CN115027506B - Logistics luggage tractor driving control system and method - Google Patents
Logistics luggage tractor driving control system and method Download PDFInfo
- Publication number
- CN115027506B CN115027506B CN202210967876.8A CN202210967876A CN115027506B CN 115027506 B CN115027506 B CN 115027506B CN 202210967876 A CN202210967876 A CN 202210967876A CN 115027506 B CN115027506 B CN 115027506B
- Authority
- CN
- China
- Prior art keywords
- luggage
- logistics
- driving
- tractor
- carriage
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000012423 maintenance Methods 0.000 claims abstract description 16
- 230000008447 perception Effects 0.000 claims description 23
- 230000007613 environmental effect Effects 0.000 claims description 12
- 230000010006 flight Effects 0.000 claims description 11
- 230000001276 controlling effect Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 238000005299 abrasion Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000033001 locomotion Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000004148 unit process Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims 1
- 238000007405 data analysis Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 4
- 230000009471 action Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000003137 locomotive effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- 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
Abstract
The invention discloses a system and a method for controlling the driving of a logistics luggage tractor, and belongs to the technical field of the driving safety control of the logistics luggage tractor. The system comprises a driving order module, a route processing module, a safety prediction module and a scheduling module; the output end of the driving list arranging module is connected with the input end of the route processing module; the output end of the route processing module is connected with the input end of the safety prediction module; the output end of the safety prediction module is connected with the input end of the scheduling module. The invention also provides a driving control method, which can plan the driving route of the logistics luggage tractor in an airport environment, prompt and process complex traffic scenes, construct a prediction model according to different loads and tractions, and enable the mean square error of the predicted articulated car coupler wear value of each carriage to be within a constant range according to scheduling and scheduling lists, so as to generate uniform maintenance time and meet driving safety control.
Description
Technical Field
The invention relates to the technical field of logistics luggage tractor driving safety control, in particular to a logistics luggage tractor driving control system and a method.
Background
Commodity circulation luggage tractor is an instrument of using commonly used at airport luggage transport, along with the development of science and technology and economy, unmanned commodity circulation luggage tractor has gradually gone into market, and unmanned commodity circulation luggage tractor is exactly to be the general large-scale freight train or the semitrailer that pulls with articulated coupling between locomotive and the carriage, and there is the locomotive of driving capability in the front to call the tractor, does not pull the carriage of the car of driving capability at the back and calls the tractor, and the carriage is dragged away by the tractor. In general, the tractor adopts a full-trailer mode, namely, the front end of the carriage is connected with the rear end of the tractor, and the tractor only provides forward pulling force to drag the trailer to move, but does not bear the downward weight of the trailer.
The main problem of an unmanned logistics luggage tractor facing in an airport is planning and ordering of routes, the obstacle avoidance is realized by acquiring surrounding data through different environment sensing capabilities, and meanwhile, under the condition that different luggage dragging is considered, the bearing force of each carriage gives abrasion pressure to an articulated coupler in a complex traffic scene, so that a driving safety control system can be established, and the problem to be solved urgently is always solved.
Disclosure of Invention
The present invention provides a system and a method for controlling driving of a baggage tractor, so as to solve the problems of the background art.
In order to solve the technical problems, the invention provides the following technical scheme:
a logistics baggage tractor driving control method, the method comprising the steps of:
s1, obtaining airport flight lists, obtaining passenger data of each flight, wherein the passenger data comprise the number data of luggage in a flight luggage compartment, and constructing a logistics luggage tractor list;
s2, obtaining the destination of automatic driving of the logistics luggage tractor under the airport flight, and constructing an automatic driving route by using a sensing system algorithm and a planning system algorithm;
s3, obtaining predicted load information of each carriage on the logistics luggage tractor, obtaining the number of turning points of the route according to the automatic driving route, constructing a driving safety prediction model, and generating a predicted articulated coupler wear value of each carriage;
s4, obtaining the current articulated coupler wear value of each carriage, constructing a dispatching model, and adjusting carriage numbers to enable the mean square error of the predicted articulated coupler wear value of each carriage to be in a constant range
In the interior of said container body,
and the range is preset for the system, and the unified maintenance time is generated, so that the driving safety control is met.
According to the above technical scheme, construct commodity circulation luggage tractor row list and include:
obtaining an airport flight scheduling list which comprises time points of arrival of all flights at an airport;
acquiring passenger data of each airport flight, acquiring data of luggage stored by passengers from the passenger data, and generating luggage quantity data in a flight luggage compartment;
and constructing a logistics luggage tractor row list according to the luggage quantity data in the luggage compartment of each airport flight and the arrival time point of the luggage compartment at the airport, wherein the logistics luggage tractor row list comprises the compartment quantity and the arrival time of the logistics luggage tractor.
