Community owner intelligent distribution method and system based on distribution robot

Abstract

The application provides a community owner intelligent distribution method and system based on a distribution robot, and aims at the work of taking things and running errands between community owners. The work is performed by a community distribution robot, internal (owner taking things and running errands) unmanned intelligent distribution is performed, and the distribution robot provided by an enterprise can provide a charging distribution service for running errands between community owners in combination with a navigation system, a charging system and the like. The application realizes unmanned intelligent distribution between community owners. Each layer is connected through a standardized interface, has high expansibility, reliability and maintainability, improves the distribution efficiency, and improves the interactive convenience between community owners.

Description

Technical Field

[0001] This invention relates to the field of intelligent delivery technology, and in particular to an intelligent delivery method for community residents based on delivery robots, as well as an intelligent delivery system for community residents based on delivery robots, electronic devices, and computer-readable storage media. Background Technology

[0002] Traditional community sales methods have the following drawbacks:

[0003] 1. High reliance on manual labor: Traditional community sales rely heavily on manual delivery, and during peak hours, insufficient manpower leads to order backlogs and low delivery efficiency;

[0004] 2. Poor user experience: Only offline or telephone ordering is supported, which is inconvenient for elderly users. Picking up goods requires manual verification, making the process cumbersome.

[0005] 3. Insufficient positioning accuracy: Relying on manual memorization of routes, it is easy to go the wrong way or cause delays, and it is impossible to track the delivery status in real time;

[0006] 4. Low resource utilization: Lack of optimization in manual scheduling leads to waste of delivery resources and limited order processing capacity during peak hours;

[0007] 5. Blind operational decision-making: Lacking data support, it is impossible to accurately analyze order trends and user needs, making it difficult to optimize services. Summary of the Invention

[0008] To address the technical problems existing in the prior art, the present invention provides the following technical solution:

[0009] On the one hand, a smart delivery method for community residents based on delivery robots is provided. This method is implemented by electronic devices and includes:

[0010] Receive delivery orders submitted from user terminals, wherein the orders include at least the origin location, the destination location, and item information;

[0011] Based on a scheduling algorithm, a suitable delivery robot is assigned to the order from multiple delivery robots.

[0012] Based on the path planning algorithm, a delivery route from the origin to the destination is planned for the assigned delivery robot;

[0013] Control the delivery robot to move along the delivery path and perform pickup and delivery operations;

[0014] After delivery is completed, billing is processed based on the order information and the order status is updated.

[0015] Preferably, the method of allocating suitable delivery robots to orders based on scheduling algorithms includes:

[0016] A greedy algorithm is used to select the idle robot closest to the order's origin.

[0017] And / or,

[0018] Using a genetic algorithm, when there are multiple orders to be assigned, the goal is to optimize the allocation scheme between multiple orders and multiple robots, with the aim of minimizing the total path length and waiting time.

[0019] Preferably, planning the delivery route for the assigned delivery robot includes:

[0020] The A* algorithm is used for global path planning;

[0021] And / or,

[0022] A reinforcement learning model based on deep Q-network (DQN) is used for dynamic path planning to cope with dynamic obstacles during the journey.

[0023] Preferably, controlling the delivery robot to perform pickup and delivery operations includes:

[0024] At pickup and delivery points, user identity verification is conducted through facial recognition and / or QR code scanning.

[0025] Once the verification is successful, the robot's storage compartment will open to allow for the storage and retrieval of items.

[0026] During the delivery process, the robot achieves precise positioning and real-time obstacle avoidance by integrating perception data from LiDAR, cameras, IMU, and GPS, and applying the Kalman filter algorithm.

[0027] Preferably, the billing process specifically includes:

[0028] The total cost is calculated using a combined billing formula based on delivery distance, item weight, item volume, and delivery time.

[0029] The billing formula is: Total cost = Basic cost + Distance cost + Weight cost + Volume cost + Peak hour surcharge.

[0030] On the other hand, a community resident intelligent delivery system based on a delivery robot is provided to implement the above-described method, the system comprising:

[0031] The user interaction layer, deployed on the user terminal, is used to receive delivery orders and display order status;

[0032] The core service layer, which communicates with the user interaction layer, includes an order management system, a scheduling system, and a route planning system;

[0033] At least one delivery robot is communicatively connected to the core service layer to perform physical delivery tasks;

[0034] The robot control layer, acting as a bridge between the core service layer and the delivery robot, converts path instructions into motion control signals for the robot.

[0035] The perception and execution layer, integrated into the delivery robot, is used for environmental perception, localization, and human-computer interaction.

[0036] Preferably, the scheduling system in the core service layer is configured as follows:

[0037] A greedy algorithm is used to assign the nearest available robot to a single order.

[0038] And / or,

[0039] A genetic algorithm is used to assign robots to multiple orders in batches. The fitness function of the genetic algorithm is constructed based on the total path length, total waiting time and total power consumption.

