CN112785076A - Community group purchase fresh food delivery path optimization algorithm - Google Patents
Community group purchase fresh food delivery path optimization algorithm Download PDFInfo
- Publication number
- CN112785076A CN112785076A CN202110133120.9A CN202110133120A CN112785076A CN 112785076 A CN112785076 A CN 112785076A CN 202110133120 A CN202110133120 A CN 202110133120A CN 112785076 A CN112785076 A CN 112785076A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- fresh food
- community group
- time
- group purchase
- 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
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
Abstract
The invention discloses a community group-buying fresh food delivery path optimization algorithm, which is characterized in that visual dynamic management is carried out on fresh food warehouse information, group length information and order information, an optimal delivery path scheme is found by utilizing reinforcement learning, firstly, model hypothesis is carried out, a specific reward function is set, and finally, the construction of a model algorithm is completed.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an optimization algorithm for a community group purchase fresh food delivery path.
Background
The community group purchase fresh food delivery path problem mainly relates to three points, namely a group position, a warehouse center and an urban traffic road, wherein the group position considers whether a delivery place is in a cell or outside the cell, whether vehicles can stop or not is considered outside the cell, the vehicles are convenient to unload, whether the vehicles can enter the cell or not is considered inside the cell, the height limit and the time limit of the vehicles are required to enter the cell, whether the factors to be considered in the warehouse center are close to an urban traffic main road or not is considered, the vehicles can enter the city in time, the time period required by fresh food delivery is between 7 o 'clock and 10 o' clock in the morning, the fresh food delivery path problem just catches up with the peak time period of the city on duty, and the urban peak time period on the duty is reasonably avoided in order to meet the time window restriction of delivery;
describing the fresh distribution path problem with a time window by using graph theory, wherein G ═ V, E is a completely undirected graph, where V ═ 0, 1.. and N } is a set of nodes, 1.. and N represents the number of N terminal groups to be visited, and 0 represents a logistics distribution center; and E { (i, j): i, j ∈ V, i ≠ j } is a set of edges connecting all nodes, all distribution vehicles start from the distribution center at the same time, the maximum loading capacity of the vehicles is Q, the vehicles are vehicles of the same vehicle type, the transportation and distribution of the goods are carried out for P terminal groups, each group length point is represented by 1,xp while satisfying QxQ is less than or equal to Q, and the constraint conditions required to be met in the mathematical model are as follows: the method comprises the following steps of vehicle load constraint (the load of each vehicle is required to be smaller than the maximum load), vehicle driving distance constraint (the maximum distance arranged by the vehicle is required to be smaller than the maximum distance allowed by the vehicle), only one logistics center (only one logistics center, all vehicles are loaded from here), service times constraint of a single customer (each customer delivery driver only serves once), delivery arrival end time constraint and the like.
Disclosure of Invention
The invention provides an optimization algorithm for a community group-buying fresh food delivery path, which can effectively solve the problem of the community group-buying fresh food delivery path proposed in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the community group purchase fresh food delivery path optimization algorithm is used for finding an optimal delivery path scheme by utilizing reinforcement learning according to visual dynamic management of fresh food warehouse information, group length information and order information.
According to the technical scheme, the optimal distribution path scheme is found by utilizing reinforcement learning, firstly, model assumption is carried out, a specific reward function is set, and finally, the construction of a model algorithm is completed.
According to the above technical solution, the model assumption specifically includes the following steps:
s1, before delivery, all the fresh food is sorted in the warehouse;
s2, calculating the distribution vehicle in a single way, starting from the distribution center to carry the cargos, arriving at the end of the group length to unload the cargos, and not returning to the distribution center on the same day;
and S3, all goods are delivered to the terminal group length fixing position with time constraint, and if the delivery does not deliver the goods within the constraint time, the reimbursement fee is generated.
According to the technical scheme, all the distribution vehicles in the S1 are unified in vehicle type, the maximum load is the same, and the time for loading the vehicles in the garage is not considered;
the center position of the logistics is fixed and is only one;
the location of the delivery point for each terminal bouquet is determined and there is only one delivery point.
According to the technical scheme, each logistics distribution vehicle in the step S2 can serve a plurality of customers;
each customer has to be served every day for the fresh class and only receives one vehicle for service;
all the goods delivered by the vehicles are the same size and the same specification;
all of the mass fresh class needs are known and are less than the maximum load capacity of the vehicle and all customers require the driver to unload themselves.
