A method, apparatus, device and medium for completing robot tasks

Abstract

This application discloses a method, apparatus, device, and medium for completing a robot task, relating to the field of robotics. The method includes: when performing a target task, determining the confidence level of the target task's success rate; judging whether the robot needs external assistance based on the relationship between the confidence level and a preset confidence threshold; if so, constructing a spatial map within the target area, identifying and locating a group of objects that can provide assistance, determining several groups of candidate objects for assistance based on the spatial map and the object groups, and determining the assistance level value corresponding to each candidate object; determining a target candidate object for assistance, interacting with the target candidate object to obtain guidance information, and determining several executable tasks based on the guidance information; after executing several executable tasks, judging whether the target task is completed; if not, reverting to the step of constructing the spatial map within the target area until the target task is completed. This ensures the completion of the robot task.

Description

Technical Field

[0001] This invention relates to the field of robotics, and in particular to a method, apparatus, device, and medium for completing robot tasks. Background Technology

[0002] With the widespread application of robots in industrial manufacturing, service industries, and exploration, they often encounter unexpected situations in complex and ever-changing environments. These situations can include sensor malfunctions, loss of orientation, or incomplete information, preventing them from completing tasks independently. Current robot navigation and task execution strategies primarily rely on pre-programmed algorithms and sensor data, lacking the ability to proactively seek external assistance when encountering difficulties. This makes it difficult for robots to flexibly adapt to environmental changes, impacting task efficiency and success rates. Therefore, improving task completion efficiency and success rates is a pressing issue that needs to be addressed. Summary of the Invention

[0003] In view of this, the purpose of this invention is to provide a method, apparatus, device, and medium for completing robot tasks, enabling the robot to seek external assistance when it is unable to complete a task, efficiently integrate the obtained assistance information to complete the task, and improve the efficiency and success rate of task completion. The specific solution is as follows:

[0004] In a first aspect, this application discloses a method for completing a robot task, including:

[0005] During the execution of the target task, the confidence level of the target task completion success rate is determined, and the robot is judged whether it needs to seek external assistance based on the relationship between the confidence level and the preset confidence threshold.

[0006] If so, a spatial map within the target area is constructed, the target group of objects that can provide assistance is identified and located, and several groups of candidate objects for assistance are determined based on the spatial map and the target group, and the assistance value corresponding to each candidate object for assistance is determined.

[0007] Identify the target candidate for assistance corresponding to the highest assistance value, interact with the target candidate for assistance to obtain corresponding guidance information, and determine several executable tasks based on the guidance information;

[0008] After executing several executable tasks, it is determined whether the target task has been completed. If not, the process jumps back to the step of constructing a spatial map within the target area until the target task is completed.

[0009] Optionally, the confidence level for determining the success rate of the target task includes:

[0010] The reliability of the data from each sensor is determined based on the signal strength, signal quality, and signal integrity of each sensor in the robot.

[0011] The sensor data confidence level, which characterizes the integrity and accuracy of the sensor data, is determined based on the preset sensor weights corresponding to each sensor of the robot and the reliability of the sensor data.

[0012] The battery confidence level, which characterizes the health of the battery, is determined by the battery's capacity, power loss rate, and voltage.

[0013] The complexity of the ground is determined based on the number of obstacles on the road surface, the degree of terrain undulation, and the width of the travel path in the robot's current environment.

[0014] An environmental confidence level, which characterizes the complexity of the current environment, is determined using the environmental conditions corresponding to the robot's current environment and the complexity of the ground; the environmental conditions include light intensity, temperature, humidity, and wind speed.

[0015] Based on the vectors corresponding to the environmental data detected by the robot and the environmental data required to complete the target task, a target confidence level is determined to characterize the degree of support of the environmental data for the target task.

[0016] The confidence level for the success rate of the target task is determined based on the confidence level of the sensor data, the confidence level of the battery, the confidence level of the environment, and the confidence level of the target.

[0017] Optionally, the confidence level for determining the success rate of the target task based on the confidence level of the sensor data, the confidence level of the battery, the confidence level of the environment, and the confidence level of the target includes:

[0018] The confidence level for the success rate of the target task is determined based on the confidence levels of the sensor data, the battery, the environment, and the target, using a confidence level calculation formula. The confidence level calculation formula is as follows:

[0019] ;

[0020] in, The confidence level; The confidence level of the sensor data; The confidence level of the battery; The confidence level of the environment; The target confidence level; is the target threshold; w1, w2, w3, and w4 are preset weight values.

[0021] Optionally, determining whether the robot needs external assistance based on the relationship between the confidence level and a preset confidence threshold includes:

[0022] If the confidence level is less than or equal to the preset confidence threshold, it is determined that the robot needs to seek external assistance.

