CN115293606A - Unmanned delivery vehicle system - Google Patents
Unmanned delivery vehicle system Download PDFInfo
- Publication number
- CN115293606A CN115293606A CN202210966400.2A CN202210966400A CN115293606A CN 115293606 A CN115293606 A CN 115293606A CN 202210966400 A CN202210966400 A CN 202210966400A CN 115293606 A CN115293606 A CN 115293606A
- Authority
- CN
- China
- Prior art keywords
- delivery vehicle
- unmanned delivery
- information
- module
- goods
- 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
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000007726 management method Methods 0.000 claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000001934 delay Effects 0.000 claims description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004089 microcirculation Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000011165 process development Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned delivery vehicle system, which belongs to the technical field of logistics and comprises a user platform, an order distribution module, a cargo registration module, a vehicle-mounted camera, a driving control module, a cargo taking recording module, a management platform and a parameter analysis module, wherein the user platform is used for a client to log in, select articles required by the user platform and confirm the articles; the unmanned delivery vehicle parameter updating method can accurately control the unmanned delivery vehicle according to the surrounding environment, reduce the accident occurrence probability, improve the commodity safety, protect the benefits of customers and merchants, efficiently and accurately update the unmanned delivery vehicle parameters by constructing the analysis neural network, and improve the delivery efficiency of the unmanned delivery vehicle.
Description
Technical Field
The invention relates to the technical field of logistics, in particular to an unmanned delivery vehicle system.
Background
The unmanned automobile depends on the cooperative cooperation of artificial intelligence, visual calculation, radar, a monitoring device and a global positioning system, so that a computer can automatically and safely operate the motor vehicle without any active operation of human beings, as the 5G era comes and the takeaway industry is continuously strong, the unmanned delivery wagon also appears and is popularized, the unmanned delivery wagon appears and generates real-time interconnection interaction with community roads and scenes, the non-contact 'safe delivery' is realized, the 'last kilometer' intelligent logistics microcirculation is unblocked, the intelligent community construction is effectively promoted, and the unmanned delivery wagon belongs to a new product appearing in the process development of the automatic driving industry, and the product is always in a blank area of management. Therefore, the safety of the unmanned delivery vehicle in the running process becomes one of the key research directions of enterprises;
the existing unmanned delivery vehicle system cannot accurately control the unmanned delivery vehicle according to the surrounding environment, has high accident occurrence probability and cannot ensure the safety of goods; in addition, the existing unmanned delivery vehicle system cannot update the parameters of the unmanned delivery vehicle by self, so that the delivery efficiency of the unmanned delivery vehicle is reduced, and the data of the unmanned delivery vehicle is inconvenient to modify and maintain by managers; to this end, we propose an unmanned delivery vehicle system.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides an unmanned delivery vehicle system.
In order to achieve the purpose, the invention adopts the following technical scheme:
an unmanned delivery vehicle system comprises a user platform, an order distribution module, a cargo registration module, a vehicle-mounted camera, a driving control module, a cargo taking recording module, a management platform and a parameter analysis module;
the user platform is used for logging in by a client, selecting an article required by the user platform and confirming the article;
the order distribution module is used for receiving each group of data sent by the user platform, generating corresponding order information and then selectively distributing each order information;
the goods registration module is used for loading and registering goods to be transported by the unmanned delivery vehicle according to the order information;
the vehicle-mounted camera is used for acquiring road surface information in real time during the driving process of the unmanned delivery vehicle;
the driving control module is used for receiving the road surface information acquired by the vehicle-mounted camera and performing cascade analysis on the road surface information;
the goods taking recording module is used for sending goods taking information to the customer and recording and storing the goods taking information;
the parameter analysis module is used for acquiring the running parameters of the unmanned delivery vehicle in real time and analyzing and adjusting the running parameters;
and the management platform is used for a manager to check the running condition of the unmanned delivery vehicle and send a related control instruction.
As a further scheme of the present invention, the order distribution module selects distribution specific steps as follows:
the method comprises the following steps: the order distribution module classifies each group of order information according to different areas, then generates area record tables with the same quantity according to the classification information, and records the order information of each area into the corresponding area record table;
step two: then detecting whether the customer receiving address in each area record table is in the distribution range of the unmanned delivery vehicle, if not, sending the order to a management platform for delivery personnel to select to take, and if so, extracting the position of a merchant;
step three: and positioning the unmanned delivery vehicles in each area, calculating the distance between the position of each unmanned delivery vehicle in each area and the position of a merchant corresponding to each area, drawing a corresponding pick-up route for each group of unmanned delivery vehicles according to the distance from near to far, and sending corresponding order information to the relevant unmanned delivery vehicles for storage.