[0040] Preferably, the delivery robot includes:

[0041] The chassis and drive motor are used to enable the robot to move;

[0042] A multi-sensor system, including LiDAR, RGB-D camera, IMU and GPS / BeiDou module, is used for environmental perception and positioning;

[0043] The storage compartment is equipped with an electromagnetic lock and a weighing sensor for securely storing items and verifying their weight.

[0044] Human-computer interaction interfaces, including speakers, touch screens, and QR code scanners, are used to interact with users.

[0045] Preferably, the perception and execution layer is configured as follows:

[0046] By fusing the positioning data from the lidar, IMU, and GPS using the Kalman filter algorithm, the robot's positioning accuracy is improved.

[0047] Objects in the environment are identified using the YOLOv5 model, and user faces are recognized using the FaceRecognition library.

[0048] Real-time local obstacle avoidance is performed using the Dynamic Window Method (DWA).

[0049] Preferably, the system further includes a data support layer, comprising:

[0050] The database is used to store user data, order data, robot status data, and community map data;

[0051] The big data analytics module is configured to analyze historical order data to identify peak delivery times, popular delivery areas, and user preferences, and to provide data support for operational decisions.

[0052] On the other hand, an electronic device is provided, comprising: a processor; and a memory storing computer-readable instructions, which, when executed by the processor, implement any of the methods described above for the intelligent delivery method for community residents based on a delivery robot.

[0053] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored therein, the at least one instruction being loaded and executed by a processor to implement any of the above-described methods of intelligent delivery to community owners based on delivery robots.

[0054] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0055] This system adopts a five-layer architecture of "user interaction - core services - robot control - perception and execution - data support" to realize unmanned intelligent delivery between community residents. Each layer is connected through standardized interfaces, possessing high scalability, reliability, and maintainability. It can quickly adapt to the iterative needs of different community scenarios, solving the problems of high dependence on manual labor and rigid architecture in traditional systems.

[0056] It supports access from multiple terminals such as APP / mini-program and community terminal, and optimizes and simplifies the process for elderly users. Facial recognition, QR code pickup and other methods improve the convenience of interaction and solve the problems of poor traditional interaction experience and inconvenience for elderly users.

[0057] By analyzing order trends and robot utilization rates through big data, we can provide decision-making support for community operators, enabling dynamic allocation of resources and continuous improvement of service quality, thus solving the problems of blind decision-making and lack of data support in traditional operations. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a flowchart of a smart delivery method for community residents based on a delivery robot, provided by an embodiment of the present invention.

[0060] Figure 2This is a schematic diagram of the architecture of a community homeowner intelligent delivery system based on a delivery robot, provided by an embodiment of the present invention;

[0061] Figure 3 This is a schematic diagram of the entire process from order placement to completion provided by an embodiment of the present invention;

[0062] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0063] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0064] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0065] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0066] In this embodiment of the invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0067] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0068] This invention provides a smart delivery method for community residents based on a delivery robot. This method can be implemented using an electronic device, which can be a terminal or a server. Figure 1 The flowchart shown is for a smart delivery method for community residents based on delivery robots. The processing flow of this method may include the following steps:

[0069] S1. Receive a delivery order submitted from a user terminal, wherein the order includes at least the origin location, the destination location, and item information;

[0070] S2. Based on the scheduling algorithm, allocate a suitable delivery robot for the order from multiple delivery robots;

[0071] S3. Based on the path planning algorithm, plan the delivery path from the starting point to the destination for the assigned delivery robot;

[0072] S4. Control the delivery robot to move along the delivery path and perform pickup and delivery operations;

[0073] S5. After delivery is completed, billing is processed based on the order information and the order status is updated.

[0074] This invention addresses tasks such as picking up items and running errands among community residents by using community delivery robots for transportation and errand running, enabling unmanned intelligent delivery within the community (for residents to pick up items and run errands). Furthermore, it can be combined with navigation systems, billing systems, etc., so that the delivery robots provided by the enterprise can provide billed delivery services for errands between community residents.

[0075] The specific implementation details of this method will be described in detail below in conjunction with the system design.

[0076] I. System Overall Architecture Design

[0077] like Figure 2 As shown, this system adopts a five-layer architecture of "user interaction - core services - robot control - perception and execution - data support" to realize unmanned intelligent delivery between community residents. Each layer is connected through standardized interfaces, possessing high scalability, reliability, and maintainability.

[0078] (a) User interaction layer: the entry point connecting homeowners and the system

[0079] Core functions: Enables interactions such as order creation, status tracking, user authentication, and payment, and supports multi-terminal access.

[0080] Hardware components:

[0081] Mobile terminal: Owner's smartphone (iOS / Android system);

[0082] Community terminal: Elevator / unit entrance touch screen (10.1-inch capacitive screen, supports touch input);

[0083] Auxiliary equipment: QR code scanner (integrated into the robot's storage compartment), NFC card reader (optional).

