Mobile AI energy storage charging robot

Abstract

The invention discloses a mobile AI energy storage charging robot. The mobile AI energy storage charging robot comprises an AI robot main body and a charging module, the AI robot main body comprises a mobile platform, an energy storage module, a communication module, a navigation and sensor module and an AI control module; the moving platform is used for assisting the robot to move in different terrains; the energy storage module is used for storing energy and supporting bidirectional charging and discharging; the AI control module is used for realizing the functions of task scheduling, energy distribution and path planning; the navigation and sensor module is used for environment perception and obstacle detection; the communication module is used for data exchange and cooperation; the charging module is used for charging target equipment; the charging module supports quick charging and can dynamically adjust charging current and voltage based on the battery state of the target equipment or the vehicle; the AI control module optimizes a charging task and a path through a deep learning model, and efficient task scheduling and energy utilization optimization are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of charging robots, and in particular to a mobile AI energy storage charging robot. Background Art

[0002] With the rapid development of new energy vehicles and smart devices, the demand for charging is increasing, especially in remote areas or cities where there is a lack of charging facilities. Traditional fixed charging stations face many challenges. Fixed charging stations require expensive infrastructure construction and are difficult to flexibly meet the temporary charging needs of vehicles or equipment. In addition, most existing charging technologies are one-way charging, that is, they can only provide electrical energy but cannot store excess electrical energy, which has imposed certain restrictions on the utilization efficiency of new energy. At the same time, charging speed and efficiency are also a major bottleneck in existing charging technologies. Most existing charging devices rely on wired charging methods. Although wireless charging technology has gradually developed, its transmission efficiency and stability are not yet fully mature. In addition, traditional charging systems lack intelligent control means and cannot dynamically adjust charging strategies according to external conditions such as the battery status of the device or vehicle and the ambient temperature, resulting in low efficiency and high losses in the charging process.

[0003] There are some existing solutions to the above problems, such as the introduction of portable charging devices and intelligent scheduling systems, but these technical solutions have the following disadvantages: First, portable charging devices are often limited by battery capacity and endurance, and cannot provide charging support for multiple devices for a long time or efficiently; second, the existing intelligent scheduling systems are mostly focused on fixed scenes, lack dynamic path planning and energy scheduling capabilities, and are difficult to adapt to complex urban environments or remote operation scenes. In order to solve the above problems, designing a mobile, AI-controlled, autonomously perceiving and planning energy storage charging robot has become an important research direction for improving the utilization rate of new energy, optimizing the charging process, and improving user experience. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] Therefore, in order to solve the above technical problems, the present invention provides the following technical solutions: a mobile AI energy storage charging robot, comprising an AI robot body and a charging module;

[0006] The main body of the AI ​​robot includes a mobile platform, an energy storage module, a communication module, a navigation and sensor module, and an AI control module. The mobile platform is used to assist the robot in moving in different terrains. The energy storage module is used for energy storage and supports bidirectional charging and discharging. The AI ​​control module is used to implement task scheduling, energy distribution, and path planning. The navigation and sensor module is used for environmental perception and obstacle detection. The communication module is used to exchange and collaborate with other robots and the cloud.

[0007] The charging module is used to charge the target device.

[0008] As a preferred solution of the mobile AI energy storage and charging robot described in the present invention, the energy storage module is arranged on the mobile platform, and the energy storage module is a high-efficiency lithium battery or a solid-state battery with high-efficiency energy storage and discharge functions.

[0009] As a preferred solution of the mobile AI energy storage and charging robot described in the present invention, the navigation and sensor module includes a laser radar, a camera, an ultrasonic sensor, etc., which are used for environmental perception and vehicle identification.

[0010] As a preferred solution for the mobile AI energy storage and charging robot described in the present invention, the communication module is used to interact with the cloud and other robots, and supports networks such as G and Wi-Fi.

[0011] As a preferred solution of the mobile AI energy storage charging robot described in the present invention, wherein: the charging module includes a charging plug, and the charging plug is arranged on the charging seat; the charging seat is connected to a multi-axis robotic arm, and the multi-axis robotic arm is fixed on the mobile platform; a smoke sensor is arranged on the charging seat, and the smoke sensor is connected to a pump body, and the feed side of the pump body is connected to a fire extinguishing tank through a pipeline, and the discharge side of the pump body is connected to a fire extinguishing nozzle through a pipeline; a nozzle mounting groove for use with the fire extinguishing nozzle is provided at the front end of the charging seat, and a sealing rotary plate for protecting the fire extinguishing nozzle is arranged on the nozzle mounting groove, and the sealing rotary plate is connected to a motor for driving it to rotate and exposing the fire extinguishing nozzle. The charging module includes a charging plug, and the charging plug is arranged on the charging seat; the charging seat is connected to a multi-axis robotic arm, and the multi-axis robotic arm Fixed on the mobile platform; a smoke sensor is arranged on the charging seat, the smoke sensor is connected to the pump body, the feed side of the pump body is connected to the fire extinguishing tank through a pipeline, and the discharge side of the pump body is connected to the fire extinguishing nozzle through a pipeline; a nozzle mounting groove for use with the fire extinguishing nozzle is opened at the front end of the charging seat, and a sealing rotary plate for protecting the fire extinguishing nozzle is arranged on the nozzle mounting groove, and the sealing rotary plate is connected to a motor for driving it to rotate and expose the fire extinguishing nozzle; a rotating shaft is fixedly connected to the sealing rotary plate, and a rotating gear is arranged on the rotating shaft, and the rotating gear is meshingly connected to a driving gear ring, and the driving gear ring is meshingly connected to a driving gear, and the driving gear is connected to a motor; an annular tooth groove group is arranged in an annular array on the circumferential inner wall of the driving gear ring, and the annular tooth groove group is meshingly connected to the driving gear and the rotating gear.