According to the above technical solution, the constructing an automatic driving route includes:
generating a driving area and a route identification of the automatic driving route by using a perception system algorithm;
processing the environmental data obtained according to the plurality of laser radars to form elevation data in a perception environmental area; the classified vehicle speed control on different scales is realized on the road section with the complex shape; classifying the fluctuating road sections by using local features of different scales;
the perception system algorithm is also used for providing the functions of road marking identification, traffic sign identification and vehicle and pedestrian detection;
generating a route track of an automatic driving route and control under a complex traffic scene by using a planning system algorithm;
classifying the driving area according to a planning system algorithm, analyzing a classification result through multi-frame data, generating a road area in the driving area, and finding out moving obstacles; controlling the logistics luggage tractor to be capable of driving along the central line of the road, and generating a plurality of drivable routes in a state space according to the positions of the starting point and the target point of the vehicle; determining a plurality of necessary passing points required in a driving mode according to the generated road area, and autonomously generating a movable track;
the planning system algorithm also provides control under complex traffic scenes including turns, intersections and T-shaped intersections, and the logistics luggage tractor generates turn prompts when recognizing the complex traffic scenes.
According to the technical scheme, the construction of the driving safety prediction model comprises the following steps:
obtaining the quantity data of the luggage in the luggage compartment of any airport flight, and numbering the luggage in the luggage compartment from small to large, wherein the numbering mode is based on the sequence close to the exit of the luggage compartment or contacting with the conveyor belt, for example, two pieces of luggage lean against the exit of the luggage compartment, the luggage above is marked as 1, the luggage below is marked as 2, because the luggage above is firstly placed on the conveyor belt when the conveyor belt is transported, and the like;
obtaining the predicted load information of each carriage on the logistics luggage tractor, wherein the calculation of the predicted load information comprises the following steps:
；
；
wherein, the first and the second end of the pipe are connected with each other,
represents taking the minimum value greater than 0;
representing the carriage bearing area;
respectively represent
The maximum footprint of a piece of luggage (the maximum footprint here refers to the maximum usable area of the piece of luggage, for example, an inverted trapezoidal piece with a bottom area of 30 and a top surface area of 40, the top surface area of which is taken as the maximum footprint);
is represented in
When the minimum value which is larger than 0 is obtained, the value of n is obtained;
representing the advance of any car x on a logistic baggage tractorMeasuring load information;
representing the self weight information of the logistics luggage tractor;
respectively correspond to
Weight information of the piece of luggage;
obtaining the number of turning points of the route according to the automatic driving route, and constructing a driving safety prediction model:
(ii) a Wherein the content of the first and second substances,
representing a predicted articulated coupler wear value at the xth car;
representing the number of turning points on the autonomous driving route;
representing a cornering coefficient of wear;
representing the total number of logistics luggage tractor compartments required by airport flights corresponding to the automatic driving routes;
constructing a time period T, since airport flights typically take two to three hours, or more, for a shift; and acquiring the predicted articulated coupler wear value of each carriage of the logistics luggage tractor under each airport flight in the time period T, and outputting the articulated coupler wear value to the scheduling module.
According to the above technical solution, the scheduling model includes:
acquiring the airport pickup time of the logistics luggage tractor in a time period T;
on the premise of not causing time coincidence, deploying airport flights of which all carriages participate in transportation and allocating the serial numbers of all carriages;
the allocation of each carriage number meets the following conditions:
constructing the sum of the wear values of the predicted articulated couplers in all the transportation times of the same carriage in the time period T, recording the sum data of the wear values of the predicted articulated couplers of all the carriages into a set C, and meeting the condition that the mean square deviation of the data in the set C is in a constant range
Internal;
and setting an articulated coupler wear value threshold, and generating uniform maintenance time when the average value of the data in the set C exceeds the threshold, and outputting the uniform maintenance time to an administrator port.
A logistics luggage tractor driving control system comprises a driving list arranging module, a route processing module, a safety prediction module and a scheduling module;
the driving list module is used for acquiring flight lists of an airport, acquiring passenger data of each flight, wherein the passenger data comprises the luggage quantity data in a flight luggage cabin, and constructing a logistics luggage tractor list; the route processing module is used for acquiring the destination of the automatic driving of the logistics luggage tractor under the airport flight, and constructing an automatic driving route by using a sensing system algorithm and a planning system algorithm; the safety prediction module is used for acquiring the predicted load information of each carriage on the logistics luggage tractor, acquiring the number of turning points of a route according to an automatic driving route, constructing a driving safety prediction model and generating a predicted articulated coupler wear value of each carriage; the dispatching module is used for obtaining the current articulated car coupler abrasion value of each carriage, constructing a dispatching model and regulating carriage numbers to ensure that the mean square error of the predicted articulated car coupler abrasion value of each carriage is in a constant range
Generating uniform maintenance time to meet driving safety control;
the output end of the driving list arranging module is connected with the input end of the route processing module; the output end of the route processing module is connected with the input end of the safety prediction module; the output end of the safety prediction module is connected with the input end of the scheduling module.