According to the technical scheme, all terminal group length unloading positions in the S3 have connectable roads and parking positions, and the distance between a driver parking point and the unloading point is not considered;
the running distance and the running time of the vehicle cannot be longer than the maximum duration;
without defining the service time required for each bouquet, the discharge time after the delivery vehicle arrives at the point of receipt is related only to the weight of the cargo, and the discharge time per unit of cargo volume is 1.
According to the technical scheme, the fresh group buying distribution of the community still meets the time window required by the client, so that the specific reward function is the minimum value of the sum of the three, and the specific setting is as follows:
fixing cost: the assumption of vehicles is that the vehicles are uniformly loaded in a uniform vehicle type and are vehicles with the same property, so that the fixed cost of the vehicles in distribution is only related to the number of the vehicles actually participating in distribution, the number of the required vehicles is large, the fixed cost is increased, and therefore the number of the vehicles which come out of the day needs to be reduced to reduce the fixed cost, so that the cost of enterprises can be saved1For a fixed cost total, the fixed cost is expressed as:
W1u as the number of vehicles;
variable cost during transportation: the variable cost of the vehicle in the transportation process is mainly fuel consumption, and because the speed of the vehicle in the road driving process is assumed to be constant, the fuel consumption of the vehicle is only related to the driving distance of the vehicle in the distribution process, the fuel consumption of the vehicle is larger as the driving distance of the vehicle in the distribution process is longer, the fuel cost is increased, and the variable cost is increased, wherein the fuel consumption cost is set to be F yuan/km, and the vehicle speed is set to be the variable cost in the transportation process to be W2Then the variable cost is expressed as:
W2＝F∑s；
time penalty cost over time window: aiming at the time constraint of receiving fresh goods by the delivery client of the community group purchase, if the goods are in [ h ]i,ji]If the time window reaches the range, the satisfaction degree of the client is the highest, and the time penalty cost is 0; if it is notIn the time window range acceptable to the clienti,li]Internal, but not in [ hi,ji]The penalty charge is the order amount
If the cargo is exceeding liIf the time is reached, the penalty charge is twice the amount of the order.
According to the technical scheme, the path planning model is built, the storage and generalization problems of the value function are solved by using the RBF neural network, the signal provided for the neural network to learn is a signal obtained by interaction between the reinforcement learning agent and the environment, and finally the interaction process of the agent and the environment is realized, and the specific algorithm flow is as follows:
s1, initializing an RBF neural network, and setting the initial vehicle number;
s2, observing the use state of the vehicle and calculating the reward;
s3, observing the current state of the intelligent agent to obtain a feasible direction set of the vehicle or the path, and selecting the behavior according to a behavior selection strategy;
s4, executing behaviors, adjusting vehicles or paths, entering the state behaviors into a neural network, and calculating forward to obtain a behavior value function;
s5, finding the maximum value of the behavior value function of the next state, and carrying out iterative update on the current value function according to the iterative rule of the learning algorithm;
s6, updating the state of the agent in the RBF neural network;
s7, judging whether the operation is finished or not, if not, returning to S2, and repeatedly executing;
and S8, storing the neural network parameters into a file, and ending.
According to the technical scheme, the resource scheduling planning is evaluated through the visual simulation environment, and the optimized learning parameters are applied to the optimization of the actual community group purchase fresh food delivery path.
Compared with the prior art, the invention has the beneficial effects that: the system has a scientific and reasonable structure, is safe and convenient to use, integrates data management and a reinforcement learning algorithm, realizes the optimized configuration of the group purchase fresh food delivery path of the community, greatly facilitates the delivery path, reduces unnecessary loss and improves the distribution effect.
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 schematic structural view of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example (b): as shown in fig. 1, the invention provides a technical solution, namely a community group purchase fresh food delivery path optimization algorithm, which utilizes reinforcement learning to find an optimal delivery path scheme according to visual dynamic management of fresh food warehouse information, group length information and order information.
According to the technical scheme, the optimal distribution path scheme is found by utilizing reinforcement learning, firstly, model assumption is carried out, a specific reward function is set, and finally the construction of a model algorithm is completed.
According to the above technical solution, the model assumption specifically includes the following steps:
s1, before delivery, all the fresh food is sorted in the warehouse;
s2, calculating the distribution vehicle in a single way, starting from the distribution center to carry the cargos, arriving at the end of the group length to unload the cargos, and not returning to the distribution center on the same day;
and S3, all goods are delivered to the terminal group length fixing position with time constraint, and if the delivery does not deliver the goods within the constraint time, the reimbursement fee is generated.