[0012] As a preferred solution of the mobile AI energy storage charging robot of the present invention, the charging module supports fast charging and dynamically adjusts the charging current based on the battery status (SoC, SoH and temperature) of the vehicle. The specific adjustment formula is:

[0013] Among them, I opt is the optimal charging current, C i Indicates the current battery capacity of the vehicle; E i Indicates the current remaining power of the vehicle; T i Indicates the required charging time of the current vehicle; f(SoC,SoH,T) is a coefficient adjusted by the vehicle's current battery status (SoC and SoH) and temperature T, and the coefficient is dynamically optimized according to the battery's health, remaining power and ambient temperature, and T represents temperature.

[0014] As a preferred solution of the mobile AI energy storage charging robot of the present invention, the charging module supports fast charging and dynamically adjusts the charging voltage based on the battery status (SoC, SoH and temperature) of the vehicle. The specific adjustment steps are as follows:

[0015] If SoC is less than 80%, constant current charging is adopted and the charging current is maintained at I opt ;

[0016] When SoC>80%, switch to constant voltage charging and keep the voltage at V opt ;

[0017] V opt The calculation formula is: V opt =V nom +k·(1-SoC);

[0018] Among them, V nom is the nominal voltage of the battery and k is the charge factor of the battery.

[0019] As a preferred solution for the mobile AI energy storage charging robot described in the present invention, the AI ​​control module includes a task scheduling unit and an optimization control unit. The task scheduling unit is used to allocate charging tasks according to the priority and charging requirements of the vehicle, and the optimization control unit is used to calculate and optimize the robot's moving path in real time.

[0020] As a preferred solution of the mobile AI energy storage charging robot described in the present invention, the task scheduling unit optimizes the charging task based on the deep learning model, generates the best dynamic power allocation strategy for the charging station, and ensures the optimal allocation of power resources; the specific steps are as follows:

[0021] Preset the following variables: P j represents the priority (set according to vehicle type and user needs, range [0,1]); α represents the temperature coefficient; R j represents the energy demand rate, defined as D i represents the remaining power of the energy storage charging robot; N represents the number of vehicles to be charged; β i represents the coefficient of energy loss (related to environmental factors); F represents the total amount of power classification; then, the task scheduling unit generates the optimal dynamic power allocation strategy according to the following formula, and the calculation formula is as follows:

[0022]

[0023] In this formula, P opt,i : The optimal dynamic power distribution of the i-th vehicle; In the integral term, the energy demand rate R of each vehicle is j , Priority P j 、Remaining power C j -E j and the influence of time, through Reflects the attenuation of charging efficiency and adds normalization correction of temperature factors; Denominator: Normalizes the charging weights of all vehicles to ensure the relative fairness of the entire system in allocating electricity; Integral term: Calculates the cumulative effect of energy distribution within time T to ensure changes over time; Ambient temperature normalization factor, through the normalization function Indicates the impact of the environment on charging time;

[0024] Formula value range: between [0,1], indicating the proportion of charging distribution. Through the normalized power distribution mechanism, the charging efficiency and energy utilization of each vehicle are maximized. Specifically, 0 means no power is allocated to the vehicle (possibly because of sufficient power or low task priority); 1 means allocating maximum power to the vehicle (possibly because of severe power shortage or high task priority).