According to the technical scheme, the driving list arranging module comprises a flight information acquisition unit and a logistics luggage tractor list arranging unit;
the flight information acquisition unit is used for acquiring an airport flight list, acquiring passenger data of each flight, selecting data of passengers for storing luggage from the passenger data, and constructing the luggage quantity data in the luggage compartment under each flight; the logistics luggage tractor ordering unit is used for generating the number of carriages and ordering time required by the logistics luggage tractor according to the luggage quantity data in the luggage cabin of each flight;
the output end of the flight information acquisition unit is connected with the input end of the logistics luggage tractor list arranging unit; and the output end of the logistics luggage tractor list arranging unit is connected with the input end of the route processing module.
According to the technical scheme, the route processing module comprises a perception planning unit and a system planning unit;
the sensing planning unit processes the environmental data obtained by the plurality of laser radars by using a sensing system algorithm to form elevation data in a sensing environmental area; by utilizing multiple observations, the data validity is improved, and errors caused by vehicle attitude and terrain changes are avoided. The classified vehicle speed control on different scales is realized on the road section with the complex shape; classifying the fluctuating road sections by using local features of different scales;
the perception planning unit also provides the functions of road marking identification, traffic sign identification and vehicle and pedestrian detection;
for example, when the curvature of the central line of the lane of the road changes linearly along with the arc length of the lane, a simplified road model is established to verify the driving precision of the track; extracting corresponding features, and performing feature fusion and feature selection by using deep learning and machine learning features; converting the maximum posterior probability estimation into an optimal estimation problem of road model parameters; detecting the traffic signs by utilizing deep learning and machine learning characteristics; carrying out traffic sign identification by utilizing more detailed characteristics; the method utilizes deep learning and machine learning characteristics to detect the target of the pedestrian and the vehicle, and has the function of tracking the track change of the vehicle and the pedestrian;
the system planning unit is used for classifying the driving area according to a planning system algorithm, analyzing a classification result through multi-frame data, generating a road area in the driving area and finding out a moving obstacle; controlling the logistics luggage tractor to be capable of driving along the central line of the road, and generating a plurality of drivable routes in a state space according to the positions of the starting point and the target point of the vehicle; determining a plurality of necessary road points required in a driving mode according to the generated road area, and autonomously generating a movable motion track;
the system planning unit also provides control under a complex traffic scene, the complex traffic scene comprises a turn, a crossroad and a T-shaped intersection, and the logistics luggage tractor generates a turn prompt when recognizing the complex traffic scene;
and constructing an automatic driving route of the logistics luggage tractor according to output results of the perception planning unit and the system planning unit.
According to the technical scheme, the safety prediction module comprises a carriage information acquisition unit and a safety prediction unit;
the compartment information acquisition unit is used for acquiring the predicted load information of each compartment on the logistics luggage tractor; the safety prediction unit is used for acquiring the number of turning points of the route according to the automatic driving route, constructing a driving safety prediction model and generating a predicted articulated coupler wear value of each carriage;
the output end of the carriage information acquisition unit is connected with the input end of the safety prediction unit; and the output end of the safety prediction unit is connected with the input end of the scheduling module.
According to the technical scheme, the scheduling module comprises a model building unit and an adjusting unit;
the model construction unit is used for obtaining eachConstructing a dispatching model according to the current articulated coupler abrasion value of the coupling compartment; the adjusting unit is used for adjusting the carriage numbers so that the mean square error of the predicted articulated coupler wear value of each carriage is in a constant range
In the method, uniform maintenance time is generated to meet driving safety control;
the output end of the model building unit is connected with the input end of the adjusting unit.
Compared with the prior art, the invention has the following beneficial effects:
the method can plan the driving route of the logistics luggage tractor in an airport environment, prompt complex traffic scenes, construct a prediction model according to different loads and tractions, realize the wear prediction of the carriage articulated coupler of the logistics luggage tractor, ensure that the mean square error of the predicted articulated coupler wear value of each carriage is in a constant range according to scheduling lists, generate uniform maintenance time and meet driving safety control.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flow chart of a logistic baggage tractor driving control system and method of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, in the present embodiment:
the first embodiment is as follows:
the automatic driving method of the logistics luggage tractor comprises the following steps:
constructing the logistics baggage tractor volleyball includes:
obtaining an airport flight scheduling list which comprises time points of arrival of all flights at an airport;
acquiring passenger data of each airport flight, acquiring data of passengers storing luggage in the passenger data, and generating luggage quantity data in a flight luggage cabin;
and constructing a logistics luggage tractor row list according to the luggage quantity data in the luggage compartment of each airport flight and the arrival time point of the luggage compartment at the airport, wherein the logistics luggage tractor row list comprises the compartment quantity and the arrival time of the logistics luggage tractor.
Constructing an automatic driving route includes:
generating a driving area and a route identification of the autonomous driving route by using a perception system algorithm;
processing the environmental data obtained by the plurality of laser radars to form elevation data in a perception environmental area; the classified vehicle speed control on different scales is realized on the road section with the complex shape; classifying the fluctuating road sections by using local features of different scales;
for example, an RS-Ruby (a 128-line laser radar from Itanium poly-creation, with a vertical angle resolution of 0.1 degrees and a ranging capability of 200 m and 10% reflectivity) is arranged on the roof of the vehicle and used for sensing the middle and long distances of 360 degrees; four RS-BPearl (a short-distance blind-supplementary laser radar from the surging and gathering initiative, having an ultra-wide angle of view of 360 ° × 90 °) are respectively installed around the vehicle body, and the short-distance blind areas are covered by the ultra-wide angle of view.
