obstacle avoidance control method in embodiment 1.
As shown in fig. 2, an unmanned integrated card semi-autonomous remote control obstacle avoidance control system, the system comprises:
remote control system: the method comprises the steps of sending speed and direction signals, and enabling the remote control unmanned integrated card to run, wherein the remote control unmanned integrated card comprises a remote control transmitter and a remote control receiver;
and a perception module: sensing the surrounding environment of the unmanned integrated card by using the high-definition camera module and the laser radar module to obtain camera image data and radar point cloud data;
obstacle avoidance module: accessing sensor data of a sensing module, splicing high-definition camera image data to form 360 images of the unmanned integrated card, splicing laser radar point cloud data to form surrounding environment data of the unmanned integrated card, fusing the two sensing data, fully learning a sensing system, and obtaining accurate obstacle information;
and a planning module: according to signals of the remote control system and the obstacle avoidance module, a running track of the unmanned integrated card during remote control is pre-planned, the distance of the obstacle is judged, and a speed and direction signal is issued to the control system in time;
and the control module is used for: and analyzing the speed and direction signals of the planning module and forwarding the speed and direction signals to the chassis system.
In this embodiment, the remote control system includes a remote control transmitter and a remote control receiver, and the remote control transmitter is connected to the remote control receiver through a PWM waveform signal.
In this embodiment, the remote control system is connected to the planning module, the planning module is connected to the sensing module, the obstacle avoidance module, and the control module is connected to the chassis system.
In the embodiment, firstly, according to 360 images of an unmanned integrated card displayed by a remote control transmitter, observing the surrounding situation of a vehicle, sending PWM waveform signals such as gear, speed, direction and the like to a remote control receiver, and then converting the received waveform signals into CAN signals by the remote control receiver to be sent to an automatic driving system; secondly, the automatic driving system sends the surrounding environment to the obstacle avoidance module through the sensing module, the obstacle avoidance module forms corresponding obstacle information and sends the corresponding obstacle information to the planning module, the planning module fuses control information such as the speed and the direction of the remote control module and the obstacle information of the obstacle avoidance module, the optimal driving route of the unmanned collection card is judged, and the judged speed and direction signals are sent to the control module; and finally, the control module converts the analyzed speed and direction signals into CAN signals and sends the CAN signals to the chassis system. Therefore, the technical scheme of semi-autonomous remote control obstacle avoidance is realized.
To achieve the above and other related objects, the present invention also provides a computer-readable storage medium having stored thereon a computer program programmed or configured to perform the unmanned set card semi-autonomous remote obstacle avoidance control method of any one of the above.
Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
In summary, the invention not only integrates the obstacle avoidance function of the automatic driving system, reduces the collision risk of manual control of the vehicle and reduces the cost of vehicle repair and maintenance of the automatic driving system, but also fully utilizes the functional module of the automatic driving system without increasing additional hardware cost.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (10)
1. The unmanned integrated card semi-autonomous remote control obstacle avoidance control method is characterized by comprising the following steps of:
s1, starting an unmanned integrated card, carrying out initialization detection and fault processing on a vehicle-mounted high-definition camera module and a vehicle-mounted laser radar module, if the vehicle-mounted high-definition camera module and the vehicle-mounted laser radar module are normal, entering a step S2, and if the vehicle-mounted high-definition camera module and the vehicle-mounted laser radar module are abnormal, prompting fault detection;
s2, acquiring and splicing image data information of the surrounding environment of the unmanned aerial vehicle collector card in real time based on the vehicle-mounted high-definition camera module to obtain integral image data information of the unmanned aerial vehicle collector card, and acquiring and splicing point cloud data information of the surrounding environment of the unmanned aerial vehicle collector card based on the vehicle-mounted laser radar module to obtain integral point cloud data information of the unmanned aerial vehicle collector card;
s3, based on the overall image data information of the unmanned set card and the overall point cloud data information of the unmanned set card, carrying out data fusion processing by adopting a Dempster algorithm, and outputting fusion data information;
s4, inputting the fused data information into a neural network to train and learn an obstacle model, and obtaining data information of the obstacle;
s5, based on the data information of the obstacle, adopting RRT * And carrying out path optimization processing by the algorithm to obtain optimal path data information, coupling control data information of the remote control system in real time, and outputting control data information of the unmanned set card.