[0025] As a preferred solution of the mobile AI energy storage charging robot of the present invention, wherein: the optimization control unit optimizes the charging path based on the deep learning model to generate the optimal moving path of the robot, taking into account energy consumption, path length and task priority; the specific steps are as follows:

[0026] The following variables and parameters are preset: i The attenuation coefficient related to vehicle energy consumption and environmental factors; (x, y) The spatial coordinates of the charging robot, indicating its mobile position in the smart city; γ i Energy loss coefficient related to vehicle and environment; β i The coefficient of energy loss depends on factors such as ambient temperature;

[0027] Determine the multiple objectives that need to be optimized to simultaneously minimize path length, energy consumption, and maximize task priority, while ensuring that the robot has enough power to complete the task;

[0028] Then, the calculation formula of the optimal moving path for multi-objective optimization is as follows:

[0029]

[0030] Task priority function T i (x, y, t): represents the priority of the task point that the robot needs to reach at a certain position (x, y) at time t. This function is related to the importance of the task, deadline, etc.; Energy consumption function E i (x, y, t): represents the energy consumption required for the robot to move to the position (x, y), which depends on the current position, speed v and terrain characteristics; path length function D(x, y): represents the distance from the current point to the target point of the robot, which is calculated based on Euclidean distance or Manhattan distance; charging station location function C(x c ,yc ): indicates the relative position of the charging station. The robot can choose to charge midway during the mission to increase the power; AI learning optimization function L(t): AI optimizes the path and energy use strategy through historical data and real-time feedback; the power belongs to the function R i (t): represents the remaining power of the robot at time t; Travel time τ(x, y, v): represents the time required for the robot to travel to position (x, y) at speed v; Integral representation: This formula is a time integral, which represents the optimal travel path and strategy that the robot needs to consider at time t; The time dimension allows the robot to adjust according to dynamic power, task and path information; The task priority part T i (x(t), y(t), τ(x, y, v)): The robot prioritizes high-priority tasks. The exponential term indicates that the importance of the task gradually decreases over time. The more urgent the task, the higher the priority weight; energy consumption part The exponential function represents the impact of energy consumption on path planning. The greater the energy consumption, the more the robot needs to consider the balance between path and energy. Path length D(x(t), y(t)): Path length directly affects the robot's travel time and energy consumption. The shorter the path, the better. Charging station C(x c ,y c ): The location of the charging station will affect the path planning. If the robot is low on power, the AI ​​algorithm will give priority to recharging at the charging station; AI learning part L(t): Through the AI ​​learning optimization function, the robot can continuously adjust its strategy based on historical data and path feedback to improve task execution efficiency;

[0031] Formula F opt The range of (t): The range of this formula represents the comprehensive optimization degree of the robot at time t; the smaller the range, the more favorable the robot has found a route that can maximize the task priority while minimizing the path length and energy consumption.

[0032] Beneficial effects of the present invention:

[0033] 1. The mobile platform in the present invention can not only adapt to complex terrain conditions, but also combines navigation and sensor modules to perform environmental perception and obstacle detection. This design allows the robot to move autonomously and plan paths efficiently to meet charging needs in various scenarios. Compared with traditional fixed charging stations, mobility greatly improves the coverage of charging services, especially in areas or scenarios where fixed charging facilities are lacking, and can provide more flexible charging solutions.

[0034] 2. The energy storage module of the present invention uses high-efficiency lithium batteries or solid-state batteries and has bidirectional charging and discharging functions; this means that the robot can not only provide charging for other equipment or vehicles, but also store excess electrical energy itself and even feed the stored electrical energy back to the power grid; this bidirectional energy management method improves the utilization efficiency of energy, avoids energy waste, and further improves the environmental performance of the system.

[0035] 3. The charging module of the present invention supports fast charging and can dynamically adjust the charging current and voltage based on the battery status of the target device or vehicle (including the battery health status SoH, the remaining power SoC and the temperature T); compared with the traditional fixed charging method, the present invention improves the safety and efficiency of charging through intelligent adjustment; especially when the ambient temperature and battery condition are complex and changeable, the present invention can adapt to different external conditions, provide the best charging strategy, and extend the service life of the device and the battery.

[0036] 4. The AI ​​control module of the present invention optimizes charging tasks and paths through a deep learning model. AI can not only assign charging tasks according to vehicle priority, energy demand and other conditions, but also calculate the optimal mobile path in real time. The path planning algorithm not only takes into account energy consumption and path length, but also combines environmental factors and task priorities to achieve efficient task scheduling and energy utilization optimization; in a dynamically changing environment, the robot can continuously adjust its strategy based on real-time feedback, thereby improving task execution efficiency and energy utilization efficiency.

[0037] 5. The communication module of the present invention supports high-speed networks such as 5G and Wi-Fi, and can exchange and collaborate with other robots and cloud servers. By working in collaboration with the cloud, the robot can obtain more environmental information and task scheduling optimization suggestions, thereby further improving the overall performance of the system. In addition, the collaboration between multiple robots can achieve large-scale charging task allocation and path coordination, reduce system delays and energy waste, and enhance the reliability and flexibility of the overall system. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0039] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0040] Figure 2 It is a schematic diagram of the overall structure of the present invention.

[0041] Figure 3 It is a schematic diagram of a partially enlarged structure of the present invention.

[0042] Figure 4 It is a schematic diagram of the installation structure of the sealing rotary plate of the present invention.

[0043] Figure 5 It is a schematic diagram of the installation structure of the fire extinguishing nozzle of the present invention.