Or by using Horizon (laser radar from non-repetitive scanning in wonhois bound of university in Xinjiang), the Horizon is a similar rectangular field angle, the FOV is equal to 81.7 degrees multiplied by 25.1 degrees, and by adopting the laser radar in a transverse scanning mode, the 360-degree full-field coverage can be realized by carrying five horizons. In this embodiment, a Horizon may be installed at each of the left, middle, and right parts of the front of the vehicle for sensing the left, front, and right environmental information, and a Horizon may be installed at each of the left and right parts of the rear of the vehicle for sensing the left, rear, and right environmental information. Full coverage of 360 ° is achieved by five lidar beams with horizontal field angles of 81.7 °.
The perception system algorithm is also used for providing the functions of road marking identification, traffic sign identification and vehicle and pedestrian detection;
generating a route track of an automatic driving route and control under a complex traffic scene by using a planning system algorithm;
classifying the driving area according to a planning system algorithm, analyzing a classification result through multi-frame data, generating a road area in the driving area, and finding out a moving obstacle; controlling the logistics luggage tractor to be capable of driving along the central line of the road, and generating a plurality of drivable routes in a state space according to the positions of the starting point and the target point of the vehicle; determining a plurality of necessary passing points required in a driving mode according to the generated road area, and autonomously generating a movable track;
for example, by using the D × lite algorithm, a reverse search is performed in a given map set to find an optimal path. In the process of approaching the target point, the occurrence of the dynamic obstacle point is dealt with by searching in a local range. The algorithm has the advantages that the path search of each point is finished, when an obstacle point is encountered and the approximation cannot be continuously carried out according to the original path, the data obtained through incremental search is reused to directly re-plan an optimal path at the current position which is hindered, and then the algorithm continues to advance.
The planning system algorithm also provides control under a complex traffic scene, the complex traffic scene comprises a turn, a crossroad and a T-shaped intersection, and when the logistics luggage tractor identifies the complex traffic scene, the logistics luggage tractor records a turn point and generates a turn prompt.
The construction of the driving safety prediction model comprises the following steps:
obtaining the quantity data of the luggage in the luggage compartment of any airport flight, numbering the luggage in the luggage compartment from small to large, wherein the numbering mode takes the sequence close to the exit of the luggage compartment or contacting with a conveyor belt as a reference;
obtaining the predicted load information of each compartment on the logistics luggage tractor, wherein the calculation of the predicted load information comprises the following steps:
；
；
wherein, the first and the second end of the pipe are connected with each other,
representing taking a minimum value greater than 0;
representing the carriage bearing area;
respectively represent
The maximum footprint of the piece of luggage;
is represented in
When the minimum value which is larger than 0 is obtained, the value of n is obtained;
representing the predicted load information of any carriage x on the logistics baggage tractor;
representing the self weight information of the logistics luggage tractor;
respectively correspond to
Weight information of the piece of luggage;
obtaining the number of turning points of the route according to the automatic driving route, and constructing a driving safety prediction model:
(ii) a Wherein the content of the first and second substances,
representing a predicted articulated coupler wear value at the xth car;
representing the number of turning points on the autonomous driving route;
representing a cornering coefficient of wear;
representing the total number of logistics luggage tractor compartments required by airport flights corresponding to the automatic driving routes;
constructing a time period T; and acquiring the predicted articulated coupler wear value of each carriage of the logistics luggage tractor under each airport flight in the time period T, and outputting the articulated coupler wear value to the scheduling module.
The scheduling model comprises:
acquiring the time of connecting the machine of the logistics luggage tractor in a time period T;
under the premise of meeting the condition that time coincidence does not occur, deploying airport flights of which all carriages participate in transportation and allocating serial numbers of all carriages;
the allocation of each carriage number meets the following conditions:
constructing the sum of the wear values of the predicted articulated couplers in all the transportation times of the same carriage in the time period T, recording the sum data of the wear values of the predicted articulated couplers of all the carriages into a set C, and meeting the condition that the mean square deviation of the data in the set C is in a constant range
Internal;
and setting a wear value threshold of the articulated coupler, generating unified maintenance time when the average value of the data in the set C exceeds the threshold, and outputting the unified maintenance time to an administrator port.
For example, three airport flights are taken within the time period T, which respectively require 5, 6 of cars;
respectively acquiring the load of each airport flight, and generating a predicted articulated coupler wear value of each carriage of each airport flight;
respectively noted as first time: 40. 30, 20, 15, 10; and (3) for the second time: 45. 35, 25, 20, 10; and thirdly: 70. 60, 50, 35, 30, 20;
six carriages are arranged to undertake the three times of transportation, and then:
the wear values corresponding to the six carriages are respectively as follows:
blank space represents not participating in transportation;
setting a mean square error constant range
If the mean square error is more than 2 and less than 5, the mean square error is calculated to be 3.4351128; if the range is met, the order is arranged according to the current sequence number;
in the first list, the carriage No. 5 is arranged as the first carriage, the carriage No. 2 is arranged as the second carriage, and so on.
