A logistics robot control method and system based on artificial intelligence

Abstract

The present invention discloses an artificial intelligence-based logistics robot control method and system, which relates to the field of robotics technology and includes the following steps: Step 1: Each logistics robot connects to a data acquisition API when starting to perform a task, automatically records task data, and all logistics robots upload the task data to a cloud learning platform via a wireless network to build a preliminary experience database; the present invention records task data in real time by connecting the logistics robots to the data acquisition API, and uploads it to the cloud learning platform to build a preliminary experience database. By integrating the task data of all robots, the system is dynamically trained using online learning to establish a multi-dimensional task experience database, and intelligently selects experience areas for task allocation based on the current logistics status, optimizes control strategies, and dynamically optimizes upper-level decisions and lower-level feedback based on real-time feedback, thereby achieving the common accumulation and sharing of experience and continuously optimizing the operating strategies of all robots.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a logistics robot control method and system based on artificial intelligence. Background Art

[0002] With the rapid growth of e-commerce and global logistics, the demand for automation and intelligent logistics is increasing. Traditional logistics management methods often rely on manual operations, which are not only inefficient but also susceptible to human factors. Therefore, many companies have begun to apply robotics technology to the logistics field to achieve automation and intelligent logistics processes.

[0003] The existing technology has the following shortcomings: traditional logistics management methods can no longer meet the market's requirements for high efficiency and low cost, resulting in frequent manual intervention and low operational efficiency. Although the existing artificial intelligence-based logistics robot control method can realize the automation of some tasks, it lacks environmental adaptability, poor task execution flexibility, insufficient real-time data processing capabilities, and an imperfect experience sharing mechanism. Due to the lack of effective feedback mechanisms and dynamic optimization strategies, it is difficult to perform at its best in complex and changing environments, which limits the success rate and efficiency of robots in logistics tasks. There is also a lack of effective experience sharing and collective learning mechanisms among robots, which makes it impossible for successful experiences and failure lessons to be effectively transmitted to all robots.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a logistics robot control method and system based on artificial intelligence to solve the problems in the above-mentioned background technology.

[0006] In order to achieve the above objectives, the present invention provides the following technical solution: a logistics robot control method based on artificial intelligence, comprising the following steps:

[0007] Step 1: Each logistics robot connects to the data collection API at the beginning of a mission and automatically records mission data, including the mission environment status, mission execution status, and mission feedback information. All logistics robots upload the mission data to the cloud learning platform via wireless network to build a preliminary experience database;

[0008] Step 2: Integrate the task data of all logistics robots through the cloud learning platform and use online learning to conduct dynamic training based on real-time task data;

[0009] Step 3: Establish a multi-dimensional task experience database, divide the upper-level decision-making process, automatically select experience zones for logistics task allocation based on the current logistics status, optimize the execution control strategy, and divide the lower-level feedback process to feed back the corresponding task data experience to the cloud in real time based on the logistics tasks.

[0010] Step 4: Dynamically optimize upper-level decisions and lower-level feedback based on feedback, continuously update to form a closed loop, enable all logistics robots to accumulate experience together when performing tasks, and share experience through the cloud learning platform to optimize the operating strategies of all logistics robots.

[0011] Preferably, each logistics robot connects to the data acquisition API when starting to perform a task, and automatically records the task data, including the task environment status, task execution status and task feedback information, wherein the task environment status includes the current position of the logistics robot, the obstacle position and the task target, the task execution status includes the task start time, the task completion time, and whether the task is successful or not, and the task feedback information includes the task execution problems, the obstacles encountered in the task, and the task success rate. In the process of automatically recording the task data, the global positioning system and the internal positioning algorithm are used to accurately record the precise coordinates of the current position of the logistics robot, and the internal sensor group is used to detect the surrounding environment of the logistics robot and dynamically record the obstacle position. According to the task target location and the scheduled task information, the task execution status is compared with the preset task completion status. The task feedback information is recorded by the internal information transmission group in combination with the task environment status and the task execution status. All logistics robots upload the task data to the cloud learning platform through the wireless network to build a preliminary experience database, which is divided into the first experience area, the second experience area, the third experience area and the fourth experience area. The first experience area includes the execution records of all successfully completed tasks, the second experience area includes the execution records of all failed tasks, the third experience area includes the task execution status of different environmental variables, and the fourth experience area includes the impact of manual intervention on the task execution status.