As a further scheme of the present invention, the loading registration of the cargo registration module specifically comprises the following steps:
step (1): after the unmanned delivery vehicle runs to a corresponding merchant, sending goods taking information to the merchant, and waiting for the merchant to store goods;
step (2): if the merchant does not store the commodities in the unmanned delivery vehicle within the specified time, the goods registration module removes the order information and sends the order information to the management platform for delivery personnel to select and pick up, and if the merchant stores the commodities in the unmanned delivery vehicle within the specified time, the merchant scans and confirms the commodity order bar code and sends commodity pick-up information to the customer.
As a further scheme of the present invention, the driving control module cascade analysis specifically comprises the following steps:
the first step is as follows: after collecting each group of image information collected by each vehicle-mounted camera, the driving control module processes videos or image sequence frames with fixed frame rates in an off-line mode and calculates the interval time of actual video frames;
the second step: recording the calculated interval time of the actual video frames, establishing a motion model through a Kalman filtering theory, simultaneously acquiring the motion state of the road surface target in real time through the established motion model, collecting the appearance characteristic vectors of all the road surface targets, and then defining the motion state of the moving target in the video frames by the motion model according to the linear motion assumption of the moving target;
the third step: collecting the motion state of the road surface target in the current video frame, constructing a prediction equation to estimate the motion state of each road surface target in the next video frame, and then controlling the unmanned delivery vehicle to make steering, straight-going or parking in advance;
the fourth step: when the unmanned delivery vehicle is at the crossroad, the extracted appearance feature vector is sent into a bidirectional feature pyramid for feature fusion, then classification regression is carried out on a fusion result, and a detection box, a category and a score are output;
the fifth step: collecting traffic light detection frame information in a video or image sequence frame with a fixed frame rate, generating corresponding detection frame coordinates, and performing expanded cutting on the video or image sequence frame with a related fixed frame rate to obtain a traffic light picture;
and a sixth step: and filtering simple negative samples belonging to the background in each group of traffic light pictures, selecting a traffic light corresponding to the driving road of the unmanned delivery vehicle for judgment, if the traffic light is green, continuing driving the unmanned delivery vehicle, and if the traffic light is red or yellow, stopping driving the unmanned delivery vehicle.
As a further aspect of the present invention, in the first step, the specific calculation formula of the interval time is as follows:
in the formula,. DELTA.t k+1 Representing the interval between two sets of video frames,
representing the delay time between the downsampled video frame and the original video stream,
represents the elapsed time of the tracking algorithm processing the video frame;
the motion state in the second step is specifically defined as follows:
wherein S represents the motion state of the tracking target, (x, y, w, h) represents the coordinate of the central point and the width and the height of the bounding box of the tracking target,
representing the corresponding tracking target speed value.
As a further scheme of the present invention, the detailed recording and storing steps of the pickup recording module are as follows:
s1.1: after the unmanned delivery vehicle reaches the client position, sending goods taking information to a corresponding client mobile phone according to the stored order information, and waiting for the client to take goods within a specified time;
s1.2: if the customer arrives at the goods taking place within the specified time, the unmanned delivery vehicle scans the two-dimensional code for the goods taking of the customer through the scanner and confirms the order information of the customer, then the corresponding goods storage bin is opened for the user to take the goods, and if the customer does not arrive at the goods taking place within the specified time, the unmanned delivery vehicle goes to the next customer place with the nearest distance and delays the goods taking information to the customer scheme;
s1.3: meanwhile, the number of sent orders is counted regularly by the unmanned delivery vehicle, the orders are sent to an external database to be stored, and meanwhile the completion amount of the orders every day is fed back to the management platform to be checked by workers.