In the second embodiment: the logistics luggage tractor driving control system comprises a driving list arranging module, a route processing module, a safety prediction module and a scheduling module;
the driving list module is used for acquiring airport flight lists, acquiring passenger data of each flight, wherein the passenger data comprises the luggage quantity data in the flight luggage compartment, and constructing a logistics luggage tractor list; the route processing module is used for acquiring the destination of automatic driving of the logistics luggage tractor under the airport flight, and constructing an automatic driving route by using a perception system algorithm and a planning system algorithm; the security predictionThe module is used for acquiring the predicted load information of each carriage on the logistics luggage tractor, acquiring the number of turning points of a route according to an automatic driving route, constructing a driving safety prediction model and generating a predicted articulated coupler wear value of each carriage; the dispatching module is used for acquiring the current articulated coupler wear value of each carriage, constructing a dispatching model and regulating carriage numbers to ensure that the mean square error of the predicted articulated coupler wear value of each carriage is in a constant range
In the method, uniform maintenance time is generated to meet driving safety control;
the output end of the driving list arranging module is connected with the input end of the route processing module; the output end of the route processing module is connected with the input end of the safety prediction module; the output end of the safety prediction module is connected with the input end of the scheduling module.
The driving ordering module comprises a flight information acquisition unit and an ordering unit of a logistics luggage tractor;
the flight information acquisition unit is used for acquiring an airport flight list, acquiring passenger data of each flight, selecting data of passengers for storing luggage from the passenger data, and constructing the luggage quantity data in the luggage compartment under each flight; the logistics luggage tractor ordering unit is used for generating the number of carriages and ordering time required by the logistics luggage tractor according to the luggage quantity data in the luggage cabin of each flight;
the output end of the flight information acquisition unit is connected with the input end of the logistics luggage tractor list arranging unit; and the output end of the logistics luggage tractor list arranging unit is connected with the input end of the route processing module.
The route processing module comprises a perception planning unit and a system planning unit;
the perception planning unit processes environment data obtained by a plurality of laser radars by using a perception system algorithm to form elevation data in a perception environment area; the classified vehicle speed control on different scales is realized on the road section with the complex shape; classifying the fluctuating road section by using local features of different scales;
the perception planning unit also provides the functions of road marking identification, traffic sign identification and vehicle and pedestrian detection;
the system planning unit is used for classifying the driving area according to a planning system algorithm, analyzing a classification result through multi-frame data, generating a road area in the driving area and finding out a moving obstacle; controlling the logistics luggage tractor to be capable of driving along the central line of the road, and generating a plurality of drivable routes in a state space according to the positions of the starting point and the target point of the vehicle; determining a plurality of necessary passing points required in a driving mode according to the generated road area, and autonomously generating a movable track;
the system planning unit also provides control under a complex traffic scene, the complex traffic scene comprises a turn, a crossroad and a T-shaped intersection, and the logistics luggage tractor generates a turn prompt when recognizing the complex traffic scene;
and constructing an automatic driving route of the logistics luggage tractor according to output results of the perception planning unit and the system planning unit.
The safety prediction module comprises a carriage information acquisition unit and a safety prediction unit;
the compartment information acquisition unit is used for acquiring the predicted load information of each compartment on the logistics luggage tractor; the safety prediction unit is used for acquiring the number of turning points of the route according to the automatic driving route, constructing a driving safety prediction model and generating a predicted articulated coupler wear value of each carriage;
the output end of the carriage information acquisition unit is connected with the input end of the safety prediction unit; and the output end of the safety prediction unit is connected with the input end of the scheduling module.
