Intelligent trolley tracking obstacle-avoiding delivery system

The intelligent vehicle-based obstacle avoidance delivery system integrates power drive, visual recognition, and Huawei Cloud platform. By combining PID control and adaptive mechanisms, it solves the problem of fixed paths in traditional delivery vehicles, enabling flexible path planning and efficient obstacle avoidance, thereby improving delivery efficiency and system intelligence.

CN118915761AInactive Publication Date: 2024-11-08DONGGUAN CITY COLLEGE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411040597.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional delivery vehicles have fixed routes and inflexible scheduling, making it difficult to adapt to market demands and sudden environmental changes, thus affecting delivery efficiency.

Method used

The intelligent vehicle-based obstacle avoidance delivery system integrates a power drive module, a vision recognition sub-module, a main control unit, a Huawei cloud platform interface module, and an intelligent obstacle avoidance module. It combines PID control and adaptive control mechanisms, and uses OpenMV vision recognition and infrared line-following recognition to achieve path planning and obstacle avoidance.

Benefits of technology

It enables dynamic path planning and efficient obstacle avoidance for vehicles in complex environments, improving system intelligence and response speed, adapting to flexible delivery needs, and ensuring safe and efficient delivery of goods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915761A_ABST
    Figure CN118915761A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of trolley obstacle-avoiding delivery, and discloses an intelligent trolley tracking obstacle-avoiding delivery system, and a module for tracking obstacle-avoiding delivery comprises a power driving module for controlling advancing, retreating, acceleration, deceleration and steering of a trolley, and ensuring accurate control of power output; the visual identification sub-module is used for capturing environment images, identifying paths, obstacles and target positions through an image processing algorithm, and providing advanced navigation capability for the trolley; the main control unit is used for realizing data processing and decision making; the Huawei cloud platform docking module exchanges data with a Huawei cloud platform through a wireless network to realize remote monitoring, task scheduling and map updating; the intelligent avoiding module is used for combining preset map information with an advanced path planning algorithm, so that the trolley can autonomously plan an optimal path from a starting point to a terminal point, avoid obstacles and efficiently distribute goods; and the chip integration module is used for integrating an efficient processing chip into the system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of small vehicle obstacle avoidance delivery, and in particular to an intelligent small vehicle tracking obstacle avoidance delivery system. Background Art

[0002] With the rapid development of the e-commerce industry and the increasing demand of consumers for fast and accurate delivery services, traditional logistics methods are facing huge challenges, especially automated and unmanned delivery technology, which has become an important way to improve logistics efficiency, reduce costs, and shorten delivery time. The maturity and popularization of Internet of Things technology has made the connection between devices closer, and the data collection and processing capabilities have been greatly enhanced. Through the WiFi function and OpenHarmony operating system integrated in the HiSilicon Hi 3861V100 chip, the smart car can communicate with the cloud platform in real time to achieve remote monitoring, data analysis and task scheduling;

[0003] At the same time, the application of OpenMV cameras and corresponding visual recognition technology marks the deep integration of artificial intelligence technology in the field of logistics. Through image recognition and object detection algorithms, the car can identify paths, obstacles, and even locate targets, greatly enhancing its autonomous navigation and obstacle avoidance capabilities. By connecting to the Huawei cloud platform, it means that the car can use the powerful computing resources of the cloud to plan paths, analyze data, and optimize decisions, achieving more efficient task scheduling and resource management. The cloud platform can also provide real-time monitoring, data analysis reports and other services to help companies optimize logistics networks;

[0004] In logistics distribution, many traditional delivery carts rely on pre-set delivery routes and schedules. When market demand or external environment changes, the carts are difficult to adjust and lack flexibility, especially in the face of emergencies such as temporary obstacles and route changes, which affects the delivery efficiency of the carts. Therefore, an intelligent cart tracking and obstacle avoidance delivery system is proposed here. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art, such as fixed paths and inflexible scheduling, and to propose an intelligent vehicle tracking and obstacle avoidance delivery system.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An intelligent vehicle tracking and obstacle avoidance delivery system, the module for tracking and obstacle avoidance delivery includes:

[0008] Power drive module: controls the forward, backward, acceleration, deceleration and steering of the car to ensure precise control of power output;

[0009] Visual recognition submodule: captures environmental images, identifies paths, obstacles, and target locations through image processing algorithms, and provides advanced navigation capabilities for the car;

[0010] Main control unit: realizes data processing and decision making;

[0011] Huawei cloud platform docking module: Exchanges data with Huawei cloud platform through wireless network to achieve remote monitoring, task scheduling, and map updates;

[0012] Intelligent avoidance module: pre-set map information combined with advanced path planning algorithms enables the car to autonomously plan the best path from the starting point to the end point, avoid obstacles and deliver goods efficiently;

[0013] Chip integration module: Integrate high-efficiency processing chips into the system.

