Robot charging optimization control method and system

Abstract

This invention provides a robot charging optimization control method and system, relating to the field of robot control technology. The method includes: planning a charging path for the robot to a charging station with the goal of simultaneously satisfying multiple optimization conditions; and controlling the robot to perform a charging operation based on the charging path. The multiple optimization conditions include: the robot's first remaining battery power upon arrival at the charging station is lower than a preset battery power threshold; the time the robot spends charging at the charging station has less impact on its remaining tasks than a preset impact threshold; and when the robot passes any potential non-autonomous behavior execution point, its second remaining battery power is sufficient to support the execution of the corresponding non-autonomous behavior. By comprehensively considering battery management, task execution efficiency, and non-autonomous behavior response requirements, an optimal charging path is planned and the charging operation is controlled, achieving an optimal balance between battery replenishment and task execution.

Description

Technical Field

[0001] This invention relates to the field of robot control technology, and in particular to a robot charging optimization control method and system. Background Technology

[0002] Currently, with the rapid development of modern automation and robotics, the application scenarios of robots have expanded from industrial production to daily services, becoming an important part of human life and work. However, with the increasing complexity of tasks and the diversity of usage scenarios, the problem of robot power management has become increasingly prominent. Traditional power management strategies usually rely on simple power threshold settings, that is, when the power is lower than a certain fixed value, the robot automatically goes to a charging station to recharge. Although this method is simple to operate, it has revealed many shortcomings in practical applications.

[0003] First, traditional strategies do not fully consider the dynamic nature of power consumption during task execution. Different tasks have significantly different power consumption rates, and a single threshold is insufficient to adapt to diverse operating scenarios. This may lead to premature charging of the robot, reducing task efficiency, or insufficient power to support task completion, causing interruptions. Second, the impact of the charging process on task execution is often overlooked. The robot cannot work during charging, potentially causing task backlog or delays. Especially in time-sensitive scenarios, the timing of charging is crucial, and traditional methods fail to effectively balance charging needs and task execution. Furthermore, external factors may trigger non-autonomous behaviors during robot operation (such as being temporarily called upon by staff), leading to additional power consumption. Traditional strategies lack the ability to predict and respond to such emergencies, and insufficient power can easily affect the execution of non-autonomous behaviors.

[0004] In summary, current power management strategies still have shortcomings in balancing power replenishment with task execution efficiency and in addressing non-autonomous behavior. Therefore, a comprehensive approach is urgently needed to optimize charging paths and operational control to achieve optimal coordination between power and tasks, thereby improving the robot's work efficiency and system reliability in multi-tasking or long-term operation scenarios. Summary of the Invention

[0005] One of the objectives of this invention is to provide a robot charging optimization control method and system to solve the problems mentioned in the background art.

[0006] In a first aspect, the robot charging optimization control method provided in the embodiments of the present invention includes:

[0007] With the goal of simultaneously satisfying multiple optimization conditions, a charging path is planned for the robot to reach the charging station;

[0008] Based on the charging path, control the robot to perform charging operations;

[0009] The optimization conditions include:

[0010] The robot's initial remaining battery level upon arrival at the charging station is lower than a preset battery threshold.

[0011] The time the robot spends charging at the charging station has less impact on its tasks than a preset impact threshold.

[0012] When the robot passes through any potential point of non-autonomous behavior execution, its second remaining power is sufficient to support the execution of the corresponding non-autonomous behavior.

[0013] Optionally, the steps for obtaining the potential involuntary behavior execution points and their corresponding involuntary behaviors include:

[0014] Based on the site map and charging path, determine the multiple working loops that the robot will travel through;

[0015] For each working cycle:

[0016] Identify the target path points that may trigger hesitation in the corresponding work unit regarding whether to use the robot's target function when the robot passes through the work circle.

[0017] Determine whether the robot's first movement after the target path point when it passes through the work circle can dispel the worker's hesitation and prompt it to choose to use the target function.

[0018] If so, then the working circle is designated as the non-autonomous behavior execution point, and the robot's execution of the target function is designated as a non-autonomous behavior.

[0019] Optionally, the step of determining the target path point includes:

[0020] Based on a preset interval, multiple candidate path points are determined from the path along which the robot traverses the working circle;

[0021] For each candidate path point:

[0022] Based on the expected completed work of the corresponding work unit in the current work cycle before the robot arrives at the candidate path point, the work requirements are determined.

[0023] Identify the candidate functions that the robot should possess to meet the job requirements;

[0024] Based on the work profile of the corresponding work entity, determine whether the corresponding work entity is familiar with the candidate functions;

[0025] If you are familiar with it, then identify the candidate function as the target function and the candidate path point as the target path point.