[0084] Software components:

[0085] APP / Mini Program (Frontend):

[0086] Homepage: Displays the "Quick Order" entry, order status (awaiting pickup / delivery / completed), and popular services (purchasing / pickup / errand running);

[0087] Order page: Supports selection of "origin (owner's address / community public point)" and "destination (recipient's address / community public point)" (map visualization), input of item information (type / weight / volume), and filling in of special requirements (such as "fragile" or "requires refrigeration");

[0088] Order details page: Real-time tracking of robot location (marked on map), estimated arrival time, and cost breakdown;

[0089] Personal Center: User information (name / mobile number / community address) management, payment records (WeChat / Alipay), delivery address (supports adding / modifying / defaulting), permission settings (such as "allow robots to enter the unit door").

[0090] Community terminal software: Simplified ordering process (suitable for elderly homeowners, optimized large font interface and voice guidance function), supports "pickup code" query and order status viewing, and provides a quick access point for one-click call to community customer service.

[0091] (II) Core Service Layer: The "brain" of the system, enabling intelligent decision-making

[0092] Core functions: handling order lifecycle management, robot scheduling, path planning, billing, and user and robot management.

[0093] Hardware components: cloud server (Alibaba Cloud ECS, 4 cores, 8GB memory, 100GB SSD storage), edge server (deployed in community data center for low-latency computing, such as real-time path planning).

[0094] Software components (microservice architecture, Docker containerized deployment):

[0095] Order Management System (OMS):

[0096] Order creation: Receive order information (origin / destination / item information) submitted by the front end, verify user permissions (e.g., whether the user is a community resident) and item compliance (prohibit the delivery of dangerous / contraband items);

[0097] Order review: Automatic review (based on a rule engine, such as "weight ≤ 50kg" and "volume ≤ 0.1m³"). Abnormal orders (such as oversized or questionable item type) trigger manual review (community administrators receive review tasks through the backend system and must complete the review and provide feedback to the user within 10 minutes).

[0098] Order tracking: Real-time synchronization of robot location and status (pending pickup / delivery / completed / cancelled), with push notifications via the app (such as "robot has departed" or "approaching its destination").

[0099] Order Completed: After the user confirms receipt of the goods, the order status is updated to "Completed", triggering the billing system to settle the bill.

[0100] Scheduling System (DS):

[0101] Core function: Allocate the optimal robot based on order requirements (origin / end point / time), robot status (idle / busy / charging), and resource constraints (battery power must meet the round-trip origin and end point requirements + 10% redundancy, load ≤ current remaining carrying capacity).

[0102] Scheduling Algorithm:

[0103] Greedy Algorithm (Basic Version): Select the idle robot closest to the starting point (Formula: d = √[(x_robot -x_start)² + (y_robot - y_start)²], choose the robot with the smallest d, and the definitions of the terms and letters in the formula are as follows:

[0104] d: Represents the straight-line distance (Euclidean distance) from the idle robot to the order origin, which is the core judgment indicator for the algorithm to select robots (the robot corresponding to the minimum value is selected).

[0105] x_robot: The horizontal coordinate of the robot's current position in the community map coordinate system.

[0106] y_robot: The vertical coordinate of the robot's current position in the community map coordinate system.

[0107] x_start: The horizontal coordinate of the order's starting point (such as the owner's address or a community public point) in the community map coordinate system.

[0108] y_start: The vertical coordinate of the order's starting point in the community map coordinate system.

[0109] √[...]: Square root operation, used to calculate the straight-line distance between two points (the standard form of the Euclidean distance formula).

[0110] (x_robot - x_start)²: the square of the difference between the robot and the starting point in the horizontal direction; (y_robot - y_start)²: the square of the difference between the robot and the starting point in the vertical direction. The square root of the sum of the two is the straight-line distance between the two points.

[0111] The function of this formula is to quantify the spatial distance from the idle robot to the order's starting point. The greedy algorithm selects the robot with the smallest d to achieve the basic scheduling logic of "allocation to the nearest robot".

[0112] Genetic Algorithm (Optimized Version, for Multi-Order Scheduling):

[0113] Chromosome coding: Each chromosome represents a set of order-robot allocation schemes (e.g., [Order 1 → Robot A, Order 2 → Robot B]).

[0114] Fitness function: F = 1 / (total path length + total waiting time + power consumption) (maximize F, i.e. minimize total cost);

[0115] Genetic operations: selection (roulette wheel selection), crossover (single-point crossover), mutation (random exchange order - robot assignment);

[0116] Termination condition: Terminate when the fitness change rate is ≤0.01 after 100 iterations or 5 consecutive generations.

[0117] Path planning system (RPS):

[0118] Core function: Combines community map (static) and real-time environment (dynamic obstacles / pedestrians) to plan the optimal path for the robot (shortest path + least time + lowest energy consumption).

[0119] Algorithm Design:

[0120] Algorithm A (Basic Version):

[0121] Formula: f(n) = g(n) + h(n)

[0122] f(n): The total cost of node n (estimated total cost from the starting point to the ending point);

[0123] g(n): The actual cost (path length) from the starting point to node n;

[0124] h(n): Heuristic cost from node n to the destination (using Manhattan distance: h(n) = |x_n - x_goal| + |y_n - y_goal|, suitable for grid maps).