As a further scheme of the present invention, the specific steps of analyzing and adjusting by the parameter analysis module are as follows:
s2.1: the parameter analysis module constructs and optimizes a group of analysis neural networks, then collects all the operation parameters of the unmanned delivery vehicle in the driving process, converts all the operation parameters into binary data meeting conditions through symbolic value conversion, leads all the operation parameters into the analysis neural networks, and converts all the operation parameters into a specified detection interval through normalization processing;
s2.2: extracting characteristic information of each operation parameter, performing characteristic dimension reduction on the characteristic information, dividing the processed operation parameters into a verification set, a test set and a training set, repeatedly using each group of data in the verification set for multiple times to verify the accuracy of the analysis neural network, counting the root mean square error of each group of data in the test set, predicting each group of data once, and outputting the data with the best prediction result as the optimal parameter;
s2.3: the analysis neural network carries out standardization processing on the training set according to the optimal parameters to generate training samples, then an upper controller is built according to the training samples, expected driving and braking speeds are calculated, a lower controller is built, and driving control and braking control are generated based on a fuzzy control theory and longitudinal dynamics;
s2.4: and respectively updating parameters of the driving scheme and the braking scheme according to the generated driving control and braking control, updating the parameters of the unmanned delivery vehicle according to the two generated schemes, and transmitting the updated parameter values to a management platform for a manager to check.
Compared with the prior art, the invention has the beneficial effects that:
1. the method comprises the steps that during the driving process of the unmanned delivery vehicle, road surface information is collected in real time through vehicle-mounted cameras, a driving control module collects each group of image information collected by each vehicle-mounted camera, video or image sequence frames with fixed frame rates are processed in an off-line mode, the interval time of actual video frames is calculated, the interval time of the calculated actual video frames is recorded, a motion model is built through a Kalman filtering theory, the motion state of a road surface target is obtained in real time through the built motion model, a prediction equation is built to estimate the motion state of each road surface target in the next video frame, then the unmanned delivery vehicle is controlled to turn, move straight or stop in advance, when the unmanned delivery vehicle is located at a crossroad, feature fusion is carried out on the video or image sequence frames with fixed frame rates to generate a detection frame, the detection frame is enlarged and cut to obtain a traffic light picture, simple negative samples belonging to the background in each group of traffic light pictures are filtered, traffic lights corresponding to the driving of the unmanned delivery vehicle are selected for judgment, the unmanned delivery vehicle can be accurately controlled according to the surrounding environment, the occurrence probability of goods is reduced, the goods accident occurrence probability of the unmanned delivery vehicle, the safety of the client is improved, and the benefit of the merchant is protected;
2. the invention constructs a group of analysis neural networks through a parameter analysis module, collects various operation parameters of the unmanned delivery vehicle, converts the various operation parameters into a specified detection interval through the analysis neural networks, predicts each group of data once, outputs the data with the best prediction result as the optimal parameters, standardizes the data by the analysis neural networks according to the optimal parameters to generate training samples, then constructs an upper controller according to the training samples, calculates expected driving and braking speeds, constructs a lower controller, generates driving control and braking control based on a fuzzy control theory and longitudinal dynamics, and finally respectively updates the driving scheme and the braking scheme according to the generated driving control and braking control and updates the parameters of the unmanned delivery vehicle according to the generated two groups of schemes.
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.
Fig. 1 is a system block diagram of an unmanned delivery vehicle system according to the present 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.
Example 1
Referring to fig. 1, an unmanned delivery vehicle system includes a user platform, an order distribution module, a cargo registration module, a vehicle-mounted camera, a travel control module, a pickup recording module, a management platform, and a parameter analysis module.
The user platform is used for the customer to log in and select the required articles and confirm.
The order distribution module is used for receiving each group of data sent by the user platform, generating corresponding order information and then selectively distributing each order information.
Specifically, the order distribution module classifies each group of order information according to different areas, then generates area record tables with the same quantity according to the classification information, records the order information of each area into the corresponding area record tables, then detects whether a customer delivery address in each area record table is in a delivery range of the unmanned delivery vehicle, if not, sends the order to a management platform for delivery personnel to select and pick up, if so, extracts a merchant position, and finally, the order distribution module positions the unmanned delivery vehicle of each area, calculates the distance between the position of the unmanned delivery vehicle of each area and the merchant position corresponding to each area, then draws a corresponding delivery route for each group of unmanned delivery vehicles according to the distance from near to far, and sends the corresponding order information to the relevant unmanned delivery vehicle for storage.
And the cargo registration module is used for loading and registering the cargo to be transported by the unmanned delivery vehicle according to the order information.