The scheduling module comprises a model building unit and an adjusting unit;
the model building unit is used for obtaining the wear value of the current articulated coupler of each carriage and building a scheduling model; the adjusting unit is used forThe car numbers are adjusted so that the mean square error of the predicted articulated coupler wear values for each car is within a constant range
Generating uniform maintenance time to meet driving safety control;
the output end of the model building unit is connected with the input end of the adjusting unit
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A driving control method of a logistics luggage tractor is characterized by comprising the following steps: the method comprises the following steps:
s1, obtaining airport flight lists, obtaining passenger data of each flight, wherein the passenger data comprise the number data of luggage in a flight luggage compartment, and constructing a logistics luggage tractor list;
s2, obtaining the destination of automatic driving of the logistics luggage tractor under the airport flight, and constructing an automatic driving route by using a sensing system algorithm and a planning system algorithm;
s3, obtaining predicted load information of each carriage on the logistics luggage tractor, obtaining the number of turning points of the route according to the automatic driving route, constructing a driving safety prediction model, and generating a predicted articulated coupler wear value of each carriage;
s4, obtaining the current articulated coupler wear value of each carriage, constructing a scheduling model, and adjusting carriage numbers to enable the mean square deviation of the predicted articulated coupler wear value of each carriage to be in a constant range
In the interior of said container body,
a preset range is set for the system, and uniform maintenance time is generated to meet driving safety control;
the construction of the driving safety prediction model comprises the following steps:
the method comprises the steps of obtaining the quantity data of luggage in a luggage compartment of any airport flight, numbering the luggage in the luggage compartment from small to large, and taking the sequence close to the exit of the luggage compartment or in contact with a conveyor belt as a reference in the numbering mode;
obtaining the predicted load information of each compartment on the logistics luggage tractor, wherein the calculation of the predicted load information comprises the following steps:
；
；
wherein the content of the first and second substances,
represents taking the minimum value greater than 0;
representing the carriage bearing area;
respectively represent
The maximum footprint of the piece of luggage;
is represented in
When the minimum value which is larger than 0 is taken, the value of n is taken;
representing the predicted load information of any carriage x on the logistics baggage tractor;
representing the self weight information of the logistics luggage tractor;
respectively correspond to
Weight information of the piece of luggage;
obtaining the number of turning points of the route according to the automatic driving route, and constructing a driving safety prediction model:
(ii) a Wherein the content of the first and second substances,
representing a predicted articulated coupler wear value at the xth car;
is represented byThe number of turning points on the driving route;
representing a cornering coefficient of wear;
representing the total number of logistics luggage tractor compartments required by airport flights corresponding to the automatic driving routes;
constructing a time period T; acquiring a predicted articulated coupler wear value of each carriage of the logistics luggage tractor under each airport flight in a time period T, and outputting the predicted articulated coupler wear value to a scheduling module;
the scheduling model includes:
acquiring the time of connecting the machine of the logistics luggage tractor in a time period T;
under the premise of meeting the condition that time coincidence does not occur, deploying airport flights of which all carriages participate in transportation and allocating serial numbers of all carriages;
the allocation of each carriage number satisfies the following conditions:
constructing the sum of the wear values of the predicted articulated couplers in all the transportation times of the same carriage in the time period T, recording the sum data of the wear values of the predicted articulated couplers of all the carriages into a set C, and meeting the condition that the mean square deviation of the data in the set C is in a constant range
Inner;
and setting a wear value threshold of the articulated coupler, generating unified maintenance time when the average value of the data in the set C exceeds the threshold, and outputting the unified maintenance time to an administrator port.
2. The logistics baggage tractor driving control method according to claim 1, wherein: the build logistics luggage tractor row sheet comprises:
obtaining an airport flight scheduling list which comprises time points of arrival of all flights at an airport;
acquiring passenger data of each airport flight, acquiring data of luggage stored by passengers from the passenger data, and generating luggage quantity data in a flight luggage compartment;
and constructing a logistics luggage tractor row list according to the luggage quantity data in the luggage compartment of each airport flight and the arrival time point of the luggage compartment at the airport, wherein the logistics luggage tractor row list comprises the compartment quantity and the arrival time of the logistics luggage tractor.
3. The logistics luggage tractor driving control method according to claim 1, wherein: the constructing an automatic driving route includes:
generating a driving area and a route identification of the autonomous driving route by using a perception system algorithm;
processing the environmental data obtained by the plurality of laser radars to form elevation data in a perception environmental area; the classified vehicle speed control on different scales is realized on the road section with the complex shape; classifying the fluctuating road section by using local features of different scales;
the perception system algorithm is also used for providing the functions of road marking identification, traffic sign identification and vehicle and pedestrian detection;
generating a route track of an automatic driving route and control under a complex traffic scene by using a planning system algorithm;
classifying the driving area according to a planning system algorithm, analyzing a classification result through multi-frame data, generating a road area in the driving area, and finding out moving obstacles;
the multi-frame data analysis comprises the following steps:
acquiring a running region environment image frame sequence in a current image acquisition time period, extracting a characteristic diagram of no less than M frames of environment images in the running region environment image frame sequence, and constructing the characteristic sequence, wherein M is a system setting constant; inputting the characteristic sequence into a long-short term memory network, outputting a characteristic sequence training set, and performing deconvolution on the output characteristic sequence training set and a corresponding driving area environment image frame sequence to obtain a dimension-increasing characteristic;
inputting the reverse order of the characteristic sequence into a pre-trained long-short term memory network to obtain a second characteristic sequence training set; deconvoluting the second feature sequence training set and the corresponding running area environment image frame sequence to obtain a dimension-increasing feature;
determining a road area in a driving area in the current environment image frame based on the two dimension-increasing characteristics, and finding out a movement barrier;
controlling the logistics luggage tractor to be capable of driving along the center line of the road, and generating a plurality of drivable routes in a state space according to the positions of a starting point and a target point of the vehicle; determining a plurality of necessary road points required in a driving mode according to the generated road area, and autonomously generating a movable motion track;
the planning system algorithm also provides control under complex traffic scenes, wherein the complex traffic scenes comprise turning, crossroads and T-shaped intersections, and when the logistics luggage tractor identifies the complex traffic scenes, turning points are recorded to generate turning prompts.