[0044] In the figure: 100, AI robot body; 101, mobile platform; 102, energy storage module; 103, communication module; 104, navigation and sensor module; 105, AI control module;

[0045] 200. Charging module; 201. Charging plug; 202. Charging base; 203. Multi-axis robotic arm; 204. Smoke sensor; 205. Pump body; 206. Fire sprinkler; 207. Sprinkler mounting slot; 208. Sealing rotary plate; 209. Motor; 210. Rotating gear; 211. Driving gear ring; 212. Driving gear. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0049] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0050] Example 1

[0051] Reference Figure 1, which is the first embodiment of the present invention, provides a mobile AI energy storage charging robot, including an AI robot body 100 and a charging module 200;

[0052] The AI ​​robot body 100 includes a mobile platform 101, an energy storage module 102, a communication module 103, a navigation and sensor module 104, and an AI control module 105; wherein the mobile platform 101 is used to assist the robot in moving in different terrains; the energy storage module 102 is a high-efficiency lithium battery or solid-state battery, which has high-efficiency energy storage and discharge functions, is used for energy storage, and supports bidirectional charging and discharging; the AI ​​control module 105 is used to implement task scheduling, energy distribution, and path planning functions; the navigation and sensor module 104 includes a laser radar, a camera, and an ultrasonic Sensors, etc., for environmental perception and vehicle identification; communication module 103, for data exchange and collaboration with other robots and the cloud; communication module 103 is used to interact with the cloud and other robots, and supports 5G, Wi-Fi and other networks; communication module 103 realizes real-time communication of robots through a low-latency local area network, ensuring information synchronization and task collaboration between robots; specifically, by equipping each robot with an AI chip, supporting a cluster intelligent scheduling system, and using deep learning algorithms to analyze the current status of all robots, including power, task priority, location, and charging target device requirements.

[0053] A charging module 200 is used to charge the target device;

[0054] The charging module 200 includes a charging plug 201, which is arranged on a charging seat 202; the charging seat 202 is connected to a multi-axis robot 203, and the multi-axis robot 203 is fixed on the mobile platform 101; a smoke sensor 204 is arranged on the charging seat 202, and the smoke sensor 204 is connected to a pump body 205, and the feed side of the pump body 205 is connected to a fire extinguishing tank through a pipeline, and the discharge side of the pump body 205 is connected to a fire extinguishing nozzle 206 through a pipeline; the front end of the charging seat 202 is provided with a nozzle installation groove 207 used in conjunction with the fire extinguishing nozzle 206, and the nozzle installation groove 204 is connected to the pump body 205 through a pipeline. 07 is provided with a sealing rotary plate 208 for protecting the fire extinguishing nozzle 206, and the sealing rotary plate 208 is connected to a motor 209 for driving it to rotate and expose the fire extinguishing nozzle 206; the sealing rotary plate 208 is fixedly connected to a rotating shaft, and a rotating gear 210 is arranged on the rotating shaft, and the rotating gear 210 is meshingly connected to a driving gear ring 211, and the driving gear ring 211 is meshingly connected to a driving gear 212, and the driving gear 212 is connected to the motor 209; an annular tooth groove group is arranged in an annular array on the circumferential inner wall of the driving gear ring 211, and the annular tooth groove group is meshingly connected to the driving gear 212 and the rotating gear 210;

[0055] Among them, in actual use, the mobile platform 101 of the AI ​​robot body 100 enables the robot to move, and performs environmental perception and obstacle detection through the navigation and sensor module 104 to ensure that the robot can accurately move to the vicinity of the device that needs to be charged; the charging module 200 on the robot can control the charging plug 201 to dock with the charging interface of the target device through the multi-axis robotic arm 203, ensuring the smooth progress of the charging process.

[0056] During the charging process, the smoke sensor 204 equipped on the charging seat 202 is used to monitor in real time whether abnormal smoke occurs during the charging process. If the smoke sensor 204 detects an abnormality, a signal is sent to the control end of the pump body 205 and the motor 209, so that the motor 209 controls the driving gear 212 to rotate, the driving gear 212 drives the driving gear ring 211 to rotate, the driving gear ring 211 drives the rotating gear 210 to rotate, and the rotating gear 210 drives the sealing rotary plate 208 to rotate 180° through the rotating shaft to expose the fire extinguishing nozzle 201; at the same time, the pump body 205 is started, and the fire extinguishing agent in the fire extinguishing tank is transported to the fire extinguishing nozzle 206 through the pipeline, and the fire extinguishing agent is sprayed to the surrounding area of ​​the charging plug 201 (the fire source) through the fire extinguishing nozzle 206 to extinguish the fire.

[0057] In this embodiment, the design of the sealing rotary plate 208 enables the fire extinguishing nozzle 206 to be effectively protected when not in use, plays a role in preventing dust and preventing the nozzle hole from being blocked, thereby affecting the fire extinguishing effect.