[0026] If the robot is not familiar with the function, further determine whether the second movement before the candidate path point when the robot passes through the work circle can make the corresponding workpiece familiar with the candidate function.

[0027] If the determination is yes, then the candidate function is identified as the target function, and the candidate path point is identified as the target path point.

[0028] Optionally, the steps to determine whether the first movement can alleviate the worker's hesitation and prompt them to choose to use the target function include:

[0029] Determine the first autonomous behavior change of the robot related to the target function from the first movement situation;

[0030] For each autonomous action in the first autonomous action change:

[0031] Analyze the first utility value of the autonomous behavior that can dispel the worker's hesitation and prompt them to choose to use the target function. Determine whether the first utility value matches the worker's decision sensitivity level at the point where the autonomous behavior occurs. If the determination is yes, it is determined that the first movement situation can dispel the worker's hesitation and prompt them to choose to use the target function.

[0032] Among them, the decision sensitivity level is positively correlated with the sum of the utility values ​​of other autonomous behaviors that occur before the path point and can dispel the hesitation of the working body and prompt it to choose to use the target function, and negatively correlated with the distance from the path point to the robot's departure from the working circle.

[0033] Optionally, the steps for determining whether the second movement will enable the corresponding workpiece to become familiar with the selected function include:

[0034] Determine the second autonomous behavior change of the robot in relation to the candidate function from the second movement situation;

[0035] Analyzing changes in second autonomous behavior can enable the corresponding working entity to become familiar with the second utility value of the candidate function;

[0036] When the second utility value exceeds the preset first utility threshold, it is determined that the second movement situation enables the corresponding work body to become familiar with the selected function.

[0037] Optionally, the analysis steps for the first utility value include:

[0038] Determine the first utility value corresponding to the autonomous behavior from the preset first utility value library.

[0039] Optionally, the steps to determine whether the first utility value matches the decision sensitivity level include:

[0040] Determine whether the utility value exceeds the preset second utility threshold corresponding to the decision sensitivity level;

[0041] When the judgment is yes, the first utility value is matched with the decision sensitivity level.

[0042] Optionally, the analysis steps for the second utility value include:

[0043] Determine the second utility value corresponding to the change in the second autonomous behavior from the preset second utility value library.

[0044] Optionally, after controlling the robot to perform the charging operation based on the charging path, the method further includes:

[0045] If the robot suddenly performs an uncontrolled action during the charging operation, after the uncontrolled action is completed, it returns to plan the charging path to the charging station again with the goal of simultaneously satisfying multiple optimization conditions.

[0046] Secondly, the robot charging optimization control system provided in the embodiments of the present invention includes:

[0047] The charging path planning module is used to plan the charging path of the robot to the charging station with the goal of simultaneously satisfying multiple optimization conditions.

[0048] The charging operation execution module is used to control the robot to perform charging operations based on the charging path.

[0049] The optimization conditions include:

[0050] The robot's initial remaining battery level upon arrival at the charging station is lower than a preset battery threshold.

[0051] The time the robot spends charging at the charging station has less impact on its tasks than a preset impact threshold.

[0052] When the robot passes through any potential point of non-autonomous behavior execution, its second remaining power is sufficient to support the execution of the corresponding non-autonomous behavior.

[0053] The present invention has achieved the following beneficial effects:

[0054] By comprehensively considering power management, task execution efficiency, and the need to respond to non-autonomous behaviors, the optimal charging path is planned and the charging operation is controlled to achieve the best balance between power replenishment and task execution. The setting and satisfaction of multiple optimization conditions ensure that the robot efficiently manages power during long-term operation or multi-tasking scenarios, avoiding task interruptions due to insufficient power, reducing efficiency losses caused by frequent charging, and ultimately significantly improving overall work efficiency and system reliability.

[0055] Through multi-objective optimized charging path planning and precise charging control, an efficient and reliable power management solution is provided for robots, suitable for complex and variable working environments.

[0056] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0057] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0058] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0059] Figure 1 This is a flowchart of the robot charging optimization control method in an embodiment of the present invention;

[0060] Figure 2 This is a schematic diagram of the robot charging optimization control system in an embodiment of the present invention. Detailed Implementation

[0061] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0062] The research and development approach of this application is to plan the optimal charging path for the robot to the charging station by comprehensively considering the robot's power management, task execution efficiency, and the need to cope with potential non-autonomous behaviors. Based on this path, the charging operation is controlled to achieve the best balance between power replenishment and task execution. By setting and satisfying multiple optimization conditions, the robot can efficiently manage its power during long-term operation or multi-tasking scenarios, avoiding task interruptions due to insufficient power, while reducing efficiency losses caused by frequent charging, ultimately improving overall work efficiency and system reliability.