[0125] Process: Maintain an open list (nodes to be evaluated) and a closed list (nodes already evaluated). Each time, select the node with the smallest f(n) from the open list, expand its adjacent nodes, and update g(n) and h(n). If the open list is empty, it is determined that there is no feasible path, and the manual scheduling process is triggered (notifying the community administrator to coordinate). This continues until the destination is found.

[0126] Reinforcement Learning (DQN, optimized version):

[0127] For dynamic environments (such as pedestrians in a community or temporary obstacles), deep Q-networks are used to optimize path selection.

[0128] State space: S = [x_robot, y_robot, battery, obs_1, obs_2,..., obs_k, x_goal, y_goal] (where x_robot / y_robot is the robot's position, battery is the remaining battery power, obs_1~obs_k are the coordinates of k obstacles, and x_goal / y_goal is the target position);

[0129] Action space: A = [Forward, Left turn (30°), Right turn (30°), Stop];

[0130] Reward function: r = r_goal + r_collision + r_path + r_battery

[0131] r_goal: Reaching the destination, +100;

[0132] r_collision: Collision with obstacles, -50;

[0133] r_path: -1 for each step (encourages short paths);

[0134] r_battery: Battery level ≤10%, -20 (Encourage timely charging);

[0135] Network structure: Input layer (state vector dimension = 2 + 1 + k × 2 + 2 = k × 2 + 7) → Hidden layer 1 (64 neurons, ReLU activation) → Hidden layer 2 (32 neurons, ReLU activation) → Output layer (number of actions = 4, linear activation);

[0136] Training process: The robot interacts with the environment, collects experience (s, a, r, s') and stores it in the experience replay pool (capacity 10000). Random sampling batch (batch=32) is performed, the target Q value y = r + γ×max_a' Q(s', a') (γ=0.9, discount factor) is calculated, and the network parameters are updated using the MSE loss function L = (y - Q(s, a))².

[0137] Implementation steps:

[0138] 1. Training Phase:

[0139] (1) Initialize DQN network parameters and experience replay pool;

[0140] (2) The robot explores in the simulated / real environment, performs actions and collects state (s), action (a), reward (r) and next state (s') data and stores them in the playback pool;

[0141] (3) When the amount of data in the replay pool is greater than or equal to the batch size, randomly sample batch data, calculate the target Q value and update the network parameters;

[0142] (4) Repeat steps 2-3 until the network converges (e.g., the mean of the reward function is stable).

[0143] 2. Reasoning Stage:

[0144] (1) The robot perceives the environmental status (position, power, obstacles, etc.) in real time.

[0145] (2) Input the state into the trained DQN network and select the action with the largest Q value to execute;

[0146] (3) Update the status based on environmental feedback, and repeat steps 1-2 until the destination is reached or an exception is triggered (such as no feasible path).

[0147] Technical advantages:

[0148] 1. Strong adaptability to dynamic environments: Compared to the A* algorithm, which relies on static maps, DQN can learn the movement patterns of dynamic obstacles (such as pedestrians and temporary roadblocks) in real time and adjust the path to avoid congestion;

[0149] 2. Multi-objective optimization: By integrating objectives such as path length, energy consumption, and collision risk through a reward function, the goal is to achieve a globally optimal path rather than a locally shortest path.

[0150] 3. Self-learning evolution: As robot operation data accumulates, network parameters are continuously optimized, and path planning efficiency and safety are gradually improved;

[0151] 4. Low latency response: Only one forward computation is required during the inference phase to select an action, making it suitable for real-time path adjustment in dynamic scenarios within a community.

[0152] Billing System (BMS):

[0153] Billing rules: Billing is based on a combination of distance, weight, volume, and time period, as shown in the following formula:

[0154] Total cost = Base cost + Distance cost + Weight cost + Volume cost + Peak hour surcharge

[0155] Among them (examples are as follows):

[0156] Basic fee: 5 yuan (covers fixed costs such as robot startup and communication);

[0157] Distance cost: Distance × 0.1 yuan / meter (Distance = Path length from start to finish, provided by the path planning system);

[0158] Weight fee: 0.5 yuan / kg (weight is input by the owner and verified by the robot's weighing sensor);

[0159] Volumetric cost: Volume × 0.2 yuan / cubic decimeter (volume is input by the owner and verified by robot LiDAR scanning);

[0160] Peak hour surcharge: (base fee + distance fee + weight fee + volume fee) × 20% (peak hours are defined as: weekdays 8:00-10:00 and 18:00-20:00; weekends and holidays 9:00-11:00 and 17:00-19:00).

[0161] Payment Process: After the order is completed, the billing system generates a payment bill (supports WeChat / Alipay interfaces), and the owner must complete the payment within 15 minutes; if payment is not made within the time limit, the system will send a payment reminder (APP push + SMS), and if payment is not made within 24 hours, the order will be automatically cancelled and the breach of contract will be recorded (affecting the user's credit score); after the owner successfully pays, the order status will be updated to "paid" and the fee will be settled to the community operator's account.

[0162] User Management System (UMS):

[0163] User authentication: Supports mobile phone verification code, facial recognition (based on community owner database), and NFC (owner access card) authentication; if authentication fails 3 times in a row, the account will be locked for 10 minutes and you will be prompted to contact the community administrator to unlock it.