[0058] In addition, the charging module 200 supports fast charging and dynamically adjusts the charging current and charging voltage based on the vehicle's battery status (SoC, SoH, and temperature);

[0059] The charging current regulation formula is:

[0060] Among them, I opt is the optimal charging current, C i Indicates the current battery capacity of the vehicle; E i Indicates the current remaining power of the vehicle; T i Indicates the required charging time of the current vehicle; f(SoC,SoH,T) is a coefficient adjusted by the vehicle's current battery status (SoC and SoH) and temperature T, and the coefficient is dynamically optimized according to the battery's health, remaining power and ambient temperature, and T represents temperature.

[0061] The specific steps for adjusting the charging voltage are as follows:

[0062] If SoC is less than 80%, constant current charging is adopted and the charging current is maintained at I opt ;

[0063] When SoC>80%, switch to constant voltage charging and keep the voltage at V opt ;

[0064] V opt The calculation formula is: V opt =V nom +k·(1-SoC);

[0065] Among them, V nom is the nominal voltage of the battery and k is the charge factor of the battery.

[0066] The AI ​​control module 105 is used to implement the functions of task scheduling, energy allocation and path planning; the AI ​​control module 105 includes a task scheduling unit and an optimization control unit, the task scheduling unit is used to allocate charging tasks according to the priority and charging demand of the vehicle, and the optimization control unit is used to calculate and optimize the movement path of the robot in real time;

[0067] Specifically, the task scheduling unit optimizes the charging task based on the deep learning model, generates the best dynamic power allocation strategy for the charging station, and ensures the optimal allocation of power resources; the specific steps are as follows:

[0068] Preset the following variables: P j represents the priority (set according to vehicle type and user needs, range [0,1]); α represents the temperature coefficient; R j represents the energy demand rate, defined as D i represents the remaining power of the energy storage charging robot; N represents the number of vehicles to be charged; β i represents the coefficient of energy loss (related to environmental factors); F represents the total amount of power classification; then, the task scheduling unit generates the optimal dynamic power allocation strategy according to the following formula, and the calculation formula is as follows:

[0069]

[0070] In this formula, P opt,i : The optimal dynamic power distribution of the i-th vehicle; In the integral term, the energy demand rate R of each vehicle is j , Priority P j 、Remaining power C j -E j and the influence of time, through Reflects the attenuation of charging efficiency and adds normalization correction of temperature factors; Denominator: Normalizes the charging weights of all vehicles to ensure the relative fairness of the entire system in allocating electricity; Integral term: Calculates the cumulative effect of energy distribution within time T to ensure changes over time; Ambient temperature normalization factor, through the normalization function Indicates the impact of the environment on charging time;

[0071] Formula value range: between [0,1], indicating the proportion of charging allocation. Through the normalized power allocation mechanism, the charging efficiency and energy utilization of each vehicle are maximized. Specifically, 0 means no power is allocated to the vehicle (possibly because the power is sufficient or the task priority is low); 1 means the maximum power is allocated to the vehicle (possibly because the power is seriously insufficient or the task priority is high).

[0072] The optimization control unit optimizes the charging path based on the deep learning model and generates the best movement path for the robot, taking into account energy consumption, path length and task priority; the specific steps are as follows:

[0073] The following variables and parameters are preset: i The attenuation coefficient related to vehicle energy consumption and environmental factors; (x, y) The spatial coordinates of the charging robot, indicating its mobile position in the smart city; γ i Energy loss coefficient related to vehicle and environment; β i The coefficient of energy loss depends on factors such as ambient temperature;

[0074] Determine the multiple objectives that need to be optimized to simultaneously minimize path length, energy consumption, and maximize task priority, while ensuring that the robot has enough power to complete the task;

[0075] Then, the calculation formula of the optimal moving path for multi-objective optimization is as follows:

[0076]

[0077] Task priority function T i (x, y, t): represents the priority of the task point that the robot needs to reach at a certain position (x, y) at time t. This function is related to the importance of the task, deadline, etc.; Energy consumption function E i (x, y, t): represents the energy consumption required for the robot to move to the position (x, y), which depends on the current position, speed v and terrain characteristics; path length function D(x, y): represents the distance from the current point to the target point of the robot, which is calculated based on Euclidean distance or Manhattan distance; charging station location function C(x c ,y c ): indicates the relative position of the charging station. The robot can choose to charge midway during the mission to increase the power; AI learning optimization function L(t): AI optimizes the path and energy use strategy through historical data and real-time feedback; the power belongs to the function R i(t): represents the remaining power of the robot at time t; Travel time τ(x, y, v): represents the time required for the robot to travel to position (x, y) at speed v; Integral representation: This formula is a time integral, which represents the optimal travel path and strategy that the robot needs to consider at time t; The time dimension allows the robot to adjust according to dynamic power, task and path information; The task priority part T i (x(t), y(t), τ(x, y, v)): The robot prioritizes high-priority tasks. The exponential term indicates that the importance of the task gradually decreases over time. The more urgent the task, the higher the priority weight; energy consumption part The exponential function represents the impact of energy consumption on path planning. The greater the energy consumption, the more the robot needs to consider the balance between path and energy. Path length D(x(t), y(t)): Path length directly affects the robot's travel time and energy consumption. The shorter the path, the better. Charging station C(x c ,y c ): The location of the charging station will affect the path planning. If the robot is low on power, the AI ​​algorithm will give priority to recharging at the charging station; AI learning part L(t): Through the AI ​​learning optimization function, the robot can continuously adjust its strategy based on historical data and path feedback to improve task execution efficiency;