[0063] Figure 1 A flowchart of a robot charging optimization control method is provided for embodiments of this application, such as... Figure 1 As shown, the method includes:

[0064] 101. With the goal of simultaneously satisfying multiple optimization conditions, plan the charging path for the robot to the charging station.

[0065] The core of this step is to plan a path to the charging station through multi-objective optimization, so that the robot can simultaneously meet the following three optimization conditions during the charging process:

[0066] Condition 1: The robot's initial remaining battery power upon arrival at the charging station is lower than a preset battery power threshold.

[0067] In this condition, the preset battery threshold is a threshold representing when the robot's battery is about to run out. By ensuring that the robot's initial remaining battery level upon arrival at the charging station is below this threshold, charging efficiency can be improved and the number of charging cycles reduced. When planning the route, based on past battery consumption experience, the battery level consumed by the robot during its journey to the charging station can be calculated. Subtracting this consumed battery level from the current battery level yields the initial remaining battery level.

[0068] Condition 2: The time the robot spends charging at the charging station has less impact on its pending tasks than a preset impact threshold.

[0069] In this condition, "occupancy time" refers to the time required for the charging station to charge the robot from its initial remaining power to the target power, which can be determined based on past charging speed experience. "Pending tasks" refers to tasks assigned to the robot that have not yet been completed during charging. The impact of occupancy time on tasks can be quantified by the time the pending tasks are delayed due to charging. The preset impact threshold is a standard value representing a minimal impact. By ensuring the impact is below this threshold, excessive interference with task execution during charging can be avoided.

[0070] Condition 3: When the robot passes through any potential non-autonomous behavior execution point, its second remaining power is sufficient to support the execution of the corresponding non-autonomous behavior.

[0071] In this condition, non-autonomous behavior refers to actions that the robot does not autonomously due to external conditions, such as a worker temporarily using a function of the robot. Potential non-autonomous behavior execution points are specific locations along the robot's path that may trigger such behavior; each execution point corresponds one-to-one with a specific non-autonomous behavior. Similarly, when planning the path, based on past power consumption experience, the power consumed by the robot during its journey before reaching a potential non-autonomous behavior execution point can be calculated. Subtracting this consumed power from the current power level yields the second remaining power. For example, taking a logistics robot as an example, assuming its current power is 50% and the preset power threshold is 10%. When planning the path, if the power consumption from the current location to the charging station is calculated to be 20%, then the first remaining power is 30% (50% - 20%), which is higher than 10%, failing to meet condition one. After adjusting the path or task, assuming the consumption increases to 45%, then the first remaining power is 5% (50% - 45%), satisfying condition one. Simultaneously, the impact of charging time (e.g., 10 minutes) on task delay (delay of 5 minutes) is calculated. If the preset impact threshold is 6 minutes, then condition two is satisfied. If the route passes through a location where on-site personnel need to use a function, it is necessary to ensure that the second remaining power (e.g., 20%) is sufficient to support the execution of the corresponding function (e.g., 15%), thus satisfying condition three.

[0072] 102. Based on the charging path, control the robot to perform charging operations.

[0073] In this step, the robot travels to the charging station along the planned charging path and performs a charging operation upon arrival, ensuring a balance between power replenishment and task execution. Continuing with the logistics robot example above, the robot travels to the charging station along the adjusted path (consuming 45% of its power). Upon arrival, it has 5% remaining power and immediately charges to the target level (e.g., 80%). During charging, task delays are controlled within 5 minutes, meeting a preset threshold, and the robot has sufficient power for on-site personnel to use during the journey. The robot successfully completes charging and returns to perform its task.

[0074] This method comprehensively considers power management, task execution efficiency, and non-autonomous behavior response requirements to plan the optimal charging path and control the charging operation, achieving the best balance between power replenishment and task execution. The setting and satisfaction of multiple optimization conditions ensure that the robot efficiently manages power during long-term operation or multi-tasking scenarios, avoiding task interruptions due to insufficient power, reducing efficiency losses from frequent charging, and ultimately significantly improving overall work efficiency and system reliability.

[0075] In summary, this application provides a highly efficient and reliable power management solution for robots through multi-objective optimized charging path planning and precise charging control, which is suitable for complex and variable working environments.