[0012] Preferably, the task data of all logistics robots are integrated through a cloud learning platform, and the task data of different logistics robots in the same time period are associated based on timestamps to obtain diversified task execution status under the same environmental variables. A corresponding label is assigned to each task target. Based on the integrated task data set, a basic deep reinforcement learning model is constructed through the cloud learning platform for rapid adaptation, and the task rules and control strategies of the logistics robots are continuously optimized. The task data uploaded in real time from the logistics robots is received through online learning and processed using an incremental learning method. The task execution status is input as an immediate reward signal into the basic deep reinforcement learning model for online update. An incremental feedback loop mechanism is established. After each task is executed, the new task data is immediately used to update the weight of the deep reinforcement learning model. The task data is weighted based on the environmental variables. The specific formula is:

[0013]

[0014] Among them, w final represents the weight of each task execution state after update, β represents the feedback influence factor of task feedback on task data, E t Indicates the specific indicator of the task execution status at the current timestamp, α t Indicates the time impact factor of the timestamp on the current task execution status, E i,t Indicates the execution status of the i-th task at timestamp t, E env Indicates the specific indicator of the task execution status in the current environment variable, E j,env represents the jth task execution state when the environment variable env is set, ω represents the time impact factor of the environment variable on the current task execution state, ω pre It represents the weight of each task execution status after the last update, N represents the total number of task data involved in the weight calculation, and M represents the total number of task data involved in the environment variable calculation. Tasks executed in complex environments are prioritized to help all logistics robots update their learning goals.

[0015] Preferably, the preliminary experience database is reclassified based on the success rate dimension, including high success rate area, medium success rate area and low success rate area, and is reclassified based on the environmental condition dimension, including humidity area and temperature area. The preliminary experience database is reclassified based on the task characteristics dimension, including task type area and task complexity area. The logistics API is connected to monitor the current logistics status in real time and divide the upper-level decision-making to train high-level experience area decisions. Based on the current logistics status, the optimal experience area after reclassification is dynamically selected through the decision-making algorithm to allocate logistics tasks. After assigning tasks, resources are automatically optimized according to the task execution status, and the lower-level feedback is divided to feed back the experience of the corresponding task data to the cloud in real time according to the logistics tasks.

[0016] Preferably, the decision algorithm is retrained regularly based on the latest feedback. Once a new control strategy is generated, the logistics robot will immediately receive the updated control strategy so that it can be executed in the next round of tasks. Continuous updates form a closed loop, and a feedback gain model is constructed to quantify the improvement. The specific formula is:

[0017]

[0018] Among them, F(t) represents the feedback value of the current execution task, α represents the feedback gain factor, F(t-1) represents the feedback value of the previous timestamp, γ represents the historical feedback gain factor, and F k represents the total feedback value of the past k task executions, C t represents the complexity factor of the current task, δ represents the immediate reward factor, and R(t) represents the immediate reward signal for executing the task at time t. The optimal experience area is completely converted into a collective knowledge base, so that all logistics robots can accumulate experience together when performing tasks. The collective wisdom is used to identify common problems and successful control strategies through machine learning algorithms, and the best experience is generated for reference by all logistics robots. The experience is shared through the cloud learning platform to optimize the operation strategies of all logistics robots.

[0019] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0020] 1. By connecting to the data collection API and uploading task data in real time, the logistics robot can dynamically record and analyze the task environment status and execution status, improving the accuracy and reliability of the data.