[0014] The power drive module is based on the PID controller. For speed control, the ratio of the PID controller is fine-tuned to reduce overshoot and improve response speed.

[0015] An adaptive control mechanism is introduced, and the PID parameters are dynamically adjusted according to the system status during runtime. The adjustment process is as follows:

[0016]

[0017] α is the leakage factor of the integral term, which prevents integral saturation;

[0018] K p e(t): is the proportional term;

[0019] is the integral term;

[0020] is the differential term.

[0021] The visual recognition submodule includes the OpenMV visual recognition unit, which is correctly connected to the microcontroller of the main control unit of the smart car, and the power supply and communication interface are set;

[0022] Initialize the configuration of the OpenMV camera, including resolution setting, frame rate adjustment, and exposure time, to adapt to different lighting conditions and recognition requirements.

[0023] The visual recognition submodule includes an infrared line patrol recognition unit, which uses a highly sensitive and fast-responding infrared reflective sensor to adapt to ground guide lines of different colors and materials.

[0024] According to the size of the car and the width of the ground guide line, the infrared sensors are arranged in the front, middle and back to ensure that they can cover the path in front of the car. At the same time, the sensors on both sides are used for edge detection and correction.

[0025] Fix the sensor on the bottom of the trolley and adjust the angle and spacing to ensure that the sensor can accurately detect the guide line.

[0026] The main control unit includes a chip integration module. The chip integration module uses a chip with WiFi function and supports the OpenHarmony operating system. HiSilicon Hi3861V100 is used as the main controller, responsible for data processing and high-level decision-making;

[0027] Select the appropriate STM32 series microcontroller for motor control and sensor data acquisition low-level real-time control tasks;

[0028] Design the communication interface between the main control unit and STM32, and design the motor and visual recognition sensor drive circuits and connect them to STM32;

[0029] Assemble all hardware modules, including the main control board, STM32 control board, sensors, and motor drivers, and ensure that the physical connections are correct;

[0030] On the basis of hardware integration, software integration is carried out, the communication between the main control unit and STM32 is smooth, the system functions normally, and the Huawei platform docking module is activated.

[0031] The Huawei platform docking module registers an account on Huawei Cloud, creates a project, and configures device access, message queues, and database services;

[0032] Develop cloud platform API to receive device data, issue task instructions, and update map information;

[0033] Implement data processing logic in the cloud, analyze the vehicle's operating status, and optimize the task scheduling strategy for the intelligent avoidance module;

[0034] After completing the integration of hardware and software, the optimized system is deployed in the actual environment.

[0035] The intelligent avoidance module abstracts the actual environment into a two-dimensional or three-dimensional map based on the visual recognition submodule;

[0036] Multiple nodes are set in the graph, each node represents a walkable location, and the edge represents the connection relationship and movement cost between locations;

[0037] Mark inaccessible areas or obstacle locations on the map and eliminate them through route planning;

[0038] The information of obstacles will be reflected in the map construction stage. The position occupied by obstacles is not considered when searching for paths. Every time a node is expanded, it is checked whether the new node is feasible and an obstacle-free path is generated;

[0039] If the car encounters an obstacle that is not foreseen in real time during its movement, it will replan the path, return to the path planning, and search again based on the latest map information.

[0040] The intelligent avoidance module includes a buzzer prompt unit, which installs a sound playback module and a speaker on the car, is compatible with the main control board in the main control unit, and is connected to a power supply;

[0041] Program to read the data of the visual recognition submodule and power monitoring;

[0042] When an obstacle is detected approaching, the task is completed, or the battery level is lower than a preset value, the corresponding event is triggered. Based on the triggering event, the audio playback library or API is called to select and play the preset warning or prompt sound effect.