Specifically, after the unmanned delivery vehicle travels to a corresponding merchant, goods taking information is sent to the merchant, the merchant waits for goods storage, if the merchant does not store the goods into the unmanned delivery vehicle within a set time, the goods registration module removes the order information and sends the order information to the management platform for delivery personnel to select and take, if the merchant stores the goods into the unmanned delivery vehicle within the set time, the goods order bar code is scanned and confirmed, and goods taking information is sent to the customer.
The vehicle-mounted camera is used for collecting road surface information of the unmanned delivery vehicle in real time in the driving process.
And the driving control module is used for receiving the road surface information acquired by the vehicle-mounted camera and carrying out cascade analysis on the road surface information.
Specifically, after collecting each set of image information collected by each vehicle-mounted camera, a driving control module processes video or image sequence frames with a fixed frame rate in an off-line mode, calculates the interval time of actual video frames, records the calculated interval time of the actual video frames, establishes a motion model through a Kalman filtering theory, simultaneously obtains the motion state of a road target in real time through the established motion model, collects the appearance characteristic vectors of all the road targets, then defines the motion state of the moving target in the video frames according to the linear motion assumption of the moving target, collects the motion state of the road target in the current video frame, establishes a prediction equation to estimate the motion state of each road target in the next video frame, then controls an unmanned delivery vehicle to turn, go straight or stop, sends the extracted appearance characteristic vectors to a bidirectional characteristic pyramid for feature fusion when the unmanned delivery vehicle is at an intersection, classifies the fusion result, outputs a detection frame, categories and scores, detects the video or image sequence of the video or image sequence with the fixed frame rate, filters out the corresponding traffic light, and obtains a traffic light frame, and then judges whether the traffic light sequence of the traffic light is a traffic light.
It should be further noted that the specific calculation formula of the interval time is as follows:
in the formula,. DELTA.t k+1 Representing the interval between two sets of video frames,
representing the delay time between the downsampled video frame and the original video stream,
represents the elapsed time of the tracking algorithm processing the video frame;
the motion state is specifically defined as follows:
wherein S represents the motion state of the tracking target, (x, y, w, h) represents the coordinate of the central point and the width and the height of the bounding box of the tracking target,
representative phaseAnd a corresponding tracking target speed value.
Example 2
Referring to fig. 1, an unmanned delivery vehicle system includes a user platform, an order distribution module, a cargo registration module, a vehicle-mounted camera, a driving control module, a pickup recording module, a management platform, and a parameter analysis module.
The goods taking recording module is used for sending goods taking information to the customer and recording and storing the goods taking information.
Specifically, after the unmanned delivery vehicle arrives at a client position, goods taking information is sent to a corresponding client mobile phone according to stored order information, meanwhile, the user waits for goods taking within a set time, if the user arrives at a goods taking place within the set time, the unmanned delivery vehicle scans a two-dimensional code for goods taking of the client through a scanner and confirms the order information of the client, then, a corresponding storage bin is opened for the user to take goods, if the user does not arrive at the goods taking place within the set time, the unmanned delivery vehicle goes to the next client place with the nearest distance, meanwhile, the goods taking information is delayed for the scheme of the client, meanwhile, the unmanned delivery vehicle periodically counts the number of sent orders and sends the number to an external database for storage, and meanwhile, the completion quantity of the orders every day is fed back to a management platform for workers to check.
The parameter analysis module is used for collecting the driving parameters of the unmanned delivery vehicle in real time and analyzing and adjusting the driving parameters.
The method comprises the steps that a parameter analysis module constructs and optimizes a group of analysis neural networks, then various operation parameters of an unmanned delivery vehicle in the running process are collected, the operation parameters are converted into binary data meeting conditions through symbolic value conversion, the operation parameters are led into the analysis neural networks, then the operation parameters are converted into a specified detection interval through normalization processing, characteristic information of the operation parameters is extracted, characteristic dimension reduction is carried out on the operation parameters, the processed operation parameters are divided into a verification set, a test set and a training set, meanwhile, the group data in the verification set are repeatedly used for multiple times to verify the accuracy of the analysis neural networks, root mean square errors of the data in the test set are counted, each group of data are subjected to primary prediction, the data with the best prediction result are output as optimal parameters, the analysis neural networks carry out standardization processing on the training sets according to the optimal parameters to generate training samples, then an upper-layer controller is constructed according to the training samples, expected driving and braking speeds are calculated, a lower-layer controller is constructed, driving control and braking control are generated based on a fuzzy control theory and longitudinal dynamics, finally, an upper-layer controller is constructed according to the generated driving control and braking control schemes, and an unmanned delivery vehicle management scheme is respectively updated, and parameters are transmitted to a management platform, and the management platform.