[0078] Formula F opt The range of (t): The range of this formula represents the comprehensive optimization degree of the robot at time t; the smaller the range, the more favorable the robot has found a route that can maximize the task priority while minimizing the path length and energy consumption.

[0079] Example 2

[0080] This is the second embodiment of the present invention, which is different from the first embodiment in that in order to verify the beneficial effects of the present invention (especially its technical advantages in task scheduling, charging efficiency, and mobile path optimization), experimental comparison data between the present invention and the charging robot in the prior art are provided.

[0081] This embodiment includes a mobile AI energy storage charging robot of the present invention and a traditional charging robot based on simple rule scheduling; the experimental scenario is set in a simulated smart city environment, the scenario includes complex road conditions, multiple new energy vehicles that need to be charged, and multiple charging stations; the evaluation indicators of this embodiment include charging efficiency, mobile path optimization efficiency, energy consumption, and the total time required for the robot to complete the task.

[0082] The steps of the embodiment are as follows:

[0083] Scene arrangement: The experimental scene is arranged as a parking lot containing 10 new energy vehicles. The power of each vehicle ranges from 20% to 80%. The vehicles are randomly distributed and the distance from the robot parking point ranges from 50 meters to 500 meters. The experimental scene sets multiple obstacles and an undulating terrain to simulate the complex terrain in actual applications.

[0084] Charging demand setting: The charging demand of each vehicle is evaluated according to the remaining battery capacity (SoC) and health state (SoH). Different charging priorities are assigned according to the remaining battery capacity of the vehicle and the urgency of the task; the priority ranges from 0.2 to 0.9. Vehicles with high priority need to complete charging in a short time to ensure the smooth progress of subsequent tasks.

[0085] Robot task scheduling: The AI ​​control module 105 of the present invention calculates the charging requirements of all vehicles in real time through a deep learning algorithm and generates a task priority list; the robot automatically generates the optimal power distribution strategy based on task priority, vehicle location and current vehicle status (battery power, health status, temperature, etc.) to ensure maximum energy utilization.

[0086] Path planning and execution: The robot uses an AI path optimization algorithm to plan the optimal route based on real-time environmental data and obstacle detection information to ensure that it reaches the target vehicle for charging in the shortest time. During the path planning process, the robot's own energy consumption, path length, and the urgency of the task are taken into consideration, and a dynamic adjustment mechanism based on time integration is adopted to optimize charging efficiency and energy utilization.

[0087] Charging process and adjustment: When the robot is charging the vehicle, the charging module 200 monitors the battery status (SoC, SoH and temperature) in real time and dynamically adjusts the charging current and voltage based on this. The specific adjustment formula is:

[0088] If SoC is less than 80%, constant current charging is adopted and the charging current is maintained at 5C;

[0089] If SoC>80%, switch to constant voltage charging and maintain the voltage at 4.2V.

[0090] Experimental comparison: The traditional charging robot adopts fixed rules for scheduling, charging vehicles one by one according to the distance, and does not have AI scheduling and path optimization functions. During the implementation of the embodiment, the performance of the two robots in terms of charging efficiency, energy utilization rate, and task completion time is compared and recorded. The specific situation is shown in the following table:

[0091] project Robot of the present invention Traditional charging robot Number of vehicles 10 10 Average charging efficiency (%) 92.5 78.3 Average energy consumption (kWh) 12.8 15.6 Task completion time (minutes) 65 120 Total path length (m) 850 1230 Charging time per time (minutes) 9.5 15.2 Energy utilization rate (%) 88.3 70.4 Charging strategy adjustment times 15 0

[0092] It can be seen from the above experimental data that the mobile AI energy storage charging robot of the present invention is superior to the traditional charging robot in many aspects, as shown in the following:

[0093] The charging efficiency is significantly improved: the average charging efficiency of the present invention reaches 92.5%, which is 14.2 percentage points higher than that of the traditional charging robot; this is mainly due to the intelligent scheduling and charging strategy optimization functions of the AI ​​control module 105; the traditional charging robot cannot dynamically adjust the charging current and voltage according to the vehicle status, resulting in low charging efficiency.

[0094] Significantly reduced energy consumption: The energy consumption of the present invention is 12.8 kWh, which saves about 18% of energy compared to traditional robots; this is attributed to the robot's energy optimization strategy in path planning and task scheduling, which reduces unnecessary energy consumption by real-time monitoring of the robot's remaining power and path length.