[0043] The present invention has the following beneficial effects:

[0044] 1. In the present invention, the system integrates multiple chips such as HiSilicon Hi3861V100 chip, STM32 microcontroller and Huawei cloud platform to build a full-stack intelligent architecture from hardware bottom layer to cloud service. This architecture not only realizes the local efficient control of the car, but also allows the cloud to perform global scheduling, path planning, data analysis and system optimization to form a closed-loop feedback system. Compared with traditional independently operated smart cars, this integration method greatly improves the intelligence and response speed of the system, can dynamically adapt to complex and changeable distribution environments, and solves the problems of path rigidification and inflexible scheduling in traditional logistics distribution.

[0045] 2. In the present invention, by combining OpenMV visual recognition with infrared patrol line recognition and other potential sensors, the system realizes a navigation and obstacle avoidance strategy with multi-source information fusion. Visual recognition not only improves the car's ability to understand complex environments, but also complements infrared tracking to ensure stable navigation when there are large changes in lighting or special surface materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a system block diagram of an intelligent vehicle tracking and obstacle avoidance delivery system proposed by the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Embodiment 1

[0049] like Figure 1 As shown, the present invention proposes a smart car tracking and obstacle avoidance delivery system, and the module for tracking and obstacle avoidance delivery includes:

[0050] Power drive module: controls the forward, backward, acceleration, deceleration and steering of the car to ensure precise control of power output;

[0051] Visual recognition submodule: captures environmental images, identifies paths, obstacles, and target locations through image processing algorithms, and provides advanced navigation capabilities for the car;

[0052] Main control unit: realizes data processing and decision making;

[0053] Huawei cloud platform docking module: Exchanges data with Huawei cloud platform through wireless network to achieve remote monitoring, task scheduling, and map updates;

[0054] Intelligent avoidance module: pre-set map information combined with advanced path planning algorithms enables the car to autonomously plan the best path from the starting point to the end point, avoid obstacles and deliver goods efficiently;

[0055] Chip integration module: Integrate high-efficiency processing chips into the system.

[0056] The power drive module is based on the PID controller. For speed control, the ratio of the PID controller is fine-tuned to reduce overshoot and improve response speed.

[0057] An adaptive control mechanism is introduced, and the PID parameters are dynamically adjusted according to the system status during runtime. The adjustment process is as follows:

[0058]

[0059] α is the leakage factor of the integral term, which prevents integral saturation;

[0060] K p e(t): is the proportional term;

[0061] is the integral term;

[0062] is the differential term.

[0063] The visual recognition submodule includes the OpenMV visual recognition unit, which is correctly connected to the microcontroller of the main control unit of the smart car, and the power supply and communication interface are set;

[0064] Initialize the configuration of the OpenMV camera, including resolution setting, frame rate adjustment, and exposure time, to adapt to different lighting conditions and recognition requirements.

[0065] The visual recognition submodule includes an infrared line patrol recognition unit, which uses a highly sensitive and fast-responding infrared reflective sensor to adapt to ground guide lines of different colors and materials.

[0066] According to the size of the car and the width of the ground guide line, the infrared sensors are arranged in the front, middle and back to ensure that they can cover the path in front of the car. At the same time, the sensors on both sides are used for edge detection and correction.

[0067] Fix the sensor on the bottom of the trolley and adjust the angle and spacing to ensure that the sensor can accurately detect the guide line.

[0068] In this embodiment, in the intelligent vehicle tracking and obstacle avoidance delivery system, the formula is:

[0069]

[0070] This shows the application of a PID control strategy to adjust the motion control of the car to ensure that it can accurately follow the predetermined path while effectively avoiding obstacles:

[0071] u(t): represents the output of the control signal. For the car, it is the PWM signal sent to the motor to control the speed and direction of the car in response to the current deviation;

[0072] e(t): represents the error between the actual state at the current moment and the target state, for example, the deviation between the current position of the car and the ideal trajectory position, or the angular difference between the car's direction and the target direction;

[0073] K: Proportional gain, which determines the immediate response to the current error. In the car system, a larger K can make the car respond quickly to the deviation;

[0074] The integral term accumulates past errors to eliminate steady-state errors. K is the integral gain. (1-α) is used to prevent integral saturation (i.e., excessive integral accumulation causes the control output to exceed the range) and ensure control stability. During tracking, the integral term helps the car gradually adjust to accurately match the path.