[0023] If the confidence level is greater than the preset confidence threshold, it is determined that the robot does not need to seek external assistance.

[0024] Optionally, the step of determining several groups of candidate objects for assistance based on the spatial map and the object group includes:

[0025] Group structure data is constructed based on the spatial map and the information corresponding to the object groups; the group structure data includes data defining the labels of each object group, the surrounding map of each object group, the minimum cost path from the robot to each object group, the age of each object group, and the social role of each object group;

[0026] Based on the group structure data, several groups of potential candidates for assistance are identified.

[0027] Optionally, determining the assistance value corresponding to each candidate for help includes:

[0028] The social attributes of the candidates for assistance are determined based on their clothing and facial expressions; the social attributes include any one or a combination of several of the following: children, teenagers, middle-aged people, elderly people, primary and secondary school students, high school students, and social service providers.

[0029] The appearance affinity value of the candidate for assistance is determined by a preset score corresponding to each social attribute.

[0030] The behavioral value of the candidate for assistance is determined based on the walking speed and body movements of the candidate; the body movements include any one or a combination of several of the following: empty hands, carrying items, and making a phone call; the carrying items movements include several categories of carrying items based on the estimated weight of the items.

[0031] The action cost of the robot reaching the location of the candidate object for assistance is determined based on the distance between the robot and the candidate object for assistance.

[0032] The assistance value of each of the aforementioned candidate objects is determined by the appearance affinity value, the behavior value, and the action cost value corresponding to each candidate object.

[0033] Optionally, the process of interacting with the target candidate object to obtain corresponding guidance information further includes:

[0034] Face detection and facial emotion recognition are performed on the target candidate for assistance to determine the facial expression of the target candidate for assistance, and the score corresponding to the facial expression is determined based on the score corresponding to the pre-determined facial expression classification.

[0035] The sentiment score of the discourse of the target's available help candidates is determined based on a pre-determined semantic sentiment score.

[0036] The emotional score of the body movements of the target's potential help recipients is determined by using pre-determined body movement scores.

[0037] Based on the scores corresponding to the facial expressions, the emotional scores of the speech semantics, and the emotional scores of the body movements, an emotional willingness value is determined to characterize whether the target candidate is willing to provide help.

[0038] If the emotional willingness value is less than or equal to the preset emotional willingness threshold, then the interaction with the target candidate for help is stopped, the target candidate for help is moved away from, and a new candidate for help is determined for interaction in order to obtain the corresponding guidance information.

[0039] If the emotional willingness value is greater than the preset emotional willingness threshold, then the target can-help candidate can be interacted with to obtain corresponding guidance information.

[0040] Optionally, after the step of re-jumping to the spatial map within the target area, the method further includes:

[0041] If the number of times the operation of re-jumping to the spatial map within the target area is equal to a preset threshold, and the target task is not completed, then request assistance from operations and maintenance personnel to complete the target task.

[0042] Secondly, this application discloses a robot task completion device, comprising:

[0043] The judgment module is used to determine the confidence level of the success rate of the target task during the execution of the target task, and to determine whether the robot needs to seek external assistance based on the relationship between the confidence level and a preset confidence threshold.

[0044] The assistance value determination module is used to construct a spatial map within the target range if the condition is met, identify and locate the group of objects that can provide assistance, determine several groups of candidate objects that can be helped based on the spatial map and the group of objects, and determine the assistance value corresponding to each candidate object that can be helped.

[0045] The executable task determination module is used to determine the target candidate for help corresponding to the highest assistance value, interact with the target candidate for help to obtain corresponding guidance information, and determine several executable tasks based on the guidance information.

[0046] The jump module is used to determine whether the target task has been completed after executing several executable tasks. If it has not been completed, it jumps back to the step of constructing a spatial map within the target range until the target task is completed.

[0047] Thirdly, this application discloses an electronic device, including:

[0048] Memory, used to store computer programs;

[0049] A processor is used to execute the computer program to implement the robot task completion method as described above.

[0050] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the robot task completion method as described above.