[0021] 2. Using the deep reinforcement learning model built on the cloud-based learning platform, the robot can automatically optimize task strategies based on task data and real-time feedback. Through incremental learning of task data, it can timely update decision-making rules, realize intelligent task allocation and execution, and enhance the autonomous learning and adaptability of logistics robots.

[0022] 3. Establish a multi-dimensional task experience database, and reclassify the preliminary experience database according to different dimensions based on the task data of all logistics robots, so that logistics robots can choose the most suitable execution strategy under different environmental conditions.

[0023] 4. Completely convert the optimal experience area into a collective knowledge base, so that different logistics robots can share experiences of success and failure, forming a stronger collaborative working ability of logistics robots.

[0024] 5. By constructing a feedback gain model, the effectiveness of the improved control strategy can be quantified, ensuring that the logistics robot improves its task execution capabilities through continuous learning, forming an effective closed-loop feedback mechanism, and maintaining long-term efficient operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0026] Figure 1 This is a flow chart of a method for controlling a logistics robot based on artificial intelligence of the present invention.

[0027] Figure 2 This is a module schematic diagram of an artificial intelligence-based logistics robot control system of the present invention. DETAILED DESCRIPTION

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0029] Example 1

[0030] The present invention provides Figure 1 The artificial intelligence-based logistics robot control method and system shown include the following steps:

[0031] Step 1: Each logistics robot connects to the data collection API at the beginning of a mission and automatically records mission data, including the mission environment status, mission execution status, and mission feedback information. All logistics robots upload the mission data to the cloud learning platform via wireless network to build a preliminary experience database;

[0032] Each logistics robot connects to the data collection API when it starts to perform a task, and automatically records the task data, including the task environment status, task execution status and task feedback information. The task environment status includes the current position of the logistics robot, the position of obstacles and the task target. The task execution status includes the task start time, task completion time and whether the task is successful or not. The task feedback information includes the task execution problems, the obstacles encountered in the task and the task success rate. In the process of automatically recording the task data, the global positioning system and the internal positioning algorithm are used to accurately record the precise coordinates of the current position of the logistics robot, and the internal sensor group is used to detect the surrounding environment of the logistics robot and dynamically record the obstacle position. According to the task target location and the scheduled task information, the task execution status is compared with the preset task completion status. The task feedback information is recorded through the internal information transmission group in combination with the task environment status and the task execution status. All logistics robots upload the task data to the cloud learning platform through the wireless network to build a preliminary experience database, which is divided into the first experience area, the second experience area, the third experience area and the fourth experience area. The first experience area includes the execution records of all successfully completed tasks, the second experience area includes the execution records of all failed tasks, the third experience area includes the task execution status of different environmental variables, and the fourth experience area includes the impact of human intervention on the task execution status.

[0033] Step 2: Integrate the task data of all logistics robots through the cloud learning platform and use online learning to conduct dynamic training based on real-time task data;

[0034] The task data of all logistics robots are integrated through the cloud learning platform. The task data of different logistics robots in the same time period are associated based on the timestamp to obtain the diversified task execution status under the same environmental variables. The corresponding label (such as handling, distribution, inventory, etc.) is assigned to each task target. Based on the integrated task data set, a basic deep reinforcement learning model (such as convolutional neural network (CNN) or long short-term memory network (LSTM)) is built through the cloud learning platform for rapid adaptation, and the task rules and control strategies of the logistics robots are continuously optimized. The task data uploaded in real time from the logistics robots is received through online learning and processed using the incremental learning method. The task execution status is input as an immediate reward signal into the basic deep reinforcement learning model for online update. An incremental feedback loop mechanism is established. After each task is executed, the new task data is immediately used to update the weight of the deep reinforcement learning model. The task data is weighted based on the timestamp, environmental variables and task feedback. The specific formula is:

[0035]

[0036] Among them, w finalrepresents the weight of each task execution state after update, β represents the feedback influence factor of task feedback on task data, E t Indicates the specific indicator of the task execution status at the current timestamp, α t Indicates the time impact factor of the timestamp on the current task execution status, E i,t Indicates the execution status of the i-th task at timestamp t, E env Indicates the specific indicator of the task execution status in the current environment variable, E j,env represents the jth task execution state when the environment variable env is set, ω represents the time impact factor of the environment variable on the current task execution state, ω pre It represents the weight of each task execution status after the last update, N represents the total number of task data involved in the weight calculation, and M represents the total number of task data involved in the environment variable calculation. Tasks executed in complex environments are prioritized to help all logistics robots update their learning goals.