[0075] The differential term reflects the speed of error change, which helps to respond to the changing trend of the error in advance and reduce overshoot. In the car control system, it helps the car respond more smoothly to path changes or obstacles and avoid drastic movement changes;

[0076] In summary, in the smart car system, the PID control formula helps the car dynamically adjust its behavior to accurately follow the path and effectively avoid obstacles, while maintaining system stability and response speed, ensuring that the goods can be safely and efficiently delivered from the starting point to the designated location. p ,K i ,K d The values ​​of and α can optimize the control performance of the car to meet different operating requirements and environmental changes.

[0077] Embodiment 2

[0078] like Figure 1 As shown, based on the first embodiment, the main control unit includes a chip integration module, the chip integration module uses a chip with WiFi function and supports the OpenHarmony operating system, and uses HiSilicon Hi3861V100 as the main controller, which is responsible for data processing and high-level decision-making;

[0079] Select the appropriate STM32 series microcontroller for motor control and sensor data acquisition low-level real-time control tasks;

[0080] Design the communication interface between the main control unit and STM32, and design the motor and visual recognition sensor drive circuits and connect them to STM32;

[0081] Assemble all hardware modules, including the main control board, STM32 control board, sensors, and motor drivers, and ensure that the physical connections are correct;

[0082] On the basis of hardware integration, software integration is carried out, the communication between the main control unit and STM32 is smooth, the system functions normally, and the Huawei platform docking module is activated.

[0083] The Huawei platform docking module registers an account on Huawei Cloud, creates a project, and configures device access, message queues, and database services;

[0084] Develop cloud platform API to receive device data, issue task instructions, and update map information;

[0085] Implement data processing logic in the cloud, analyze the vehicle's operating status, and optimize the task scheduling strategy for the intelligent avoidance module;

[0086] After completing the integration of hardware and software, the optimized system is deployed in the actual environment.

[0087] The intelligent avoidance module abstracts the actual environment into a two-dimensional or three-dimensional map based on the visual recognition submodule;

[0088] Multiple nodes are set in the graph, each node represents a walkable location, and the edge represents the connection relationship and movement cost between locations;

[0089] Mark inaccessible areas or obstacle locations on the map and eliminate them through route planning;

[0090] The information of obstacles will be reflected in the map construction stage. The position occupied by obstacles is not considered when searching for paths. Every time a node is expanded, it is checked whether the new node is feasible and an obstacle-free path is generated;

[0091] If the car encounters an obstacle that is not foreseen in real time during its movement, it will replan the path, return to the path planning, and search again based on the latest map information.

[0092] The intelligent avoidance module includes a buzzer prompt unit, which installs a sound playback module and a speaker on the car, is compatible with the main control board in the main control unit, and is connected to a power supply;

[0093] Program to read the data of the visual recognition submodule and power monitoring;

[0094] When an obstacle is detected approaching, the task is completed, or the battery level is lower than a preset value, the corresponding event is triggered. Based on the triggering event, the audio playback library or API is called to select and play the preset warning or prompt sound effect.

[0095] In this embodiment, when the car is running for the first time, LiDAR or camera is used for simultaneous positioning and map construction. The generated environment map is stored in the car or in the cloud for subsequent path planning. Visual landmark recognition or previously established environmental feature matching is used for precise positioning. The constructed map is divided into a grid or graph structure, where each node represents a drivable position and the edge represents the connection path and its cost such as distance and turning difficulty;

[0096] Input the starting point, end point, and map information including the location of obstacles, and output a series of nodes representing the path the car should follow. The sensor continuously monitors the surrounding environment and identifies obstacles. Once a new obstacle is detected, the path is immediately replanned according to the current environmental status. The obstacle avoidance algorithm is used to maintain a safe distance from obstacles to ensure driving safety. According to the planned path, specific speed and steering instructions are generated. The embedded system controls the motor to execute the instructions to achieve precise tracking and obstacle avoidance actions. After arriving at the designated location, the cargo pick-up and placement operations are performed.

[0097] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent vehicle tracking and obstacle avoidance delivery system, characterized in that: The modules used for tracking and obstacle avoidance delivery include: Power drive module: controls the forward, backward, acceleration, deceleration and steering of the car to ensure precise control of power output; Visual recognition submodule: captures environmental images, identifies paths, obstacles, and target locations through image processing algorithms, and provides advanced navigation capabilities for the car; Main control unit: realizes data processing and decision making; Huawei cloud platform docking module: Exchanges data with Huawei cloud platform through wireless network to achieve remote monitoring, task scheduling, and map updates; Intelligent avoidance module: pre-set map information combined with advanced path planning algorithms enables the car to autonomously plan the best path from the starting point to the end point, avoid obstacles and deliver goods efficiently; Chip integration module: Integrate high-efficiency processing chips into the system.