[0076] In some embodiments, the steps for obtaining the potential involuntary behavior execution points and their corresponding involuntary behaviors include:

[0077] 201. Based on the site map and charging path, determine the multiple working loops that the robot will take.

[0078] In this step, the site map is a 3D map of the robot's work area. A work circle refers to the fixed range of movement of a working unit during operation. Working units refer to personnel and other robots. From the site map, based on the charging path, multiple work circles that the robot will traverse can be determined. For example, suppose a logistics robot travels from warehouse point A to charging station point B. The site map shows a maintenance area for a personnel along the path; this area is defined as a work circle that the robot will soon pass through.

[0079] 202. For each working cycle, perform the following steps:

[0080] 203. Determine the target path point that may trigger hesitation in the corresponding work unit regarding whether to use the robot's target function when the robot passes through the work circle.

[0081] In this step, for each work circle, the system needs to analyze whether the robot's passage will trigger hesitation in the worker regarding the use of the robot's functions, and further determine whether this hesitation ultimately leads the worker to choose to use a particular function. This step-by-step analysis refines the identification of non-autonomous behavior to specific work circles and scenarios. This improves the accuracy of identification, ensures that each potential interaction scenario is fully evaluated, and provides a reliable basis for power management in path planning. When a worker is working within its work circle, it is unaware that the robot will pass through it and has no expectation of the robot's passage. Its own work arrangements are assumed to be completed independently or with the help of existing tools. Therefore, when the robot passes through the work circle, the worker will hesitate about whether to use a certain target function of the robot, thus generating such hesitation. Next, the development state of this hesitation is determined—whether it resolves the choice of the target function or something else. This development state is key to determining whether to use the work circle as a point of execution for non-autonomous behavior. Therefore, the target path point is determined first.

[0082] Specifically, step 203 includes the following sub-steps:

[0083] 301. Based on a preset interval, determine multiple candidate path points on the path the robot takes through the working circle.

[0084] In this step, the preset interval is the preset distance interval between path points. When determining multiple candidate path points, one path point is selected as a candidate path point every preset interval along the path the robot takes through the work circle. The evenly distributed candidate path points ensure analysis coverage, avoid missing locations that might trigger hesitation, and improve recognition accuracy. For example, within the aforementioned maintenance work circle, the total length of the robot path is 20 meters, the preset interval is 5 meters, and the system selects P1 (0 meters), P2 (5 meters), P3 (10 meters), and P4 (15 meters) as candidate path points.

[0085] 302. For each candidate path point, perform the following steps:

[0086] 303. Based on the expected completed work of the corresponding work body in the current work cycle before the robot arrives at the candidate path point, determine the work requirements.

[0087] In this step, the daily work of the work unit is divided into multiple work cycles. The current work cycle refers to the work cycle in which the work unit is currently located when the robot arrives at the candidate path point. When planning the charging path, the arrival time of the robot at different path points is determined. Therefore, when determining the expected completed work of the work unit within the current work cycle, the arrival time of the robot at the candidate path point can be determined first, and the work cycle including that time can be determined. The work arrangements before that time within that work cycle can be considered as the expected completed work. The expected completed work reflects the work unit's working status, and therefore, work requirements can be determined based on it. Accurately inferring work requirements provides a basis for subsequent function matching, ensuring that the analysis closely reflects the actual state of the work unit. For example, if the robot is expected to arrive at the aforementioned candidate path point P2 at 10:30, and the worker's work cycle is 9:00-10:00 for data entry and 10:00-11:00 for equipment maintenance, then the worker has completed the first half of the equipment maintenance, and the work requirement might be moving equipment.

[0088] 304. Identify the candidate functions that the robot should possess to meet the job requirements.

[0089] In this step, if the robot possesses a candidate function that meets the job requirements, the robot can use that candidate function. A mapping relationship between different robot functions and the job requirements they can fulfill can be established in advance. When determining a candidate function, this mapping relationship is queried. For example, if the job requirement is a material handling device, and the robot possesses a material handling function, then that function is determined as a candidate function.

[0090] 305. Based on the work profile of the corresponding work entity, determine whether the corresponding work entity is familiar with the candidate functions.

[0091] In this step, the worker's work profile includes: historical records of using different functions of the robot, work experience, etc. Based on the work profile, it can be determined whether the worker is familiar with the candidate function. Assessing familiarity through the work profile accurately predicts the worker's psychological reaction, improves the reliability of hesitation analysis, and provides a basis for determining the target path point. For example, if the work profile indicates that the worker has used the robot's handling function multiple times in the past, then it is determined that the worker is familiar with that function.

[0092] 306. If you are familiar with it, then select the candidate function as the target function and select the candidate path point as the target path point.