4. A baggage tractor driving control system to which the method of claim 1 is applied, characterized in that: the system comprises a driving order module, a route processing module, a safety prediction module and a scheduling module;
the driving list module is used for acquiring flight lists of an airport, acquiring passenger data of each flight, wherein the passenger data comprises the luggage quantity data in a flight luggage cabin, and constructing a logistics luggage tractor list; the route processing module is used for acquiring the destination of automatic driving of the logistics luggage tractor under the airport flight, and constructing an automatic driving route by using a perception system algorithm and a planning system algorithm; the safety prediction module is used for acquiring the predicted load information of each carriage on the logistics luggage tractor, acquiring the number of turning points of a route according to an automatic driving route, constructing a driving safety prediction model and generating a predicted articulated coupler wear value of each carriage; the dispatching module is used for acquiring the current articulated coupler wear value of each carriage, constructing a dispatching model and regulating carriage numbers to ensure that the mean square error of the predicted articulated coupler wear value of each carriage is inConstant range
In the interior, uniform maintenance time is generated, the driving safety control is satisfied,
presetting a range for the system;
the output end of the driving list arranging module is connected with the input end of the route processing module; the output end of the route processing module is connected with the input end of the safety prediction module; the output end of the safety prediction module is connected with the input end of the scheduling module.
5. The logistic baggage tractor driving control system according to claim 4, wherein: the driving ordering module comprises a flight information acquisition unit and an ordering unit of a logistics luggage tractor;
the flight information acquisition unit is used for acquiring an airport flight list, acquiring passenger data of each flight, selecting data of passengers for storing luggage from the passenger data, and constructing the luggage quantity data in the luggage compartment under each flight; the logistics luggage tractor ordering unit is used for generating the number of carriages and ordering time required by the logistics luggage tractor according to the luggage quantity data in the luggage compartment of each flight;
the output end of the flight information acquisition unit is connected with the input end of the logistics luggage tractor list arranging unit; and the output end of the logistics luggage tractor list arranging unit is connected with the input end of the route processing module.
6. The logistic baggage tractor driving control system according to claim 4, wherein: the route processing module comprises a perception planning unit and a system planning unit;
the sensing planning unit processes the environmental data obtained by the plurality of laser radars by using a sensing system algorithm to form elevation data in a sensing environmental area; the classified vehicle speed control on different scales is realized on the road section with the complex shape; classifying the fluctuating road sections by using local features of different scales;
the perception planning unit also provides the functions of road marking identification, traffic sign identification and vehicle and pedestrian detection;
the system planning unit is used for classifying the driving area according to a planning system algorithm, analyzing the classification result through multi-frame data, generating a road area in the driving area and finding out moving obstacles; controlling the logistics luggage tractor to be capable of driving along the center line of the road, and generating a plurality of drivable routes in a state space according to the positions of a starting point and a target point of the vehicle; determining a plurality of necessary passing points required in a driving mode according to the generated road area, and autonomously generating a movable track;
the system planning unit also provides control under a complex traffic scene, the complex traffic scene comprises a turn, a crossroad and a T-shaped intersection, and the logistics luggage tractor generates a turn prompt when recognizing the complex traffic scene;
and constructing an automatic driving route of the logistics luggage tractor according to output results of the perception planning unit and the system planning unit.
7. The logistics baggage tractor driving control system of claim 4, wherein: the safety prediction module comprises a carriage information acquisition unit and a safety prediction unit;
the compartment information acquisition unit is used for acquiring the predicted load information of each compartment on the logistics luggage tractor; the safety prediction unit is used for acquiring the number of turning points of the route according to the automatic driving route, constructing a driving safety prediction model and generating a predicted articulated coupler wear value of each carriage;
the output end of the carriage information acquisition unit is connected with the input end of the safety prediction unit; and the output end of the safety prediction unit is connected with the input end of the scheduling module.