2. According to claim 1, the intelligent vehicle tracking and obstacle avoidance delivery system is characterized in that: The power drive module is based on the PID controller. For speed control, the ratio of the PID controller is fine-tuned to reduce overshoot and improve response speed. An adaptive control mechanism is introduced, and the PID parameters are dynamically adjusted according to the system status during operation. The adjustment process is as follows: α is the leakage factor of the integral term, which prevents integral saturation; K p e(t): is the proportional term; is the integral term; is the differential term.

3. The intelligent vehicle tracking and obstacle avoidance delivery system according to claim 1 is characterized in that: The visual recognition submodule includes the OpenMV visual recognition unit, which is correctly connected to the microcontroller of the main control unit of the smart car, and the power supply and communication interface are set; Initialize the configuration of the OpenMV camera, including resolution setting, frame rate adjustment, and exposure time, to adapt to different lighting conditions and recognition requirements.

4. The intelligent vehicle tracking and obstacle avoidance delivery system according to claim 1 is characterized in that: The visual recognition submodule includes an infrared line patrol recognition unit, which uses a highly sensitive and fast-responding infrared reflective sensor to adapt to ground guide lines of different colors and materials. According to the size of the car and the width of the ground guide line, the infrared sensors are arranged in the front, middle and back to ensure that they can cover the path in front of the car. At the same time, the sensors on both sides are used for edge detection and correction. Fix the sensor on the bottom of the trolley and adjust the angle and spacing to ensure that the sensor can accurately detect the guide line.

5. The intelligent vehicle tracking and obstacle avoidance delivery system according to claim 1 is characterized in that: The main control unit includes a chip integration module. The chip integration module uses a chip with WiFi function and supports the OpenHarmony operating system. HiSilicon Hi3861V100 is used as the main controller, responsible for data processing and high-level decision-making; Select the appropriate STM32 series microcontroller for motor control and sensor data acquisition low-level real-time control tasks; Design the communication interface between the main control unit and STM32, and design the motor and visual recognition sensor drive circuits and connect them to STM32; Assemble all hardware modules, including the main control board, STM32 control board, sensors, and motor drivers, and ensure that the physical connections are correct; On the basis of hardware integration, software integration is carried out, the communication between the main control unit and STM32 is smooth, the system functions normally, and the Huawei platform docking module is activated.

6. The intelligent vehicle tracking and obstacle avoidance delivery system according to claim 1 is characterized in that: The Huawei platform docking module registers an account on Huawei Cloud, creates a project, and configures device access, message queues, and database services; Develop cloud platform API to receive device data, issue task instructions, and update map information; Implement data processing logic in the cloud, analyze the vehicle's operating status, and optimize the task scheduling strategy for the intelligent avoidance module; After completing the integration of hardware and software, the optimized system is deployed in the actual environment.

7. The intelligent vehicle tracking and obstacle avoidance delivery system according to claim 1 is characterized in that: The intelligent avoidance module abstracts the actual environment into a two-dimensional or three-dimensional map based on the visual recognition submodule; Multiple nodes are set in the graph, each node represents a walkable location, and the edge represents the connection relationship and movement cost between locations; Mark inaccessible areas or obstacle locations on the map and eliminate them through route planning; The information of obstacles will be reflected in the map construction stage. The position occupied by obstacles is not considered when searching for paths. Every time a node is expanded, it is checked whether the new node is feasible and an obstacle-free path is generated; If the car encounters an obstacle that is not foreseen in real time during its movement, it will replan the path, return to the path planning, and search again based on the latest map information.

8. The intelligent vehicle tracking and obstacle avoidance delivery system according to claim 1 is characterized in that: The intelligent avoidance module includes a buzzer prompt unit, which installs a sound playback module and a speaker on the car, is compatible with the main control board in the main control unit, and is connected to a power supply; Program to read the data of the visual recognition submodule and power monitoring; When an obstacle is detected approaching, the task is completed, or the battery level is lower than a preset value, the corresponding event is triggered. Based on the triggering event, the audio playback library or API is called to select and play the preset warning or prompt sound effect.