[0093] In this step, if the working entity is familiar with the candidate function, it will definitely hesitate about whether to use the candidate function. In this case, the candidate function will be determined as the target function, and the candidate path point will be determined as the target path point.

[0094] 307. If unfamiliar, further determine whether the second movement of the robot before the candidate path point when it passes through the work circle can make the corresponding work body familiar with the candidate function.

[0095] In this step, if the worker is unfamiliar with the candidate function, it doesn't mean it won't hesitate to use it. A special case needs to be considered: whether the robot's second movement before the candidate path point while traversing the work circle can familiarize the worker with the candidate function. The second movement refers to the robot's movement behavior before the candidate path point while traversing the work circle.

[0096] Specifically, step 307 includes the following sub-steps:

[0097] 501. Determine the second autonomous behavior change of the robot related to the candidate function from the second movement situation.

[0098] In this step, the second movement scenario includes autonomous behavior changes generated by the robot itself. These changes refer to the sequential changes in the robot's autonomously generated behaviors, from which the second autonomous behavior change related to the candidate function is determined. When planning the charging path, the overall movement of the robot along the charging path can be determined, from which the second movement scenario can be identified. If the determined second autonomous behavior change is empty, it is determined that the second movement scenario cannot enable the corresponding workpiece to become familiar with the candidate function. For example, if the candidate function is the robot's handling function, the determined second autonomous behavior change related to the candidate function is the robot's actions such as carrying and lifting items during a handling task.

[0099] 502. Analyze the second utility value of changes in the second autonomous behavior that enable the corresponding working entity to become familiar with the candidate function.

[0100] In this step, the utility of different changes in second autonomous behavior in enabling the corresponding worker to become familiar with the selected function is determined in advance through experiments. Corresponding second utility values ​​are then set, forming a second utility value library. When analyzing the second utility values, the second utility value corresponding to the second autonomous behavior change is determined from the second utility value library. For example, if the second autonomous behavior change is an action such as moving or lifting items during a transport task, its utility in enabling the corresponding worker to become familiar with the selected function is relatively high (the worker can indirectly recognize that the robot has a transport function), and the corresponding second utility value is set to 10.

[0101] 503. When the second utility value exceeds the preset first utility threshold, determine that the second movement situation enables the corresponding working body to become familiar with the selected function.

[0102] In this step, a preset first utility threshold is defined as the threshold representing the utility value that enables the corresponding work unit to become familiar with the candidate function through a second autonomous behavior change. When the second utility value exceeds the preset first utility threshold, it is determined that the second movement situation enables the corresponding work unit to become familiar with the candidate function. For example, if the first utility threshold is set to 8, and the second utility value 10 exceeds 8, then it is determined that the second movement situation enables the corresponding work unit to become familiar with the candidate function.

[0103] 308. If the determination is yes, then the candidate function is determined as the target function, and the candidate path point is determined as the target path point.

[0104] In this step, when it is determined that the second movement will enable the corresponding work unit to become familiar with the candidate function, the candidate function is identified as the target function, and the candidate path point is identified as the target path point. By comprehensively considering the impact of behavioral changes, the target path point is locked, ensuring the comprehensiveness and accuracy of the analysis and providing support for subsequent decision-making.

[0105] 204. Determine whether the robot's first movement after the target path point when it passes through the work circle can dispel the worker's hesitation and prompt it to choose to use the target function.

[0106] In this step, it is then necessary to further track the development of hesitation, determining whether the robot's first movement after the target path point when traversing the work circle can dispel the worker's hesitation and prompt it to choose to use the target function. The first movement refers to the robot's movement behavior after the target path point when traversing the work circle. Tracking the development of hesitation ensures accurate judgment of the worker's final decision, providing a basis for non-autonomous behavior recognition.

[0107] Specifically, step 204 includes the following sub-steps:

[0108] 401. Determine the first autonomous behavior change of the robot related to the target function from the first movement situation.

[0109] In this step, the first movement scenario includes autonomous behavioral changes generated by the robot itself. These changes refer to the sequential changes in the robot's autonomously generated behaviors, from which the first autonomous behavioral change related to the candidate function is identified. When planning the charging path, the overall movement of the robot along the charging path can be determined, from which the first movement scenario can be identified. When the identified first autonomous behavioral change is empty, identifying the first movement scenario cannot alleviate the worker's hesitation and prompt them to choose the target function. Identifying behaviors that influence decision-making provides specific objects for subsequent utility analysis, ensuring the relevance of the judgment. For example, if the target function is a transport function, the identified first autonomous behavioral changes related to the target function include changes in movement direction and movement position (representing locations where the robot can transport objects).