[0095] The task completion time is greatly shortened: the robot of the present invention only takes 65 minutes to complete all charging tasks, while the traditional robot takes 120 minutes; the AI ​​control module 105 enables the robot to complete the charging task in a shorter time through reasonable allocation of task priorities and path optimization.

[0096] Improved path planning efficiency: The total length of the path traveled by the robot of the present invention is 850 meters, which is significantly shorter than the 1230 meters of the traditional robot; through AI algorithm optimization, the robot effectively reduces invalid moving paths, thereby further improving the overall efficiency.

[0097] The energy utilization rate is significantly improved: the energy utilization rate of the present invention reaches 88.3%, while that of the traditional charging robot is only 70.4%; the present invention maximizes energy utilization efficiency and reduces energy waste through dynamic power distribution and charging strategy adjustment.

[0098] In summary, the mobile AI energy storage charging robot greatly improves the charging efficiency, reduces energy consumption, and shortens the task completion time by introducing the AI ​​control module 105, deep learning model and intelligent path planning. Compared with traditional technologies, the present invention not only has obvious functional advantages, but also can better adapt to complex application environments and has broad market application prospects.

[0099] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A mobile AI energy storage charging robot, characterized by: It comprises an AI robot body (100) and a charging module (200); The AI ​​robot body (100) comprises a mobile platform (101), an energy storage module (102), a communication module (103), a navigation and sensor module (104), and an AI control module (105); wherein the mobile platform (101) is used to assist the robot in moving in different terrains; the energy storage module (102) is used for energy storage and supports bidirectional charging and discharging; the AI ​​control module (105) is used to implement the functions of task scheduling, energy distribution, and path planning; the navigation and sensor module (104) is used for environmental perception and obstacle detection; and the communication module (103) is used for data exchange and collaboration with other robots and the cloud. The charging module (200) is used to charge the target device.

2. The mobile AI energy storage charging robot according to claim 1, characterized in that: The energy storage module (102) is arranged on the mobile platform (101); the energy storage module (102) is a high-efficiency lithium battery or a solid-state battery, and has high-efficiency energy storage and discharge functions.

3. The mobile AI energy storage charging robot according to claim 2, characterized in that: The navigation and sensor module (104) includes a laser radar, a camera and an ultrasonic sensor for environment perception and vehicle identification.

4. The mobile AI energy storage charging robot according to claim 3, characterized in that: The communication module (103) is used to interact with the cloud and other robots, and supports 5G and Wi-Fi networks.

5. The mobile AI energy storage charging robot according to claim 4, characterized in that: The charging module (200) comprises a charging plug (201), wherein the charging plug (201) is arranged on a charging seat (202); the charging seat (202) is connected to a multi-axis mechanical arm (203), and the multi-axis mechanical arm (203) is fixed on a mobile platform (101); a smoke sensor (204) is arranged on the charging seat (202), and the smoke sensor (204) is connected to a pump body (205); the feed side of the pump body (205) is connected to a fire extinguishing tank via a pipeline, and the discharge side of the pump body (205) is connected to a fire extinguishing nozzle (206) via a pipeline; a nozzle installation groove (207) for use with the fire extinguishing nozzle (206) is provided at the front end of the charging seat (202), and the nozzle installation groove (207) is connected to the pump body (205). ) is arranged on the fire extinguishing nozzle (206) for protecting the sealing rotary plate (208), and the sealing rotary plate (208) is connected to a motor (209) for driving the sealing rotary plate (208) to rotate and expose the fire extinguishing nozzle (206); the sealing rotary plate (208) is fixedly connected to a rotating shaft, and a rotating gear (210) is arranged on the rotating shaft, and the rotating gear (210) is meshingly connected to a driving gear ring (211), and the driving gear ring (211) is meshingly connected to a driving gear (212), and the driving gear (212) is connected to the motor (209); an annular tooth groove group is arranged in an annular array on the circumferential inner wall of the driving gear ring (211), and the annular tooth groove group is meshingly connected to the driving gear (212) and the rotating gear (210).

6. The mobile AI energy storage charging robot according to claim 5, characterized in that: The charging module (200) supports fast charging and dynamically adjusts the charging current based on the battery status (SoC, SoH and temperature) of the vehicle. The specific adjustment formula is: Among them, I opt is the optimal charging current, C i Indicates the current battery capacity of the vehicle; E i Indicates the current remaining power of the vehicle; T i Indicates the required charging time of the current vehicle; f(SoC,SoH,T) is a coefficient adjusted by the vehicle's current battery status (SoC and SoH) and temperature T, and the coefficient is dynamically optimized according to the battery's health, remaining power and ambient temperature, and T represents temperature.