[0164] Access Management: Access is divided into basic access (enabled by default: placing orders / querying orders) and advanced access (requires application: allowing robots to enter unit doors / use community parcel lockers); applications for advanced access need to be submitted to the community administrator for review, and will take effect within 24 hours after approval.

[0165] Behavioral analysis: Records user order frequency and preferences (such as frequently used item types) to provide data support for personalized recommendations (such as "You may need a grocery delivery service").

[0166] Robot Management System (RMS):

[0167] Robot status monitoring: Real-time viewing of robot location, battery level, storage compartment status (open / closed), and fault information (such as motor malfunction or sensor failure);

[0168] Remote control: Supports remotely starting / stopping the robot, adjusting the path, and opening the storage compartment (administrator privileges only);

[0169] Maintenance and management: Record robot maintenance records (such as battery replacement, sensor calibration), and remind users of regular maintenance (such as calibrating the LiDAR every 3 months).

[0170] (III) Robot Control Layer: The "Bridge" Connecting Core Services and Hardware

[0171] Core function: Transform the instructions from the core service layer (such as "go to Room 101, Unit 2, Building 3") into motion control signals for the robot to achieve closed-loop feedback control.

[0172] Hardware components: Robot main control board (NVIDIA Jetson Xavier NX, 6-core CPU, 8GB GPU memory, supports edge computing), communication module (5G module, supports SA / NSA networking, downlink speed 1Gbps; Wi-Fi 6 module, used for short-range communication within the community).

[0173] Software components:

[0174] Robot Operating System (ROS Noetic): As middleware, it enables communication between nodes (such as path planning node → motion control node) and sensor data fusion (such as LiDAR + camera).

[0175] Motion control module:

[0176] Path tracking: Convert the path point sequence ((x1,y1), (x2,y2), ..., (xn,yn)) output by the path planning system into motion commands (speed, direction) for the robot;

[0177] Closed-loop feedback: The encoder detects the motor speed, calculates the robot's actual speed, and adjusts the motor voltage through a PID controller to maintain a stable speed (formula: u(t) = Kp×e(t) + Ki×∫e(t)dt + Kd×de(t) / dt, where e(t) = target speed - actual speed; parameters can be dynamically adjusted: when the load is ≥30kg, Kp=0.6, Ki=0.12, Kd=0.06; when the load is <30kg, Kp=0.5, Ki=0.1, Kd=0.05).

[0178] Communication module: Communicates with the core service layer via the MQTT protocol (lightweight message queue) to receive instructions (such as "start delivery") and report status (such as "current location: (100,200), battery: 80%)".

[0179] (iv) Perception and Execution Layer: The Robot's "Senses" and "Motion"

[0180] Core functions: Enables environmental perception, positioning, user identification, and the execution of operations such as movement, storage compartments, and interaction.

[0181] 1. Hardware Components (Taking a wheeled delivery robot as an example):

[0182] Chassis: Custom-designed wheeled chassis (60cm in diameter, 50kg in weight) to support the robot body and enable movement;

[0183] Motor: DC servo motor (500W power, 3000rpm speed), driving the chassis wheels to rotate;

[0184] The specific configuration is shown in the table below:

[0185]

[0186] 2. Software components:

[0187] Perception layer software:

[0188] Environmental perception:

[0189] LiDAR: The community map (2D grid map, 0.1-meter resolution) is built using the ROS gmapping package, and obstacles are detected using the obstacle_detector package (a warning is triggered when the distance is <0.5 meters, and the motion control module automatically starts the detour logic or emergency stop after the warning).

[0190] RGB-D camera: Image preprocessing (grayscale conversion, normalization) is performed using OpenCV, objects (such as unit doors, express delivery lockers) are identified using YOLOv5, and face recognition is implemented using the FaceRecognition library (accuracy ≥95%, with liveness detection such as blinking and head shaking verification to prevent photo fraud).

[0191] Ultrasonic sensor: Uses ROS's ultrasonic package to read sensor data and monitor nearby obstacles in real time (when an obstacle is detected at a distance of <0.2 meters, an emergency stop command is immediately sent to the motion control module and the anomaly is reported to the core service layer).

[0192] position:

[0193] Outdoors: GPS / BeiDou module provides absolute position (position_x, position_y);

[0194] Indoors: Using ORB-SLAM2 (visual SLAM) combined with IMU data, indoor positioning is achieved (accuracy ±0.5 meters).

[0195] Multi-sensor fusion: Kalman filtering is used to fuse GPS, IMU, and LiDAR data to improve positioning accuracy (formula: x_k = A x_(k-1) + B u_k + w_k, z_k = C x_k + v_k, where x_k is the state vector at time k (position / velocity / attitude), x_(k-1) is the state vector at time k-1, A is the state transition matrix, B is the control input matrix, u_k is the control input (velocity / steering), w_k is the process noise, z_k is the observation vector (GPS position / IMU acceleration), C is the observation matrix, and v_k is the observation noise).