[0110] 402. For each autonomous action in the first autonomous action change, perform the following steps:

[0111] 403. Analyze the first utility value of the autonomous behavior that can dispel the worker's hesitation and prompt them to choose to use the target function. Determine whether the first utility value matches the worker's decision sensitivity level at the point where the autonomous behavior occurs. If the determination is yes, confirm that the first movement situation can dispel the worker's hesitation and prompt them to choose to use the target function.

[0112] In this step, experiments are conducted beforehand to determine the extent to which different changes in primary autonomous behavior can alleviate the worker's hesitation and encourage them to choose the target function. Corresponding primary utility values ​​are then established, forming a primary utility value database. When analyzing these primary utility values, the primary utility value corresponding to the autonomous behavior is determined from this database. The decision sensitivity level represents the worker's sensitivity level in deciding whether to use the target function; the higher the level, the more likely the worker is to choose the target function. The step of determining whether the primary utility value matches the decision sensitivity level includes: determining whether the utility value exceeds a preset secondary utility threshold corresponding to the decision sensitivity level; if yes, the primary utility value is considered to match the decision sensitivity level. Secondary utility thresholds are preset for different decision sensitivity levels; the higher the decision sensitivity level, the more likely the worker is to choose the target function, and the lower the corresponding secondary utility threshold. When the primary utility value matches the decision sensitivity level, it indicates that the autonomous behavior with the primary utility value is sufficient to alleviate the worker's hesitation and encourage them to choose the target function. By matching utility values ​​with sensitivity levels, the impact of behavior on decision-making can be accurately determined, ensuring the scientific validity and reliability of the results. For example: if the first autonomous behavior change is a change in movement direction or position, instructing the robot to move to the waste storage area associated with its work circle, then this can alleviate the worker's hesitation and encourage them to choose the target function. This has a high utility level (making the worker realize that the robot can carry the waste generated during its work to the corresponding waste storage area). The corresponding first utility value is set to 10. The decision sensitivity level is determined to be 2, with a corresponding preset second utility threshold of 7. Since the first utility value of 10 exceeds 7, the first utility value matches the decision sensitivity level, thus confirming that the first movement can alleviate the worker's hesitation and encourage them to choose the target function. The decision sensitivity level is positively correlated with the sum of utility values ​​from other autonomous behaviors occurring before the path point that can alleviate the worker's hesitation and encourage them to choose the target function, and negatively correlated with the distance from the path point to the robot's departure from the work circle. Similarly, the utility values ​​of other autonomous behaviors that occurred before the path point can be determined from the first utility value pool, which can alleviate the worker's hesitation and prompt them to choose the target function. These utility values ​​are then summed to obtain the total utility value. The larger the total utility value, the greater the cumulative utility of different autonomous behaviors during the worker's hesitation state, making it easier to choose the target function and thus increasing the decision sensitivity level. Therefore, there is a positive correlation between the constraint decision sensitivity level and the total utility value. The distance from the path point to the robot's departure from the work circle refers to the distance between the path point and the end of the path along the robot's path through the work circle.The smaller the distance, the more the worker will subjectively perceive that the robot is about to leave, making it easier to choose to use the target function, thus resulting in a higher decision sensitivity level. Therefore, there is a negative correlation between the decision sensitivity level and the movement distance. Specifically, different combinations of total utility values ​​and different movement distances can be pre-set, and a corresponding decision sensitivity level can be determined for each combination, forming a level table. When determining the sensitivity level, the table is directly consulted based on the total utility value and the movement distance. For example: if the total utility value is 50 and the movement distance is 12m, the decision sensitivity level corresponding to this combination is set to 3.

[0113] 205. If so, then the working circle is determined as the non-autonomous behavior execution point, and the robot's execution of the target function is determined as a non-autonomous behavior.

[0114] In this step, when it is determined that the first movement scenario can alleviate the worker's hesitation and prompt them to choose to use the target function, the work circle is designated as a non-autonomous behavior execution point, and the robot's execution of the target function is defined as a non-autonomous behavior. It should be noted that the worker's work needs will differ before different candidate path points. Furthermore, given that the worker continues to experience hesitation, it is only necessary to base the determination on the utility value (second utility value) of the second autonomous behavior change in the second movement scenario that enables the corresponding worker to become familiar with the candidate function. However, after the target path point, the worker continues to experience hesitation, and their psychological changes are slightly more complex. Therefore, it is necessary to consider the worker's decision sensitivity level in different states and analyze whether the first utility value of the autonomous behavior at the corresponding moment is appropriate to determine whether the first movement scenario can alleviate the worker's hesitation and prompt them to choose to use the target function.