2. The unmanned integrated card semi-autonomous remote control obstacle avoidance control method of claim 1, wherein in step S3, the Dempster algorithm comprises:
s31, constructing an image semantic segmentation set A= { TA, TB, TC } based on the whole image data information of the unmanned set card, wherein TA represents color semantics, TB represents texture semantics, TC represents shape semantics, constructing a point cloud feature set B= { QA, QB, QC, QD } based on the whole point cloud data information of the unmanned set card, QA represents illumination intensity features, QB represents category label features, QC represents normal vector features, QD represents gray value features, and fusing the image semantic segmentation set A and the point cloud feature set B to obtain an identification frame set R= { TA, TB, TC, QA, QB, QC, QD };
s32, defining a corresponding mass function based on the identification frame set R,
m 1 (TA)=k 1 ,m 2 (TB)=k 2 ,m 3 (TC)=k 3 ,
m 4 (QA)=k 4 ,m 5 (QB)=k 5 ,m 6 (QC)=k 6 ,
s33, based on the corresponding mass function, carrying out data fusion to obtain a fusion matrix L
,
Wherein L=TA n, TB n, TC n, QA n, QB n, QD n, h is a normalization factor;
s34, carrying out characteristic operation and analysis on the fusion matrix L, and outputting fusion data information.
3. The unmanned integrated card semi-autonomous remote control obstacle avoidance control method according to claim 2, wherein in step S33, the normalization factor h is:
4. the unmanned integrated card semi-autonomous remote control obstacle avoidance control method of claim 2, wherein, in step S32,
m 1 (TA)+m 2 (TB)+m 3 (TC)+m 4 (QA)+m 5 (QB)+m 6 (QC)+m 7 (QD)=1。
5. the unmanned set card semi-autonomous remote control obstacle avoidance control method according to claim 1, wherein the method comprises the following steps: the obstacle model includes feature matrix data information and obstacle type matrix data information of an obstacle.
6. The unmanned integrated circuit card semi-autonomous remote control obstacle avoidance control method according to claim 1, wherein in step S5, the RRT * The algorithm comprises the following steps:
s51, acquiring data information of an obstacle, taking the current position of an unmanned set card as an initial node, and setting a preset step length and a preset traversal range;
s52, traversing the data information of the obstacle based on the preset step length and the preset traversal range to obtain a second node, wherein a connecting line between the second node and the initial node has no intersection point with the obstacle;
s53, based on the second node, according to the preset step length and the preset traversing range, obtaining a third node, and sequentially traversing until the second node exceeds the preset traversing range, wherein the obtained route track is the optimal path data information.
7. An unmanned integrated card semi-autonomous remote control obstacle avoidance control system, the system comprising:
remote control system: the method comprises the steps of sending speed and direction signals, and enabling the remote control unmanned integrated card to run, wherein the remote control unmanned integrated card comprises a remote control transmitter and a remote control receiver;
and a perception module: sensing the surrounding environment of the unmanned integrated card by using the high-definition camera module and the laser radar module to obtain camera image data and radar point cloud data;
obstacle avoidance module: accessing sensor data of a sensing module, splicing high-definition camera image data to form 360 images of the unmanned integrated card, splicing laser radar point cloud data to form surrounding environment data of the unmanned integrated card, fusing the two sensing data, fully learning a sensing system, and obtaining accurate obstacle information;
and a planning module: according to signals of the remote control system and the obstacle avoidance module, a running track of the unmanned integrated card during remote control is pre-planned, the distance of the obstacle is judged, and a speed and direction signal is issued to the control system in time;
and the control module is used for: and analyzing the speed and direction signals of the planning module and forwarding the speed and direction signals to the chassis system.