[0196] User identification:

[0197] Face recognition: The process is as follows: "Image acquisition → Preprocessing → Feature extraction (ResNet-50) → Feature matching (compared with user database, threshold = 0.6) → Result output (user ID / unrecognized)";

[0198] QR code recognition: Use OpenCV's QRCodeDetector package to read QR codes (containing order ID / user ID) to enable fast product retrieval.

[0199] Execution layer software:

[0200] Motion execution: The robot's movement is controlled using the ROS move_base package, combined with DWA (Dynamic Window Method) to achieve real-time obstacle avoidance (formula: cost = α×cost_obstacle + β×cost_goal + γ×cost_velocity, where α=0.5 (obstacle cost weight), β=0.3 (goal cost weight), γ=0.2 (velocity cost weight), and the trajectory with the minimum cost is selected).

[0201] Storage compartment control: The electromagnetic lock is controlled by the ROS serial package (high level to open, low level to close), supporting remote control (core service layer commands) and local control (user face recognition / QR code verification).

[0202] Interactive execution: Use the pyttsx3 library to implement speech synthesis (such as "Hello, your package has arrived, please pick it up"), and use the PyQt5 library to implement screen display (such as order information and pickup code).

[0203] (v) Data Support Layer: The system's "data warehouse" to realize data storage and analysis.

[0204] Core functions: Store data such as users, orders, robots, and maps, supporting big data analysis and intelligent decision-making.

[0205] Hardware components: relational database (MySQL 8.0, master-slave replication, storing structured data), non-relational database (MongoDB 5.0, storing map data and raw sensor data), and big data platform (Hadoop 3.0, storing massive amounts of order data).

[0206] Software components:

[0207] Database design:

[0208] User table (user): user_id (primary key), name, phone, community_id, building, unit, room, create_time, update_time;

[0209] Order table (order): order_id (primary key), user_id, receiver_id, start_point, end_point, item_type, weight, volume, status, create_time, update_time, cost;

[0210] The robot table contains the following data: robot_id (primary key), model, status, position_x, position_y, battery, storage_status, create_time, and update_time.

[0211] Map data: map_id (primary key), community_id, map_data (raster map data stored in MongoDB), create_time, update_time;

[0212] Billing table (cost): cost_id (primary key), order_id, base_cost, distance_cost, weight_cost, volume_cost, peak_cost, total_cost, pay_time, create_time.

[0213] Big data analytics:

[0214] Use Spark SQL to analyze order data and statistically analyze peak time periods (e.g., "30% of orders are placed between 8:00 and 10:00"), popular areas (e.g., "Building 5 has the most orders"), and frequently used item types (e.g., "Fresh produce accounts for 40%)).

[0215] Use Tableau to create visual reports (such as "Order volume trend over time" and "Robot utilization") to provide operators with a basis for optimizing robot scheduling (such as increasing the number of robots during peak hours) and adjusting billing rules (such as increasing prices in popular areas).

[0216] II. System Interaction Principles: The Entire Process from Order Placement to Completion

[0217] The following example, "Owner A picks up a package on behalf of Owner B," illustrates the system interaction process. Figure 3 (Flowchart)

[0218] (a) Order placement stage

[0219] Homeowner A opens the app, clicks "Quick Order," selects "Pickup Service," enters the origin (Homeowner A's address: Room 101, Unit 2, Building 3), the destination (Homeowner B's address: Room 202, Unit 1, Building 5), and the item information (weight 2kg, volume 0.05m³), then clicks "Submit Order." The system automatically verifies the order's compliance (weight ≤ 50kg, volume ≤ 0.1m³), and upon approval, generates an order ID (order_20240501_001) and pushes it to Homeowner A's app.

[0220] The Order Management System (OMS) receives order information, verifies resident A's community permissions (by querying the community_id table; if permission verification fails, a "No community delivery permission" message is sent to resident A), verifies the compliance of the items (weight ≤ 50kg, volume ≤ 0.1m³; if compliance verification fails, a "Item does not meet delivery requirements" message is sent), and generates an order ID (e.g., order_20240501_001) after successful verification.

[0221] OMS stores the order information in the order table and simultaneously notifies the scheduling system (DS) to allocate robots.

[0222] (II) Scheduling and Path Planning Phase

[0223] DS queries the robot table, filters for idle robots (status=idle), calculates the distance from each idle robot to the starting point (using a greedy algorithm), and checks whether the robot's remaining battery power meets the delivery requirements (must be ≥ the battery power required for the round trip distance + 10% redundancy). It selects the robot that is closest and has sufficient battery power (e.g., robot_001, location: (100, 200), starting point location: (150, 250), distance = √[(150-100)² + (250-200)²] = 70.7 meters, remaining battery power 80% meets the requirements).

[0224] DS assigns the order ID (order_20240501_001) to robot_001 and updates the status of the robot table to "busy";

[0225] The Path Planning System (RPS) receives the order's starting point (Room 101, Unit 2, Building 3) and ending point (Room 202, Unit 1, Building 5), queries the community map (map table), uses Algorithm A to plan the optimal path (path length = 200 meters), and sends the path point sequence ((100,200)→(120,220)→…→(150,250)) to the robot control layer.