And the management platform is used for the management personnel to check the running condition of the unmanned delivery vehicle and send a related control instruction.
Claims (7)
1. An unmanned delivery vehicle system is characterized by comprising a user platform, an order distribution module, a cargo registration module, a vehicle-mounted camera, a driving control module, a cargo taking recording module, a management platform and a parameter analysis module;
the user platform is used for logging in by a client, selecting an article required by the user platform and confirming the article;
the order distribution module is used for receiving each group of data sent by the user platform, generating corresponding order information and then selectively distributing each order information;
the goods registration module is used for loading and registering goods to be transported by the unmanned delivery vehicle according to the order information;
the vehicle-mounted camera is used for acquiring road surface information in real time during the driving process of the unmanned delivery vehicle;
the driving control module is used for receiving the road surface information acquired by the vehicle-mounted camera and performing cascade analysis on the road surface information;
the goods taking recording module is used for sending goods taking information to the customer and recording and storing the goods taking information;
the parameter analysis module is used for acquiring the driving parameters of the unmanned delivery vehicle in real time and analyzing and adjusting the driving parameters;
and the management platform is used for a manager to check the running condition of the unmanned delivery vehicle and send a related control instruction.
2. The unmanned delivery vehicle system of claim 1, wherein the order distribution module selects distribution by the following specific steps:
the method comprises the following steps: the order distribution module classifies each group of order information according to different areas, then generates area record lists with the same quantity according to the classification information, and records the order information of each area into the corresponding area record list;
step two: then detecting whether the customer receiving address in each area record table is in the distribution range of the unmanned delivery vehicle, if not, sending the order to a management platform for delivery personnel to select to take, and if so, extracting the position of a merchant;
step three: and positioning the unmanned delivery vehicles in each area, calculating the distance between the position of the unmanned delivery vehicle in each area and the position of a merchant corresponding to each area, drawing a corresponding pickup route for each group of unmanned delivery vehicles according to the distance from near to far, and sending corresponding order information to the relevant unmanned delivery vehicles for storage.
3. The unmanned delivery vehicle system of claim 2, wherein the loading registration of the cargo registration module comprises the following steps:
step (1): after the unmanned delivery vehicle runs to a corresponding merchant, sending goods taking information to the merchant, and waiting for the merchant to store goods;
step (2): if the merchant does not store the commodities in the unmanned delivery vehicle within the specified time, the goods registration module removes the order information and sends the order information to the management platform for delivery personnel to select and pick up, and if the merchant stores the commodities in the unmanned delivery vehicle within the specified time, the merchant scans and confirms the commodity order bar code and sends commodity pick-up information to the customer.
4. The unmanned delivery vehicle system of claim 3, wherein the cascade analysis of the driving control modules comprises the following steps:
the first step is as follows: after collecting each group of image information collected by each vehicle-mounted camera, the driving control module processes videos or image sequence frames with fixed frame rates in an off-line mode and calculates the interval time of actual video frames;
the second step is that: recording the calculated interval time of the actual video frames, establishing a motion model through a Kalman filtering theory, simultaneously acquiring the motion state of the road surface target in real time through the established motion model, collecting the appearance characteristic vectors of all the road surface targets, and then defining the motion state of the moving target in the video frames by the motion model according to the linear motion assumption of the moving target;
the third step: collecting the motion state of the road targets in the current video frame, constructing a prediction equation to estimate the motion state of each road target in the next video frame, and then controlling the unmanned delivery vehicle to make steering, straight-going or parking in advance;
the fourth step: when the unmanned delivery vehicle is at the crossroad, the extracted appearance feature vectors are sent into a bidirectional feature pyramid for feature fusion, then the fusion results are classified and regressed, and a detection frame, a category and a score are output;
the fifth step: collecting traffic light detection frame information in a video or image sequence frame with a fixed frame rate, generating corresponding detection frame coordinates, and performing expanded cutting on the video or image sequence frame with a related fixed frame rate to obtain a traffic light picture;
and a sixth step: and filtering simple negative samples belonging to the background in each group of traffic light pictures, selecting a traffic light corresponding to the driving road of the unmanned delivery vehicle for judgment, if the traffic light is green, continuing driving the unmanned delivery vehicle, and if the traffic light is red or yellow, stopping driving the unmanned delivery vehicle.