[0037] Step 3: Establish a multi-dimensional task experience database, divide the upper-level decision-making process, automatically select experience zones for logistics task allocation based on the current logistics status, optimize the execution control strategy, and divide the lower-level feedback process to feed back the corresponding task data experience to the cloud in real time based on the logistics tasks.

[0038] The preliminary experience database is reclassified based on the success rate dimension, including high success rate area, medium success rate area and low success rate area, where the high success rate area includes task data with a success rate higher than 80%, the medium success rate area includes task data with a success rate between 50% and 80%, and the low success rate area includes task data with a success rate lower than 50%. The preliminary experience database is reclassified based on the environmental condition dimension, including humidity area and temperature area. The preliminary experience database is reclassified based on the task characteristics dimension, including task type area and task complexity area. The logistics API is connected to monitor the current logistics status in real time and divide the upper-level decision-making to train high-level experience area decisions (such as A3C). Based on the current logistics status, the decision-making algorithm (such as C4.5 or random forest) is used to dynamically select the optimal experience area after reclassification for logistics task allocation. After assigning tasks, resources are automatically optimized according to the task execution status. The lower-level feedback is divided and the experience of the corresponding task data is fed back to the cloud in real time according to the logistics tasks.

[0039] Step 4: Dynamically optimize upper-level decisions and lower-level feedback based on feedback, continuously updating to form a closed loop. This allows all logistics robots to accumulate experience while performing tasks, share experience through a cloud-based learning platform, and optimize the operational strategies of all logistics robots.

[0040] The decision algorithm is regularly retrained based on the latest feedback. Once a new control strategy is generated, the logistics robot will immediately receive the updated control strategy so that it can be executed in the next round of tasks. Continuous updates form a closed loop and a feedback gain model is constructed to quantify improvements. The specific formula is:

[0041]

[0042] Among them, F(t) represents the feedback value of the current execution task, α represents the feedback gain factor, F(t-1) represents the feedback value of the previous timestamp, γ represents the historical feedback gain factor, and F k represents the total feedback value of the past k task executions, C t represents the complexity factor of the current task, δ represents the immediate reward factor, and R(t) represents the immediate reward signal for executing the task at time t. The optimal experience area is completely converted into a collective knowledge base, so that all logistics robots can accumulate experience together when performing tasks. The collective wisdom is used to identify common problems and successful control strategies through machine learning algorithms (such as DQN and DDPG), generate the best experience for reference by all logistics robots, and share the experience through the cloud learning platform to optimize the operation strategy of all logistics robots.

[0043] The present invention provides Figure 2 The artificial intelligence-based logistics robot control system shown includes a record uploading module, an integrated training module, a decision feedback module, and a shared optimization module;

[0044] Record upload module: Each logistics robot connects to the data collection API at the beginning of a task and automatically records task data, including task environment status, task execution status, and task feedback information. All logistics robots upload task data to the cloud learning platform via wireless network to build a preliminary experience database;