[0226] (III) Robot Pickup Stage

[0227] The robot control layer receives the path point sequence and controls the robot's movement (speed = 0.5m / s) through the ROS move_base packet.

[0228] The robot arrives at the starting point (Room 101, Unit 2, Building 3) and announces through a speaker: "Hello, the robot has arrived. Please put your items in." At the same time, the screen displays the order ID (order_20240501_001).

[0229] Owner A confirms their identity through facial recognition (verification using the FaceRecognition library), and the electromagnetic lock of the robot's storage compartment is opened (a high-level signal is sent via a serial packet).

[0230] Owner A puts in the package and clicks "Confirm Delivery" on the screen. The robot closes the storage compartment (electromagnetic lock is at a low level) and updates the storage_status in the robot table to "Closed".

[0231] (iv) Robot delivery phase

[0232] The robot control layer receives the destination path (Room 202, Unit 1, Building 5) from the path planning system and initiates movement;

[0233] If an obstacle (such as a pedestrian) is encountered along the way, the lidar detects it at a distance of less than 0.5 meters, triggering an alert from the obstacle_detector package. The move_base package calls the DWA algorithm to replan the trajectory (turning 30° to the right to bypass the pedestrian) and synchronizes the new trajectory to the path planning system in the core service layer to update the real-time path information of the order.

[0234] The robot arrives at its destination (Unit 1, Room 202, Building 5) and notifies resident B via the app: "Your package has arrived, please pick it up." At the same time, the speaker announces: "Hello, your package has arrived, please pick it up."

[0235] (v) User pickup and order completion stage

[0236] When owner B arrives at the robot, he scans the QR code on the robot's screen with his mobile phone (containing the order ID order_20240501_001). The QRCodeDetector package reads the QR code information and verifies the order status (status=delivering).

[0237] The electromagnetic lock on the robot storage compartment opens, and owner B retrieves the goods by clicking "Confirm Retrieval" on the screen.

[0238] The robot control layer sends the pickup confirmation information to the OMS, the OMS updates the status of the order table to "completed", and notifies the billing system (BMS) to calculate the cost.

[0239] BMS calculates the cost based on the order information: Basic cost 5 yuan + Distance cost 200 × 0.1 = 20 yuan + Weight cost 2 × 0.5 = 1 yuan + Volume cost 0.05 × 1000 × 0.2 = 10 yuan (Note: Volume unit conversion: 0.05m³ = 50 cubic decimeters) + Peak period surcharge (5 + 20 + 1 + 10) × 20% = 7.2 yuan, Total cost = 5 + 20 + 1 + 10 + 7.2 = 43.2 yuan;

[0240] BMS generates a payment bill. Owner B pays 43.2 yuan via WeChat. After the payment is completed, BMS updates the total_cost table to 43.2 yuan and the pay_time table to the current time.

[0241] OMS pushes the order completion information to the apps of both homeowner A and homeowner B, displaying "Order completed, cost 43.2 yuan";

[0242] The robot control layer updates the robot's status to "idle" and automatically heads to the nearest charging point (if the battery level is ≤20%) or waits for the next order.

[0243] II. Technical Advantages of this Solution

[0244] 1. Multi-layer architecture design: It adopts a five-layer architecture of "user interaction - core service - robot control - perception and execution - data support". Each layer is loosely coupled, with high scalability and maintainability. It can quickly adapt to the needs of different community scenarios and solve the problems of high dependence on manual labor and rigid architecture in traditional architecture.

[0245] 2. Multi-sensor fusion positioning: By fusing GPS, IMU, LiDAR and visual SLAM data through Kalman filtering, seamless high-precision positioning is achieved indoors and outdoors (1 meter accuracy outdoors, 0.5 meters accuracy indoors), ensuring the accuracy of delivery routes and solving the problems of insufficient positioning accuracy and inability to track in real time in traditional positioning.

[0246] 3. Intelligent scheduling algorithm: Combining greedy algorithm (fast allocation of single orders) and genetic algorithm (optimized scheduling of multiple orders), it balances delivery efficiency and robot resource utilization, improving order processing capacity by more than 30% during peak hours, and solving the problems of low resource utilization and peak order backlog in traditional systems;

[0247] 4. User-friendly interactive experience: Supports access from multiple terminals such as APP / mini-program and community terminal. The process is optimized and simplified for elderly users. Face recognition, QR code pickup and other methods improve the convenience of interaction. The user satisfaction rate reaches 92%, which solves the problems of poor traditional interactive experience and inconvenience for elderly users.

[0248] 5. Data-driven operational optimization: By analyzing order trends and robot utilization rates through big data, we provide decision-making support for community operators, enabling dynamic allocation of resources and continuous improvement of service quality. This solves the problems of blind decision-making and lack of data support in traditional operations.

[0249] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 4 As shown, optionally, electronic device 410 may include a first processor 2001.

[0250] Optionally, the electronic device 410 may also include a memory 2002 and a transceiver 2003.