[0051] In this application, during the execution of a target task, the robot first determines the confidence level of the success rate of the target task. Based on the relationship between the confidence level and a preset confidence threshold, it determines whether the robot needs to seek external assistance. If so, a spatial map within the target area is constructed, and a group of objects that can provide assistance is identified and located. Based on the spatial map and the object group, several groups of candidate objects for assistance are determined, and the assistance level value corresponding to each candidate object is determined. Then, the target candidate object with the highest assistance level value is identified, and interaction is performed with the target candidate object to obtain corresponding guidance information. Based on the guidance information, several executable tasks are determined. Finally, after executing several executable tasks, it is determined whether the target task is completed. If not, the robot returns to the step of constructing the spatial map within the target area until the target task is completed. Therefore, this application uses confidence level to determine whether the robot can complete the task independently. If it cannot complete the task, it seeks external assistance, enabling the robot to autonomously seek external assistance, efficiently integrate the obtained assistance information to complete the task, and improve the reliability of task completion. Simultaneously, by using assistance scores to identify potential help recipients during the process of seeking external help, the efficiency of help selection is optimized. Furthermore, by evaluating and selecting the most suitable help recipient, the cost of seeking assistance is minimized. This, in turn, improves the efficiency and success rate of task completion. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0053] Figure 1 This is a flowchart of a robot task completion method disclosed in this application;

[0054] Figure 2 This is a schematic diagram of a structured data construction method disclosed in this application;

[0055] Figure 3 This is a logical diagram illustrating an information processing and execution method disclosed in this application;

[0056] Figure 4 This is a flowchart of a specific robot task completion method disclosed in this application;

[0057] Figure 5 This is a schematic diagram of the structure of a robot task completion device disclosed in this application;

[0058] Figure 6 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] Existing robot navigation and task execution strategies primarily rely on pre-programmed algorithms and sensor data, lacking the ability to proactively seek external assistance when encountering difficulties. This makes it difficult for robots to flexibly adapt to environmental changes, affecting task efficiency and success rate. To address the aforementioned technical problems, this application discloses a robot task completion method, apparatus, device, and medium, enabling robots to seek external assistance when unable to complete a task, efficiently integrating the obtained assistance information to complete the task, and improving task completion efficiency and success rate.

[0061] See Figure 1 As shown in the figure, an embodiment of the present invention discloses a method for completing a robot task, including:

[0062] Step S11: During the execution of the target task, determine the confidence level of the success rate of the target task completion, and determine whether the robot needs to seek external assistance based on the relationship between the confidence level and the preset confidence threshold.

[0063] In this embodiment, when the robot is performing a task (e.g., moving from location A to location B), it first performs a capability assessment. That is, if it loses its orientation or landmarks along the way, it first determines that the current perception information cannot support it to reach its destination and initiates the "autonomous assistance seeking" mode. Here, "self-capability assessment" is a confidence calculation logic for the success rate of task completion. When determining the confidence level for the success rate of the target task, the reliability of each sensor's data is determined based on the signal strength, signal quality, and signal integrity of each sensor. Sensor data confidence, characterizing the integrity and accuracy of the sensor data, is determined based on the preset sensor weights corresponding to each sensor and the reliability of the sensor data. Battery confidence, characterizing the battery's health, is determined using the robot's battery capacity, power loss rate, and voltage. Ground complexity is determined based on the number of obstacles, terrain undulation, and path width in the robot's current environment. Environmental confidence, characterizing the complexity of the current environment (including light intensity, temperature, humidity, and wind speed), is determined based on the vectors corresponding to the environmental data detected by the robot and the environmental data required to complete the target task. Finally, the confidence level for the success rate of the target task is determined based on sensor data confidence, battery confidence, environmental confidence, and target confidence. Specifically, the confidence level calculation formula is as follows:

[0064] ;

[0065] in, Confidence level; Confidence level of sensor data; Battery confidence level; For environmental confidence; Target confidence level; The target threshold (the red line threshold for a single factor, when the confidence level of any factor is ≤) At that time, the robot initiates an "autonomous assistance-seeking" mode based on this factor to solve the current factor problem. (This can be a uniform value, or a redline threshold can be set for each factor); w1, w2, w3, and w4 are preset weight values, i.e., the weights of each factor, reflecting the degree of influence of these factors on the confidence level, and the sum of the weights is 1. In a specific embodiment, for an indoor working environment, w1, w2, w3, and w4 can be set to 0.3, 0.2, 0.2, and 0.3 respectively. For an outdoor working environment, w1, w2, w3, and w4 can be set to 0.3, 0.15, 0.15, and 0.4 respectively. The weights can also be dynamically adjusted using an environmental awareness model.

[0066] Then, based on the relationship between the confidence level and a preset confidence threshold, it is determined whether the robot needs to seek external assistance. If the confidence level is less than or equal to the preset confidence threshold, it is determined that the robot needs to seek external assistance to continue completing the task, and the robot enters "autonomous assistance-seeking" mode. If the confidence level is greater than the preset confidence threshold, it is determined that the robot does not need to seek external assistance and can complete the task autonomously. In this way, the robot's autonomy and task completion rate are improved. The robot has the ability of "self-assessment of ability" and "autonomous assistance-seeking," and can intelligently judge and seek external help when the task is difficult, thus improving the reliability of task completion.