[0115] Through the steps described above, this method comprehensively analyzes the real-time needs of the work unit, the impact of robot behavior on hesitation, and decision-making tendencies, accurately identifying potential non-autonomous behavior execution points and their corresponding non-autonomous behaviors. This method provides crucial support in charging path planning, ensuring that the robot can balance charging needs and task execution efficiency in power management, ultimately improving overall work efficiency and system reliability.

[0116] In some embodiments, after step 102 controls the robot to perform a charging operation based on the charging path, the method further includes:

[0117] 103. When the robot performs a sudden non-autonomous behavior during the charging operation, after the sudden non-autonomous behavior is completed, return to plan the charging path to the charging station with the goal of simultaneously satisfying multiple optimization conditions.

[0118] Sudden unautonomous behavior refers to unautonomous actions performed outside of the potential unautonomous behavior execution point, such as being instructed to perform a function by a passing technician. After the sudden unautonomous behavior is completed, the robot returns to its previous position and replans its charging path to the charging station with the goal of simultaneously satisfying multiple optimization conditions, thus avoiding the impact of sudden unautonomous behavior.

[0119] Figure 2 A schematic diagram of a robot charging optimization control system is provided for an embodiment of this application, such as... Figure 2 As shown, the system includes:

[0120] The charging path planning module 100 is used to plan the charging path of the robot to the charging station with the goal of simultaneously satisfying multiple optimization conditions.

[0121] The charging operation execution module 200 is used to control the robot to perform charging operations based on the charging path.

[0122] The optimization conditions include:

[0123] The robot's initial remaining battery level upon arrival at the charging station is lower than a preset battery threshold.

[0124] The time the robot spends charging at the charging station has less impact on its tasks than a preset impact threshold.

[0125] When the robot passes through any potential point of non-autonomous behavior execution, its second remaining power is sufficient to support the execution of the corresponding non-autonomous behavior.

[0126] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A robot charging optimization control method, characterized by, The method comprises: planning a charging path for the robot to reach the charging station while satisfying multiple optimization conditions; controlling the robot to perform a charging operation based on the charging path; wherein the multiple optimization conditions comprise: a first remaining power of the robot when reaching the charging station is lower than a preset power threshold; an influence of an occupancy time of the robot charging at the charging station on a task to be performed by the robot is less than a preset influence threshold; a second remaining power of the robot when passing through any potential non-autonomous behavior execution point is sufficient to support performance of a corresponding non-autonomous behavior; the potential non-autonomous behavior execution point and its corresponding non-autonomous behavior comprise: determining multiple work circles passed through by the robot based on a field map and the charging path; for each work circle: determining a target path point at which the robot passing through the work circle can trigger a hesitation emotion of a target function of a work body about whether to use the target function; judging whether a first movement condition after the target path point can eliminate the hesitation emotion of the work body and prompt the work body to select to use the target function when the robot passes through the work circle; if yes, determining the work circle as a non-autonomous behavior execution point and determining performance of the target function by the robot as a non-autonomous behavior, wherein the determination of the target path point comprises: determining multiple candidate path points from a path of the robot passing through the work circle based on a preset interval; for each candidate path point: determining a work demand based on an estimated completed work of a corresponding work body in a current work cycle before the robot reaches the candidate path point; determining a selected function possessed by the robot that meets the work demand; judging whether the corresponding work body is familiar with the selected function based on a work profile of the corresponding work body; if yes, determining the selected function as the target function and the candidate path point as the target path point; if no, further judging whether a second movement condition before the candidate path point can make the corresponding work body familiar with the selected function when the robot passes through the work circle; if yes, determining the selected function as the target function and the candidate path point as the target path point, wherein the judging whether the first movement condition can eliminate the hesitation emotion of the work body and prompt the work body to select to use the target function comprises: determining a first autonomous behavior change of the robot related to the target function from the first movement condition; for each autonomous behavior in the first autonomous behavior change: analyzing a first utility value of the autonomous behavior in eliminating the hesitation emotion of the work body and prompting the work body to select to use the target function, judging whether the first utility value is adapted to a decision sensitivity level of the work body at an occurrence path point of the autonomous behavior, and determining that the first movement condition can eliminate the hesitation emotion of the work body and prompt the work body to select to use the target function if the judgment is yes; wherein the decision sensitivity level is positively correlated with a sum of utility values of other autonomous behaviors that can eliminate the hesitation emotion of the work body and prompt the work body to select to use the target function before the occurrence path point, and is negatively correlated with a movement distance of the robot from the work circle to the occurrence path point, wherein the judging whether the second movement condition can make the corresponding work body familiar with the selected function comprises: determining a second autonomous behavior change of the robot related to the candidate function from the second movement situation; analyzing the second autonomous behavior change is capable of making the corresponding work body familiar with a second utility value of the candidate function; when the second utility value exceeds a preset first utility threshold, determining that the second movement situation is capable of making the corresponding work body familiar with the candidate function.