[0045] The record upload module specifically described in this embodiment, when each logistics robot starts to perform a task, relies on the connection data acquisition API to automatically record and upload the task data. In the specific process, each robot first accurately obtains its current coordinates through the global positioning system and the internal positioning algorithm, and uses the internal sensor group to detect the surrounding environment of the logistics robot. The internal sensor group specifically includes an ambient temperature sensor, a light sensor, an ambient humidity sensor and an infrared sensor. During the execution of the task by the logistics robot, the task execution status is compared with the preset task completion status according to the task target position and the predetermined task information. The task feedback information is recorded by the internal information transmission group in combination with the task environment status and the task execution status. All logistics robots transmit the task data through The wireless network is uploaded to the cloud learning platform to build a preliminary experience database, which is divided into a first experience area, a second experience area, a third experience area and a fourth experience area. The first experience area includes the execution records of all successfully completed tasks, the second experience area includes the execution records of all failed tasks, the third experience area includes the task execution status of different environmental variables, and the fourth experience area includes the impact of manual intervention on the task execution status. According to experiments, the third experience area can include a task execution success rate of 90% in an environment with a humidity of 70% and a temperature of 22°C. According to experiments, the third experience area can include a logistics robot that is subject to manual intervention once during the execution of a task, resulting in the task completion time increasing to 15 minutes, but the task is successfully completed.

[0046] By connecting to the data collection API and uploading task data in real time, logistics robots can dynamically record and analyze the task environment status and execution status, improving the accuracy and reliability of the data.

[0047] Integrated training module: Integrate the task data of all logistics robots through the cloud learning platform, and use online learning to conduct dynamic training based on real-time task data;

[0048] The integrated training module specifically described in this embodiment associates the task data of different logistics robots in the same time period based on timestamps to obtain diverse task execution status under the same environmental variables. According to experiments, logistics robot A successfully executed the task at time t = 2025-10-01 9:00:00 and the environmental variables were humidity 70% and temperature 22°C.

[0049] Using the deep reinforcement learning model built on the cloud-based learning platform, the robot can automatically optimize task strategies based on task data and real-time feedback. Through incremental learning of task data, it can timely update decision-making rules, realize intelligent task allocation and execution, and enhance the autonomous learning and adaptability of logistics robots.

[0050] Decision feedback module: Establish a multi-dimensional task experience database, divide the upper-level decision-making into experience zones based on the current logistics status to automatically select logistics tasks, optimize the execution control strategy, and divide the lower-level feedback into real-time feedback of corresponding task data based on logistics tasks to the cloud;

[0051] Shared Optimization Module: Dynamically optimizes upper-level decisions and lower-level feedback based on feedback, continuously updates to form a closed loop, enables all logistics robots to accumulate experience together when performing tasks, and shares experience through the cloud learning platform to optimize the operating strategies of all logistics robots.

[0052] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A logistics robot control method based on artificial intelligence, characterized in that: The following steps are involved: Step 1: Each logistics robot connects to the data collection API at the beginning of a mission and automatically records mission data, including the mission environment status, mission execution status, and mission feedback information. All logistics robots upload the mission data to the cloud learning platform via wireless network to build a preliminary experience database; In the process of automatically recording task data, the global positioning system and internal positioning algorithm are used to accurately record the precise coordinates of the current position of the logistics robot, and the internal sensor group is used to detect the surrounding environment of the logistics robot, and the obstacle position is dynamically recorded. According to the task target position and the predetermined task information, the task execution status is compared with the preset task completion status. The task feedback information is recorded by the internal information transmission group in combination with the task environment status and the task execution status. All logistics robots upload the task data to the cloud learning platform through the wireless network; the preliminary experience database is divided into a first experience area, a second experience area, a third experience area and a fourth experience area, wherein the first experience area includes the execution records of all successfully completed tasks, the second experience area includes the execution records of all failed tasks, the third experience area includes the task execution status of different environmental variables, and the fourth experience area includes the impact of human intervention on the task execution status; Step 2: Integrate the task data of all logistics robots through the cloud learning platform and use online learning to conduct dynamic training based on real-time task data; The dynamic training includes weighting the task data based on the environmental variables, and the specific formula is: ； in, Indicates the weight of each task execution status after update, represents the feedback impact factor of task feedback on task data, Indicates the specific indicator of the task execution status at the current timestamp, Indicates the time impact factor of the timestamp on the current task execution status, Indicates the execution status of the i-th task at timestamp t, Indicates the specific indicators of the task execution status in the current environment variables. Indicates the execution status of the jth task in the environment variable env, Indicates the time impact factor of the environment variable on the current task execution status, Indicates the weight of each task execution status after the last update, Indicates the total number of task data involved in weight calculation, Indicates the total number of task data involved in the calculation of environment variables; Step 3: Establish a multi-dimensional task experience database, divide the upper-level decision-making process, automatically select experience zones for logistics task allocation based on the current logistics status, optimize the execution control strategy, and divide the lower-level feedback process to feed back the corresponding task data experience to the cloud in real time based on the logistics tasks. The said establishing a multi-dimensional task experience database specifically includes: reclassifying the preliminary experience database based on the success rate dimension, including a high success rate area, a medium success rate area, and a low success rate area; reclassifying the preliminary experience database based on the environmental condition dimension, including a humidity area and a temperature area; reclassifying the preliminary experience database based on the task characteristics dimension, including a task type area and a task complexity area; Step 4: Dynamically optimize upper-level decisions and lower-level feedback based on feedback, continuously update to form a closed loop, enable all logistics robots to accumulate experience together when performing tasks, and share experience through the cloud learning platform to optimize the operating strategies of all logistics robots.