5. The unmanned delivery vehicle system of claim 4, wherein in the first step, the specific calculation formula of the interval time is as follows:
in the formula,. DELTA.t k+1 Representing the interval between two sets of video frames,
representing the delay time between the downsampled video frame and the original video stream,
represents the elapsed time of the tracking algorithm processing the video frame;
the motion state in the second step is specifically defined as follows:
wherein S represents the motion state of the tracking target, (x, y, w, h) represents the coordinate of the central point and the width and the height of the bounding box of the tracking target,
representing the corresponding tracking target velocity value.
6. The unmanned delivery vehicle system of claim 1, wherein the pick-up record module records and stores the following steps:
s1.1: after the unmanned delivery vehicle reaches the client position, sending goods taking information to a corresponding client mobile phone according to the stored order information, and waiting for the client to take goods within a specified time;
s1.2: if the customer arrives at the goods taking place within the specified time, the unmanned delivery vehicle scans the two-dimensional code for taking goods of the customer through the scanner, confirms the order information of the customer, then opens the corresponding goods storage bin for the user to take goods, and if the customer does not arrive at the goods taking place within the specified time, the unmanned delivery vehicle goes to the next customer place with the nearest distance and delays the scheme of the customer for taking goods information;
s1.3: meanwhile, the number of sent orders is counted regularly by the unmanned delivery vehicle, the orders are sent to an external database to be stored, and meanwhile the completion amount of the orders every day is fed back to the management platform to be checked by workers.
7. The unmanned delivery vehicle system of claim 1, wherein the parameter analysis module analyzes and adjusts the following steps:
s2.1: the parameter analysis module constructs and optimizes a group of analysis neural networks, then collects all the operation parameters of the unmanned delivery vehicle in the driving process, converts all the operation parameters into binary data meeting conditions through symbolic value conversion, leads all the operation parameters into the analysis neural networks, and converts all the operation parameters into a specified detection interval through normalization processing;
s2.2: extracting characteristic information of each operation parameter, performing characteristic dimension reduction on the characteristic information, dividing the processed operation parameters into a verification set, a test set and a training set, repeatedly using each group of data in the verification set for multiple times to verify the accuracy of the analysis neural network, counting the root mean square error of each group of data in the test set, performing primary prediction on each group of data, and outputting the data with the best prediction result as the optimal parameter;
s2.3: the analysis neural network carries out standardization processing on the training set according to the optimal parameters to generate training samples, then an upper layer controller is built according to the training samples, expected driving and braking speeds are calculated, a lower layer controller is built, and driving control and braking control are generated based on a fuzzy control theory and longitudinal dynamics;
s2.4: and respectively updating parameters of the driving scheme and the braking scheme according to the generated driving control and braking control, updating the parameters of the unmanned delivery vehicle according to the two generated schemes, and transmitting the updated parameter values to a management platform for a manager to check.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210966400.2A CN115293606A (en) | 2022-08-12 | 2022-08-12 | Unmanned delivery vehicle system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210966400.2A CN115293606A (en) | 2022-08-12 | 2022-08-12 | Unmanned delivery vehicle system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115293606A true CN115293606A (en) | 2022-11-04 |
Family
ID=83828252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210966400.2A Pending CN115293606A (en) | 2022-08-12 | 2022-08-12 | Unmanned delivery vehicle system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115293606A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116189439A (en) * | 2023-05-05 | 2023-05-30 | 成都市青羊大数据有限责任公司 | Urban intelligent management system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030009398A1 (en) * | 2001-07-03 | 2003-01-09 | Kuang-Shin Lin | Computer system for goods management in a stock company |