According to the technical scheme, all the distribution vehicles in the S1 are unified in vehicle type, the maximum load is the same, and the time for loading the vehicles in the garage is not considered;
the center position of the logistics is fixed and is only one;
the location of the delivery point for each terminal bouquet is determined and there is only one delivery point.
According to the technical scheme, each logistics distribution vehicle in the S2 can serve a plurality of customers;
each customer has to be served every day for the fresh class and only receives one vehicle for service;
all the goods delivered by the vehicles are the same size and the same specification;
all of the mass fresh class needs are known and are less than the maximum load capacity of the vehicle and all customers require the driver to unload themselves.
According to the technical scheme, all terminal bouquets unloading positions in S3 have connectable roads and parking positions, and the distance between a driver parking point and the unloading point is not considered;
the running distance and the running time of the vehicle cannot be longer than the maximum duration;
without defining the service time required for each bouquet, the discharge time after the delivery vehicle arrives at the point of receipt is related only to the weight of the cargo, and the discharge time per unit of cargo volume is 1.
According to the technical scheme, the fresh delivery of the group purchase in the community also meets the time window required by the client, so that the specific reward function is the minimum value of the sum of the three, and the specific setting is as follows:
fixing cost: the assumption of vehicles is that the vehicles are uniformly loaded in a uniform vehicle type and are vehicles with the same property, so that the fixed cost of the vehicles in distribution is only related to the number of the vehicles actually participating in distribution, the number of the required vehicles is large, the fixed cost is increased, and therefore the number of the vehicles which come out of the day needs to be reduced to reduce the fixed cost, so that the cost of enterprises can be saved1For a fixed cost total, the fixed cost is expressed as:
W1u as the number of vehicles;
variable cost during transportation: assumptions for vehicle transportIn order to not consider the loss of vehicle components and traffic accidents on roads, the variable cost of the vehicle in the transportation process is mainly fuel consumption, and moreover, because the speed of the vehicle in the road driving process is assumed to be constant, the fuel consumption of the vehicle is only related to the distance traveled by the vehicle in the distribution process, the fuel consumption of the vehicle is larger as the distance traveled by the vehicle in the distribution process is longer, the fuel cost is increased accordingly, and the variable cost is increased, wherein the cost set by the user is F yuan/km, and the variable cost of the vehicle in the transportation process is W2Then the variable cost is expressed as:
W2＝F∑s；
time penalty cost over time window: aiming at the time constraint of receiving fresh goods by the delivery client of the community group purchase, if the goods are in [ h ]i,ji]If the time window reaches the range, the satisfaction degree of the client is the highest, and the time penalty cost is 0; if in the time window range acceptable to the client [ u ]i,li]Internal, but not in [ hi,ji]The penalty charge is the order amount
If the cargo is exceeding liIf the time is reached, the penalty charge is twice the amount of the order.
According to the technical scheme, the path planning model is built, the storage and generalization problems of the value function are solved by using the RBF neural network, the signal provided for the neural network to learn is a signal obtained by interaction between the reinforcement learning agent and the environment, and finally the interaction process of the agent and the environment is realized, and the specific algorithm flow is as follows:
s1, initializing an RBF neural network, and setting the initial vehicle number;
s2, observing the use state of the vehicle and calculating the reward;
s3, observing the current state of the intelligent agent to obtain a feasible direction set of the vehicle or the path, and selecting the behavior according to a behavior selection strategy;
s4, executing behaviors, adjusting vehicles or paths, entering the state behaviors into a neural network, and calculating forward to obtain a behavior value function;
s5, finding the maximum value of the behavior value function of the next state, and carrying out iterative update on the current value function according to the iterative rule of the learning algorithm;
s6, updating the state of the agent in the RBF neural network;
s7, judging whether the operation is finished or not, if not, returning to S2, and repeatedly executing;
and S8, storing the neural network parameters into a file, and ending.
According to the technical scheme, the resource scheduling planning is evaluated through the visual simulation environment, and the optimized learning parameters are applied to the optimization of the actual community group purchase fresh food delivery path.
Compared with the prior art, the invention has the beneficial effects that: the system has a scientific and reasonable structure, is safe and convenient to use, integrates data management and a reinforcement learning algorithm, realizes the optimized configuration of the group purchase fresh food delivery path of the community, greatly facilitates the delivery path, reduces unnecessary loss and improves the distribution effect.