2. The artificial intelligence-based logistics robot control method according to claim 1, characterized in that: In the step 2, the dynamic training specifically includes: based on the integrated task data set, building a basic deep reinforcement learning model through a cloud learning platform for rapid adaptation, receiving task data uploaded in real time from the logistics robot through online learning and processing it using an incremental learning method, inputting the task execution status as an immediate reward signal into the basic deep reinforcement learning model for online updating, establishing an incremental feedback loop mechanism to immediately update the deep reinforcement learning model weights with new task data after each task is executed, weighting the task data based on environmental variables, giving priority to tasks performed in complex environments, and helping all logistics robots update their learning goals.

3. The artificial intelligence-based logistics robot control method according to claim 1, characterized in that: In step 4, the decision algorithm is regularly retrained based on the latest feedback. Once a new control strategy is generated, the logistics robot will immediately receive the updated control strategy, continuously update it to form a closed loop, build a feedback gain model for quantitative improvement, and completely convert the task experience database into a collective knowledge base, so that all logistics robots can accumulate experience together when performing tasks, use collective wisdom to identify common problems and successful control strategies through machine learning algorithms, generate the best experience for reference by all logistics robots, and share experience through the cloud learning platform to optimize the operation strategies of all logistics robots.

4. The artificial intelligence-based logistics robot control method according to claim 3, characterized in that: The specific formula for quantitative improvement of the feedback gain model is: ； in, Indicates the feedback value of the currently executed task, represents the feedback gain factor, Indicates the last timestamp feedback value, represents the historical feedback gain factor, Represents the total feedback value of the past k task executions, Indicates the complexity factor of the currently executed task, represents the immediate reward factor, represents the immediate reward signal for performing the task at time t.

5. An artificial intelligence-based logistics robot control system, applied to an artificial intelligence-based logistics robot control method according to any one of claims 1 to 4, characterized in that: Specifically include: Record upload module: Each logistics robot connects to the data collection API at the beginning of a task and automatically records task data, including task environment status, task execution status, and task feedback information. All logistics robots upload task data to the cloud learning platform via wireless network to build a preliminary experience database; Integrated training module: Integrate the task data of all logistics robots through the cloud learning platform, and use online learning to conduct dynamic training based on real-time task data; Decision feedback module: Establish a multi-dimensional task experience database, divide the upper-level decision-making into experience zones based on the current logistics status to automatically select logistics tasks, optimize the execution control strategy, and divide the lower-level feedback into real-time feedback of corresponding task data based on logistics tasks to the cloud; Shared Optimization Module: Dynamically optimizes upper-level decisions and lower-level feedback based on feedback, continuously updates to form a closed loop, enables all logistics robots to accumulate experience together when performing tasks, and shares experience through the cloud learning platform to optimize the operating strategies of all logistics robots.

Images