2. The robot charge optimization control method of claim 1, wherein, the analysis step of the first utility value includes: determining the first utility value corresponding to the autonomous behavior from a preset first utility value library.

3. The robot charging optimization control method of claim 1, wherein, the step of judging whether the first utility value is adapted to the decision sensitivity level includes: judging whether the utility value exceeds a preset second utility threshold corresponding to the decision sensitivity level; when the judgment is yes, judging that the first utility value is adapted to the decision sensitivity level.

4. The robot charge optimization control method of claim 1, wherein, the analysis step of the second utility value includes: determining the second utility value corresponding to the second autonomous behavior change from a preset second utility value library.

5. The robot charge optimization control method of claim 1, wherein, after the robot performs the charging operation based on the charging path, further comprising: when the robot performs a sudden non-autonomous behavior halfway through the charging operation, returning to re-plan the charging path of the robot to the charging station with the goal of simultaneously satisfying multiple optimization conditions after the sudden non-autonomous behavior is completed.

6. A robot charging optimization control system characterized by, including: a charging path planning module for planning a charging path of the robot to the charging station with the goal of simultaneously satisfying multiple optimization conditions; a charging operation execution module for controlling the robot to perform a charging operation based on the charging path; wherein the multiple optimization conditions include: the first remaining power of the robot when it arrives at the charging station is lower than a preset power threshold; the impact of the occupancy time of the robot charging at the charging station on the task to be performed is less than a preset impact threshold; the second remaining power of the robot when it passes through any potential non-autonomous behavior execution point is sufficient to support the execution of the corresponding non-autonomous behavior; the acquisition step of the potential non-autonomous behavior execution point and its corresponding non-autonomous behavior includes: determining multiple work circles that the robot passes through based on the site map and the charging path; for each work circle: determining a target path point that can trigger a hesitation emotion of the corresponding work body about whether to use the target function of the robot when the robot passes through the work circle; judging whether the first movement situation after the target path point can eliminate the hesitation emotion of the work body and prompt it to choose to use the target function when the robot passes through the work circle; if yes, determining the work circle as a non-autonomous behavior execution point and determining the execution of the target function of the robot as a non-autonomous behavior, wherein the determination step of the target path point includes: determining multiple candidate path points from the path of the robot passing through the work circle based on a preset interval; for each candidate path point: determining work demand based on the expected completed work of the corresponding work body within the current work cycle before the robot arrives at the candidate path point; determining a candidate function that the robot possesses and meets the work demand; judging whether the corresponding work body is familiar with the candidate function based on the work profile of the corresponding work body; if familiar, determining the candidate function as the target function and the candidate path point as the target path point; if not familiar, further judging whether the second movement situation before the candidate path point can make the corresponding work body familiar with the candidate function when the robot passes through the work circle; If the judgment is yes, the candidate function is determined as the target function, and the candidate path point is determined as the target path point, The step of judging whether the first movement condition can eliminate the hesitation emotion of the work body and prompt the work body to select to use the target function comprises: determining, from the first movement condition, a first autonomous behavior change of the robot related to the target function; for each autonomous behavior in the first autonomous behavior change: analyzing a first utility value of the autonomous behavior to eliminate the hesitation emotion of the work body and prompt the work body to select to use the target function, judging whether the first utility value is adapted to a decision sensitivity level of the work body at a path point of occurrence of the autonomous behavior, and if the judgment is yes, determining that the first movement condition can eliminate the hesitation emotion of the work body and prompt the work body to select to use the target function; wherein the decision sensitivity level is positively correlated with a sum of utility values of other autonomous behaviors occurring before the path point of occurrence and is negatively correlated with a movement distance of the robot from the work circle, The step of judging whether the second movement condition can make the corresponding work body familiar with the candidate function comprises: determining, from the second movement condition, a second autonomous behavior change of the robot related to the candidate function; analyzing a second utility value of the second autonomous behavior change to make the corresponding work body familiar with the candidate function; when the second utility value exceeds a preset first utility threshold, determining that the second movement condition can make the corresponding work body familiar with the candidate function.

Images