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 changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. 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 (9)
1. The community group purchase fresh food delivery path optimization algorithm is characterized in that: according to the dynamic visual management of the fresh warehouse information, the group growth information and the order information, the optimal distribution path scheme is found by utilizing reinforcement learning.
2. The community group purchase fresh food delivery path optimization algorithm according to claim 1, wherein the optimal delivery path scheme is found by utilizing reinforcement learning, model assumptions are firstly made, a specific reward function is set, and finally the construction of the model algorithm is completed.
3. The community group purchase fresh produce distribution route optimization algorithm of claim 2, wherein the model assumptions specifically comprise the steps of:
s1, before delivery, all the fresh food is sorted in the warehouse;
s2, calculating the distribution vehicle in a single way, starting from the distribution center to carry the cargos, arriving at the end of the group length to unload the cargos, and not returning to the distribution center on the same day;
and S3, all goods are delivered to the terminal group length fixing position with time constraint, and if the delivery does not deliver the goods within the constraint time, the reimbursement fee is generated.
4. The community group purchase fresh produce distribution path optimization algorithm according to claim 3, wherein all distribution vehicles in the S1 are unified in model, same in maximum load, and do not consider the time of loading in the warehouse;
the center position of the logistics is fixed and is only one;
the location of the delivery point for each terminal bouquet is determined and there is only one delivery point.
5. The community group purchase fresh produce distribution path optimization algorithm according to claim 3, wherein each logistics distribution vehicle in the step S2 can serve a plurality of customers;
each customer has to be served every day for the fresh class and only receives one vehicle for service;
all the goods delivered by the vehicles are the same size and the same specification;
all of the mass fresh class needs are known and are less than the maximum load capacity of the vehicle and all customers require the driver to unload themselves.
6. The community group purchase fresh food delivery route optimization algorithm according to claim 3, wherein at all terminal group growth unloading places in S3, there are connectable roads, there are parking positions, and the distance between the driver parking point and the unloading point is not considered;
the running distance and the running time of the vehicle cannot be longer than the maximum duration;
without defining the service time required for each bouquet, the discharge time after the delivery vehicle arrives at the point of receipt is related only to the weight of the cargo, and the discharge time per unit of cargo volume is 1.
7. The community group purchase fresh food delivery path optimization algorithm according to claim 1, wherein the delivery of the community group purchase fresh food also meets a time window required by a client, so that the specific reward function is the minimum value of the sum of the three, and the specific setting is as follows:
fixing cost: setting U as a fixed cost, W1For a fixed cost total, the fixed cost is expressed as:
W1u as the number of vehicles;
variable cost during transportation: the cost of setting the oil consumption is F yuan/km, and the vehicle speed is set as the variable cost in the transportation process is W2Then the variable cost is expressed as:
W2＝F∑s；
time penalty cost over time window: aiming at the time constraint of receiving fresh goods by the delivery client of the community group purchase, if the goods are in [ h ]i,ji]If the time window reaches the range, the satisfaction degree of the client is the highest, and the time penalty cost is 0;
in the time window range acceptable to the clienti,li]Internal, but not in [ hi,ji]Then, then
The goods are in excess ofiIf the time is reached, the penalty charge is twice the amount of the order.
8. The community group purchase fresh food delivery path optimization algorithm according to claim 1, wherein a path planning model is constructed, the RBF neural network is used for realizing the storage and generalization of the solution function, the signal provided for the neural network for learning is a signal obtained by interaction between an enhanced learning agent and the environment, and finally the interaction process between the agent and the environment is realized, and the specific algorithm flow is as follows:
s1, initializing an RBF neural network, and setting the initial vehicle number;
s2, observing the use state of the vehicle and calculating the reward;
s3, observing the current state of the intelligent agent to obtain a feasible direction set of the vehicle or the path, and selecting the behavior according to a behavior selection strategy;
s4, executing behaviors, adjusting vehicles or paths, entering the state behaviors into a neural network, and calculating forward to obtain a behavior value function;
s5, finding the maximum value of the behavior value function of the next state, and carrying out iterative update on the current value function according to the iterative rule of the learning algorithm;
s6, updating the state of the agent in the RBF neural network;
s7, judging whether the operation is finished or not, if not, returning to S2, and repeatedly executing;
and S8, storing the neural network parameters into a file, and ending.