8. The unmanned set card semi-autonomous remote control obstacle avoidance control system of claim 7, wherein: the remote control system comprises a remote control transmitter and a remote control receiver, and the remote control transmitter is connected with the remote control receiver through PWM waveform signals.
9. The unmanned set card semi-autonomous remote control obstacle avoidance control system of claim 7, wherein: the remote control system is connected with the planning module, the planning module is connected with the sensing module, the obstacle avoidance module and the control module, and the control module is connected with the chassis system.
10. A computer readable storage medium having stored thereon a computer program programmed or configured to perform the unmanned cluster card semi-autonomous remote obstacle avoidance control method of any of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310411209.6A CN116501043A (en) | 2023-04-14 | 2023-04-14 | Unmanned integrated card semi-autonomous remote control obstacle avoidance control method, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310411209.6A CN116501043A (en) | 2023-04-14 | 2023-04-14 | Unmanned integrated card semi-autonomous remote control obstacle avoidance control method, system and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116501043A true CN116501043A (en) | 2023-07-28 |
Family
ID=87325864
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310411209.6A Pending CN116501043A (en) | 2023-04-14 | 2023-04-14 | Unmanned integrated card semi-autonomous remote control obstacle avoidance control method, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116501043A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117539268A (en) * | 2024-01-09 | 2024-02-09 | 吉林省吉邦自动化科技有限公司 | VGA autonomous obstacle avoidance system based on fusion of machine vision and laser radar |
-
2023
- 2023-04-14 CN CN202310411209.6A patent/CN116501043A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117539268A (en) * | 2024-01-09 | 2024-02-09 | 吉林省吉邦自动化科技有限公司 | VGA autonomous obstacle avoidance system based on fusion of machine vision and laser radar |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11854181B2 (en) | Systems and methods for utilizing machine-assisted vehicle inspection to identify insurance buildup or fraud | |
US10860896B2 (en) | FPGA device for image classification | |
US20210117787A1 (en) | Method for determining a quality grade of data sets of sensors | |
CN106926800A (en) | The vehicle-mounted visually-perceptible system of multi-cam adaptation | |
CN113223317B (en) | Method, device and equipment for updating map | |
CN106154834A (en) | For the method and apparatus controlling automatic driving vehicle | |
US20230350979A1 (en) | Generating fused sensor data through metadata association | |
US20190228240A1 (en) | Method for detecting garage parking spaces | |
CN116501043A (en) | Unmanned integrated card semi-autonomous remote control obstacle avoidance control method, system and storage medium | |
CN110796104A (en) | Target detection method and device, storage medium and unmanned aerial vehicle | |
US20210237737A1 (en) | Method for Determining a Lane Change Indication of a Vehicle | |
US11645775B1 (en) | Methods and apparatus for depth estimation on a non-flat road with stereo-assisted monocular camera in a vehicle | |
CN114379544A (en) | Automatic parking system, method and device based on multi-sensor pre-fusion | |
US11429757B2 (en) | Sensor calibration via extrinsic scanning | |
CN117382675A (en) | Method, device, vehicle and storage medium for generating drivable area of road | |
US11591012B2 (en) | Vehicle trajectory prediction using road topology and traffic participant object states | |
CN111739332B (en) | Parking lot management system | |
US20240020623A1 (en) | Multi-tiered transportation identification system | |
US20220270356A1 (en) | Platform for perception system development for automated driving system | |
Brenner et al. | Requirements of Automated Vehicles and Depots for the Initial Step of Automated Public Transport | |
CN109278861B (en) | Steering wheel return-to-normal reminding method and system based on automobile look-around | |
CN118072512A (en) | L4 vehicle-based unmanned bus station early warning method, system and medium | |
US11961309B2 (en) | Vehicle and control method thereof | |
US20210061285A1 (en) | Method for generating a reference representation | |
EP4262196A1 (en) | Image map generating systems and methods |
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 |