7. The mobile AI energy storage charging robot according to claim 6, characterized in that: The charging module (200) supports fast charging and dynamically adjusts the charging voltage based on the battery status (SoC, SoH and temperature) of the vehicle. The specific adjustment steps are as follows: If SoC is less than 80%, constant current charging is adopted and the charging current is maintained at I opt ; When SoC>80%, switch to constant voltage charging and keep the voltage at V opt ; V opt The calculation formula is: V opt =V nom +k·(1-SoC); Among them, V nom is the nominal voltage of the battery and k is the charge factor of the battery.

8. The mobile AI energy storage charging robot according to claim 7, characterized in that: The AI ​​control module (105) comprises a task scheduling unit and an optimization control unit, wherein the task scheduling unit is used to allocate charging tasks according to the priority and charging demand of the vehicle, and the optimization control unit is used to calculate and optimize the movement path of the robot in real time.

9. The mobile AI energy storage charging robot according to claim 8, characterized in that: The task scheduling unit optimizes the charging tasks based on the deep learning model and generates the best dynamic power allocation strategy for the charging station to ensure the optimal allocation of power resources. The specific steps are as follows: Preset the following variables: P j represents the priority; α represents the temperature coefficient; R j represents the energy demand rate, defined as D i represents the remaining power of the energy storage charging robot; N represents the number of vehicles to be charged; β i represents the coefficient of energy loss; F represents the total amount of power classification; then, the task scheduling unit generates the optimal dynamic power allocation strategy according to the following formula, and the calculation formula is as follows: In this formula, P opt,i : The optimal dynamic power distribution of the i-th vehicle; In the integral term, the energy demand rate R of each vehicle is j , Priority P j 、Remaining power C j -E j and the influence of time, through Reflects the attenuation of charging efficiency and adds a normalized correction for temperature factors; Denominator: Normalizes the charging weights of all vehicles to ensure relative fairness in allocating electricity across the system; Integral term: calculates the cumulative effect of energy distribution within time T to ensure changes over time; ambient temperature normalization factor, through the normalization function Indicates the impact of the environment on charging time; Formula value range: between [0,1], indicating the proportion of charging distribution. Through the normalized power distribution mechanism, the charging efficiency and energy utilization of each vehicle are maximized. Specifically, 0 means no power is allocated to the vehicle (possibly because of sufficient power or low task priority); 1 means allocating maximum power to the vehicle (possibly because of severe power shortage or high task priority).

10. The mobile AI energy storage charging robot according to claim 9, characterized in that: The optimization control unit optimizes the charging path based on the deep learning model and generates the best movement path for the robot, taking into account energy consumption, path length and task priority. The specific steps are as follows: The following variables and parameters are preset: i The attenuation coefficient related to vehicle energy consumption and environmental factors; (x, y) The spatial coordinates of the charging robot, indicating its mobile position in the smart city; γ i Energy loss coefficient related to vehicle and environment; β i The coefficient of energy loss depends on factors such as ambient temperature; The calculation formula for the optimal moving path is as follows: Task priority function T i (x, y, t): represents the priority of the task point that the robot needs to reach at a certain position (x, y) at time t. This function is related to the importance of the task, deadline, etc.; Energy consumption function E i (x, y, t): represents the energy consumption required for the robot to move to position (x, y), which depends on the current position, speed v and terrain characteristics; Path length function D(x, y): represents the distance from the current point of the robot to the target point, calculated based on Euclidean distance or Manhattan distance; Charging station location function C(x c ,y c ): indicates the relative position of the charging station. The robot can choose to charge midway during the mission to increase the power; AI learning optimization function L(t): AI optimizes the path and energy use strategy through historical data and real-time feedback; the power belongs to the function R i (t): represents the remaining power of the robot at time t; Travel time τ(x, y, v): represents the time required for the robot to travel to position (x, y) at speed v; Integral representation: This formula is a time integral, which represents the optimal travel path and strategy that the robot needs to consider at time t; The time dimension allows the robot to adjust according to dynamic power, task and path information; The task priority part T i (x(t), y(t), τ(x, y, v)): The robot prioritizes high-priority tasks. The exponential term indicates that the importance of the task gradually decreases over time. The more urgent the task, the higher the priority weight; energy consumption part The exponential function represents the impact of energy consumption on path planning. The greater the energy consumption, the more the robot needs to consider the balance between path and energy. Path length D(x(t), y(t)): Path length directly affects the robot's travel time and energy consumption. The shorter the path, the better. Charging station C(x c ,y c ): The location of the charging station will affect the path planning. If the robot is low on power, the AI ​​algorithm will give priority to recharging at the charging station; AI learning part L(t): Through the AI ​​learning optimization function, the robot can continuously adjust its strategy based on historical data and path feedback to improve task execution efficiency; Formula F opt The range of (t): The range of this formula represents the comprehensive optimization degree of the robot at time t; the smaller the range, the more favorable the robot has found a route that can maximize the task priority while minimizing the path length and energy consumption.

Images