9. The community group purchase fresh food delivery path optimization algorithm of claim 8, wherein the resource scheduling planning is evaluated by a visual simulation environment, and the optimized learning parameters are applied to the actual optimization of the community group purchase fresh food delivery path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110133120.9A CN112785076A (en) | 2021-01-29 | 2021-01-29 | Community group purchase fresh food delivery path optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110133120.9A CN112785076A (en) | 2021-01-29 | 2021-01-29 | Community group purchase fresh food delivery path optimization algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112785076A true CN112785076A (en) | 2021-05-11 |
Family
ID=75760136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110133120.9A Pending CN112785076A (en) | 2021-01-29 | 2021-01-29 | Community group purchase fresh food delivery path optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112785076A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629480A (en) * | 2023-07-19 | 2023-08-22 | 济南餐农网络科技有限公司 | Food material distribution system and distribution method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298704A (en) * | 2019-07-02 | 2019-10-01 | 深圳市聚星易科技有限公司 | A kind of community purchases by group management system |
| CN110969248A (en) * | 2018-09-28 | 2020-04-07 | 中国石油化工股份有限公司 | RBF-A2C-based reinforcement learning method and system |
-
2021
- 2021-01-29 CN CN202110133120.9A patent/CN112785076A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110969248A (en) * | 2018-09-28 | 2020-04-07 | 中国石油化工股份有限公司 | RBF-A2C-based reinforcement learning method and system |
| CN110298704A (en) * | 2019-07-02 | 2019-10-01 | 深圳市聚星易科技有限公司 | A kind of community purchases by group management system |
Non-Patent Citations (1)
| Title |
|---|
| 刘天雨: "时间窗口约束下社区团购生鲜第三方平台仓配模式优化问题研究", 《万方数据知识服务平台 学位论文》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629480A (en) * | 2023-07-19 | 2023-08-22 | 济南餐农网络科技有限公司 | Food material distribution system and distribution method |
| CN116629480B (en) * | 2023-07-19 | 2023-10-27 | 济南餐农网络科技有限公司 | Food material distribution system and distribution method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108764777B (en) | Electric logistics vehicle scheduling method and system with time window | |
| CN107766994B (en) | Shared bicycle scheduling method and scheduling system | |
| CN109034481B (en) | Constraint programming-based vehicle path problem modeling and optimizing method with time window | |
| CN110110871A (en) | A kind of method and system of Order splitting | |
| CN104700251A (en) | Maximum-minimum ant colony optimization method and maximum-minimum ant colony optimization system for solving vehicle scheduling problem | |
| Tamke et al. | The vehicle routing problem with drones and drone speed selection | |
| CN112101637B (en) | Dynamic charging optimization method based on time-of-use electricity price and energy consumption control and application thereof | |
| CN112801347B (en) | Multi-target city two-stage distribution planning method based on mobile transfer station and crowdsourcing | |
| CN112785076A (en) | Community group purchase fresh food delivery path optimization algorithm | |
| Taniguchi et al. | Multi-agent modelling for evaluating dynamic vehicle routing and scheduling systems | |
| Wang et al. | Optimization of ride-sharing with passenger transfer via deep reinforcement learning | |
| CN116596349A (en) | Night underground logistics planning method and system based on urban rail transit network | |
| CN116911729A (en) | Unmanned aerial vehicle and truck collaborative distribution method considering battery replacement plan | |
| CN116358593B (en) | Electric vehicle path planning method, device and equipment considering nonlinear energy consumption | |
| CN105894123A (en) | Determination method and apparatus for electric vehicle charging operation mode | |
| CN108921326A (en) | A kind of intelligent cultural gene Logistics Distribution Method based on similarity study | |
| Imran et al. | A-VRPD: Automating drone-based last-mile delivery using self-driving cars | |
| CN116993031A (en) | Charging decision optimization method, device, equipment and medium for electric vehicle | |
| Tafreshian et al. | A traveler incentive program for promoting community-based ridesharing | |
| Ren et al. | Routing optimization for shared electric vehicles with ride-sharing | |
| Zhao et al. | Vehicle dispatching and scheduling algorithms for battery electric heavy-duty truck fleets considering en-route opportunity charging | |
| Tang et al. | Energy-oriented routing strategy of electric vehicle: An end-to-end reinforcement learning approach | |
| Coltorti et al. | Ant colony optimization for real-world vehicle routing problems | |
| CN116001654A (en) | Battery energy control method, device, system and electronic equipment | |
| CN115751169A (en) | Intelligent scheduling method and device for hydrogen transport 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210511 |
|
| RJ01 | Rejection of invention patent application after publication |