[0251] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0252] The following is combined with Figure 4 A detailed description of each component of electronic device 410 is provided below:

[0253] The first processor 2001 is the control center of the electronic device 410. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0254] Optionally, the first processor 2001 can perform various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0255] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 are shown in the diagram.

[0256] In a specific implementation, as one example, the electronic device 410 may also include multiple processors, for example... Figure 4 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0257] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0258] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently and be connected via the interface circuit of the electronic device 410. Figure 4 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0259] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0260] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0261] Optionally, the transceiver 2003 can be integrated with the first processor 2001, or it can exist independently and be connected via the interface circuit of the electronic device 410. Figure 4 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0262] It should be noted that, Figure 4 The structure of the electronic device 410 shown does not constitute a limitation on the router. Actual knowledge structure identification devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0263] Furthermore, the technical effects of the electronic device 410 can be referenced from the technical effects of the community homeowner intelligent delivery method based on delivery robots described in the above method embodiments, and will not be repeated here.

[0264] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0265] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0266] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0267] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0268] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0269] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0270] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0271] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, systems, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0272] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0273] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0274] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0275] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0276] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A smart delivery method for community residents based on delivery robots, characterized in that, The method includes: Receive delivery orders submitted from user terminals, wherein the orders include at least the origin location, the destination location, and item information; Based on a scheduling algorithm, a suitable delivery robot is assigned to the order from multiple delivery robots. Based on the path planning algorithm, a delivery route from the origin to the destination is planned for the assigned delivery robot; Control the delivery robot to move along the delivery path and perform pickup and delivery operations; After delivery is completed, billing is processed based on the order information and the order status is updated.

2. The method according to claim 1, characterized in that, The method of allocating suitable delivery robots to orders based on scheduling algorithms includes: A greedy algorithm is used to select the idle robot closest to the order's origin. And / or, Using a genetic algorithm, when there are multiple orders to be assigned, the goal is to optimize the allocation scheme between multiple orders and multiple robots, with the aim of minimizing the total path length and waiting time.

3. The method according to claim 1, characterized in that, The process of planning delivery routes for the assigned delivery robots includes: The A* algorithm is used for global path planning; And / or, A reinforcement learning model based on deep Q-network (DQN) is used for dynamic path planning to cope with dynamic obstacles during the journey.

4. The method according to claim 1, characterized in that, The control of the delivery robot to perform pickup and delivery operations includes: At pickup and delivery points, user identity verification is conducted through facial recognition and / or QR code scanning. Once the verification is successful, the robot's storage compartment will open to allow for the storage and retrieval of items. During the delivery process, the robot achieves precise positioning and real-time obstacle avoidance by integrating perception data from LiDAR, cameras, IMU, and GPS, and applying the Kalman filter algorithm.

5. The method according to claim 1, characterized in that, The billing process is specifically as follows: The total cost is calculated using a combined billing formula based on delivery distance, item weight, item volume, and delivery time. The billing formula is: Total cost = Basic cost + Distance cost + Weight cost + Volume cost + Peak hour surcharge.

6. A community homeowner intelligent delivery system based on a delivery robot, used to implement the method as described in any one of claims 1-5, characterized in that, The system includes: The user interaction layer, deployed on the user terminal, is used to receive delivery orders and display order status; The core service layer, which communicates with the user interaction layer, includes an order management system, a scheduling system, and a route planning system; At least one delivery robot is communicatively connected to the core service layer to perform physical delivery tasks; The robot control layer, acting as a bridge between the core service layer and the delivery robot, converts path instructions into motion control signals for the robot. The perception and execution layer, integrated into the delivery robot, is used for environmental perception, localization, and human-computer interaction.

7. The system according to claim 6, characterized in that, The scheduling system in the core service layer is configured as follows: A greedy algorithm is used to assign the nearest available robot to a single order. And / or, A genetic algorithm is used to assign robots to multiple orders in batches. The fitness function of the genetic algorithm is constructed based on the total path length, total waiting time and total power consumption.

8. The system according to claim 6, characterized in that, The delivery robot includes: The chassis and drive motor are used to enable the robot to move; A multi-sensor system, including LiDAR, RGB-D camera, IMU and GPS / BeiDou module, is used for environmental perception and positioning; The storage compartment is equipped with an electromagnetic lock and a weighing sensor for securely storing items and verifying their weight. Human-computer interaction interfaces, including speakers, touch screens, and QR code scanners, are used to interact with users.

9. The system according to claim 8, characterized in that, The perception and execution layer is configured as follows: By fusing the positioning data from the lidar, IMU, and GPS using the Kalman filter algorithm, the robot's positioning accuracy is improved. Objects in the environment are identified using the YOLOv5 model, and user faces are recognized using the FaceRecognition library. Real-time local obstacle avoidance is performed using the Dynamic Window Method (DWA).

10. The system according to claim 6, characterized in that, The system also includes a data support layer, comprising: The database is used to store user data, order data, robot status data, and community map data; The big data analytics module is configured to analyze historical order data to identify peak delivery times, popular delivery areas, and user preferences, and to provide data support for operational decisions.

Images