| CN107093040A (en) * | 2017-03-03 | 2017-08-25 | 北京小度信息科技有限公司 | information generating method and device |
| CN109541943A (en) * | 2018-12-07 | 2019-03-29 | 西南交通大学 | A kind of tramcar on-line optimizing and controlling method |
| CN111199366A (en) * | 2018-11-19 | 2020-05-26 | 奥迪股份公司 | Unmanned distribution method and device, computer equipment and computer readable storage medium |
| CN111401823A (en) * | 2020-06-08 | 2020-07-10 | 北京云迹科技有限公司 | Cargo distribution method, device and system for unmanned vehicle |
| CN113052531A (en) * | 2021-03-23 | 2021-06-29 | 苏州易航远智智能科技有限公司 | Unmanned logistics vehicle distribution method and system based on motion analysis |
-
2022
- 2022-08-12 CN CN202210966400.2A patent/CN115293606A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030009398A1 (en) * | 2001-07-03 | 2003-01-09 | Kuang-Shin Lin | Computer system for goods management in a stock company |
| CN107093040A (en) * | 2017-03-03 | 2017-08-25 | 北京小度信息科技有限公司 | information generating method and device |
| CN111199366A (en) * | 2018-11-19 | 2020-05-26 | 奥迪股份公司 | Unmanned distribution method and device, computer equipment and computer readable storage medium |
| CN109541943A (en) * | 2018-12-07 | 2019-03-29 | 西南交通大学 | A kind of tramcar on-line optimizing and controlling method |
| CN111401823A (en) * | 2020-06-08 | 2020-07-10 | 北京云迹科技有限公司 | Cargo distribution method, device and system for unmanned vehicle |
| CN113052531A (en) * | 2021-03-23 | 2021-06-29 | 苏州易航远智智能科技有限公司 | Unmanned logistics vehicle distribution method and system based on motion analysis |
Non-Patent Citations (2)
| Title |
|---|
| 范婉舒，赖际舟等: "基于改进DeepSORT的视觉/激光雷达目标跟踪与定位方法", 《导航定位与授时》, vol. 9, no. 4, 31 July 2022 (2022-07-31), pages 77 - 84 * |
| 顾超越，李喆等: "基于改进Faster-RCNN的无人机巡检架空线路销钉缺陷检测", 《高电压技术》, vol. 46, no. 9, 30 September 2020 (2020-09-30), pages 3089 - 3096 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116189439A (en) * | 2023-05-05 | 2023-05-30 | 成都市青羊大数据有限责任公司 | Urban intelligent management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110398972B (en) | Self-distribution takeout robot | |
| CN109784162B (en) | Pedestrian behavior recognition and trajectory tracking method | |
| WO2022206942A1 (en) | Laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field | |
| US20210035442A1 (en) | Autonomous Vehicles and a Mobility Manager as a Traffic Monitor | |
| CN112633176B (en) | Rail transit obstacle detection method based on deep learning | |
| US20230377317A1 (en) | Systems and methods for intelligent selection of data for building a machine learning model | |
| CN112216097A (en) | Method and device for detecting blind area of vehicle | |
| Jiménez | Intelligent Vehicles: Enabling technologies and future developments | |
| CN110765922A (en) | AGV is with two mesh vision object detection barrier systems | |
| CN108491782A (en) | A kind of vehicle identification method based on driving Image Acquisition | |
| US20220230021A1 (en) | Autonomous vehicle system for intelligent on-board selection of data for building a remote machine learning model | |
| US20220301099A1 (en) | Systems and methods for generating object detection labels using foveated image magnification for autonomous driving | |
| CN115293606A (en) | Unmanned delivery vehicle system | |
| CN110796104A (en) | Target detection method and device, storage medium and unmanned aerial vehicle | |
| CN115861968A (en) | Dynamic obstacle removing method based on real-time point cloud data | |
| CN113052531A (en) | Unmanned logistics vehicle distribution method and system based on motion analysis | |
| CN115861963A (en) | Forklift operation safety early warning system based on deep learning and digital twins | |
| CN117589167A (en) | Unmanned aerial vehicle routing inspection route planning method based on three-dimensional point cloud model | |
| EP4241047A2 (en) | Architecture for map change detection in autonomous vehicles | |
| US11554794B2 (en) | Method and system for determining a mover model for motion forecasting in autonomous vehicle control | |
| WO2022086739A2 (en) | Systems and methods for camera-lidar fused object detection | |
| CN115027506B (en) | Logistics luggage tractor driving control system and method | |
| CN115790635A (en) | Block chain-based unmanned transport vehicle driving route planning method and device | |
| Astudillo et al. | Reducing the breach between simulated and real data for top view images | |
| CN117877276B (en) | Method for controlling logistics traffic in factory |
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 |