8. The logistics baggage tractor driving control system of claim 4, wherein: the scheduling module comprises a model building unit and an adjusting unit;
the model building unit is used for obtaining the abrasion value of the current articulated coupler of each carriage and building a dispatching model; the adjusting unit is used for adjusting the carriage numbers so that the mean square error of the predicted articulated coupler wear value of each carriage is in a constant range
Generating uniform maintenance time to meet driving safety control;
the output end of the model building unit is connected with the input end of the adjusting unit.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210967876.8A CN115027506B (en) | 2022-08-12 | 2022-08-12 | Logistics luggage tractor driving control system and method |
| PCT/CN2022/132265 WO2024031861A1 (en) | 2022-08-12 | 2022-11-16 | Driving control system and method for logistics baggage tractor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210967876.8A CN115027506B (en) | 2022-08-12 | 2022-08-12 | Logistics luggage tractor driving control system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115027506A CN115027506A (en) | 2022-09-09 |
| CN115027506B true CN115027506B (en) | 2022-10-25 |
Family
ID=83130636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210967876.8A Active CN115027506B (en) | 2022-08-12 | 2022-08-12 | Logistics luggage tractor driving control system and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115027506B (en) |
| WO (1) | WO2024031861A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115027506B (en) * | 2022-08-12 | 2022-10-25 | 江苏天一航空工业股份有限公司 | Logistics luggage tractor driving control system and method |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19725322A1 (en) * | 1997-06-10 | 1998-12-17 | Abb Daimler Benz Transp | Procedure for conveyance of passengers, especially from inner city areas to airports and back |
| CN104875796A (en) * | 2015-06-04 | 2015-09-02 | 中国民航大学 | Electric unmanned towing tractor set for airport logistics and luggage transport |
| CN110633718B (en) * | 2018-06-21 | 2022-06-07 | 北京京东尚科信息技术有限公司 | Method and device for determining a driving area in an environment image |
| CN110633598B (en) * | 2018-06-21 | 2022-01-07 | 北京京东尚科信息技术有限公司 | Method and device for determining a driving area in an environment image |
| GB2576800B (en) * | 2019-02-06 | 2021-03-17 | Richmond Design And Marketing Ltd | Self-propelled baggage dolly, baggage handling system, baggage handling facility, and related apparatus and methods |
| EP4145339A4 (en) * | 2020-05-11 | 2023-05-24 | Huawei Technologies Co., Ltd. | Vehicle drivable area detection method, system, and automatic driving vehicle using system |
| CN112678201A (en) * | 2021-01-29 | 2021-04-20 | 中科大路(青岛)科技有限公司 | Management and control method and system for automatic driving luggage trailer of airport |
| CN113762757B (en) * | 2021-08-31 | 2024-03-19 | 海南天益物流配送有限公司 | Box throwing transportation system |
| CN115027506B (en) * | 2022-08-12 | 2022-10-25 | 江苏天一航空工业股份有限公司 | Logistics luggage tractor driving control system and method |
-
2022
- 2022-08-12 CN CN202210967876.8A patent/CN115027506B/en active Active
- 2022-11-16 WO PCT/CN2022/132265 patent/WO2024031861A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024031861A1 (en) | 2024-02-15 |
| CN115027506A (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11353577B2 (en) | Radar spatial estimation | |
| CN110531753B (en) | Control system, control method and controller for autonomous vehicle | |
| US11726477B2 (en) | Methods and systems for trajectory forecasting with recurrent neural networks using inertial behavioral rollout | |
| CN110588653B (en) | Control system, control method and controller for autonomous vehicle | |
| US10503172B2 (en) | Controlling an autonomous vehicle based on independent driving decisions | |
| US20190361454A1 (en) | Control systems, control methods and controllers for an autonomous vehicle | |
| US11361449B2 (en) | Neural network for object detection and tracking | |
| US11618444B2 (en) | Methods and systems for autonomous vehicle inference of routes for actors exhibiting unrecognized behavior | |
| CN115027506B (en) | Logistics luggage tractor driving control system and method | |
| US11645775B1 (en) | Methods and apparatus for depth estimation on a non-flat road with stereo-assisted monocular camera in a vehicle | |
| CN116710961A (en) | Method and system for ground segmentation using graphic cutting | |
| Lombaerts et al. | Adaptive multi-sensor fusion based object tracking for autonomous urban air mobility operations | |
| Khalil et al. | Exploiting multi-modal fusion for urban autonomous driving using latent deep reinforcement learning | |
| Gavrilova et al. | Application of computer vision algorithms in the problem of coupling of the locomotive with railcars | |
| US11810370B2 (en) | Techniques for identifying curbs | |
| US11640170B1 (en) | Identification of particulate matter in sensor data | |
| YU et al. | Vehicle Intelligent Driving Technology | |
| Zyner | Naturalistic driver intention and path prediction using machine learning | |
| US20230252638A1 (en) | Systems and methods for panoptic segmentation of images for autonomous driving | |
| EP4137845A1 (en) | Methods and systems for predicting properties of a plurality of objects in a vicinity of a vehicle | |
| US20230410469A1 (en) | Systems and methods for image classification using a neural network combined with a correlation structure | |
| US20240144010A1 (en) | Object Detection and Property Determination for Autonomous Vehicles | |
| Abrosimov et al. | TECHNOLOGIES OF ARTIFICIAL INTELLIGENCE IN THE PROBLEM OF ANALYSIS OF ROAD SITUATION BY AUTONOMOUS VEHICLE |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220909 Assignee: Jiangsu Tianyi Airport Equipment Maintenance Service Co.,Ltd. Assignor: Jiangsu Tianyi Aviation Industry Co.,Ltd. Contract record no.: X2023980044219 Denomination of invention: A Driving Control System and Method for Logistics Luggage Tractor Granted publication date: 20221025 License type: Common License Record date: 20231024 |
|
| EE01 | Entry into force of recordation of patent licensing contract |