[0067] Step S12: If yes, construct a spatial map within the target area, identify and locate the group of objects that can provide assistance, determine several groups of candidate objects that can be helped based on the spatial map and the group of objects, and determine the assistance value corresponding to each candidate object.

[0068] In this embodiment, when the confidence level is less than or equal to a preset confidence threshold, the robot determines that it needs to seek external assistance and enters an "autonomous assistance-seeking" mode. This mode includes steps such as environmental analysis, assistance assessment, proactive assistance based on emotional cognition, information processing and execution, and continuous optimization. First, environmental analysis is performed. The robot perceives and understands its surroundings, identifies potential groups of people needing assistance, and models the surrounding environment. Specifically, the environmental analysis process involves the robot collecting data about its surroundings through sensors, creating a map of the environment within a 20m radius, and obtaining a spatial map S within that 20m radius. map The robot uses visual sensors, based on computer vision and deep learning models, to identify and locate a group of people (G) who may offer assistance, employing methods such as pedestrian recognition, face detection, and age / gender detection. helper For example, student groups, youth groups, and social worker groups. Then, based on spatial maps and target groups, several candidate groups for assistance are identified. Specifically, group structure data is constructed based on spatial maps and information corresponding to the target groups; such as... Figure 2As shown, the group structure data includes the labels of each object group, the surrounding map of each object group, the minimum cost path from the robot to each object group, the age of each object group, and the social role of each object group; based on the group structure data, several groups of candidate objects for assistance are determined.

[0069] When the robot selects N candidate groups SL that can be asked for help helper Afterwards, the robot enters the "assistance assessment" phase, which assesses the candidate group SL. helper For each group, a contribution value is calculated based on a combination of factors, including appearance, behavior, and cost of reaching the destination. The robot then prioritizes seeking help from the group with the highest assistance value. When determining the assistance value for each potential help recipient, the robot identifies their social attributes based on their clothing and facial expressions. Social attributes include any combination of children, teenagers, middle-aged individuals, elderly individuals, primary and secondary school students, high school students, and social service providers. The robot determines the appearance affinity value of each potential help recipient based on preset scores for each social attribute. The robot determines their behavioral value based on their walking speed and body movements. Body movements include any combination of empty hands, carrying items, and making a phone call. Carrying items includes several categories of carrying items based on the estimated weight of the items. The robot's action cost in reaching the potential help recipient's location is determined based on the distance between the robot and the potential help recipient. Finally, the assistance value for each potential help recipient is determined by their appearance affinity value, behavioral value, and action cost. Specifically, the assistance value assessment formula is:

[0070] ;

[0071] in, This is the assist value; Appearance affinity value; For the behavior value; The value of the action is represented by w1, w2, and w3, which are the weights of each factor. Here, the weight factors can be set to 0.3, 0.4, and 0.3 respectively. The weight factors can also be dynamically set based on different tasks.

[0072] The following section provides a detailed explanation of how to determine the appearance affinity value, behavior value, and action cost value. This reflects the approachability of the candidate group's appearance. Clothing and facial expressions are used to calculate the social attributes of the candidate group, indicating their willingness to help strangers. Social attributes refer to the group's social position and age, including children, teenagers, middle-aged people, the elderly, primary and secondary school students, high school students, and social service workers. Different scores are assigned to different social attributes.

[0073] ;

[0074] These are behavioral factors of the candidate group. By observing walking speed and body movements, the robot determines whether the candidate group has an urgent matter to handle or is currently handling. The robot prioritizes requesting assistance from candidate groups with stable walking and no urgent matters. For walking speed, optical flow is used to estimate the group's walking speed. Regarding body movements This includes being empty-handed, carrying a handbag, carrying heavy objects, and making a phone call.

[0075] ;

[0076] Here, you can set the maximum walking speed V. max The walking speed is 2 m / s. The weight w is the walking speed. v Body movement weights w c It can be set to 0.6 or 0.4:

[0077] ;

[0078] The robot calculates the cost of reaching candidate groups by measuring distance, and prioritizes candidate groups with lower cost. The closer the distance, the lower the cost.

[0079] ;

[0080] in, The value of the action; D is the distance between the robot and the potential assistance targets; The maximum distance for normalization can be set to 20m.

[0081] In this way, the cost of robots seeking assistance is optimized. Robots build accurate environmental models through technologies such as ubiquitous environmental perception, detection, and prediction, thereby optimizing the efficiency of selecting assistance targets.

[0082] Step S13: Determine the target candidate for assistance corresponding to the highest assistance value, interact with the target candidate for assistance to obtain corresponding guidance information, and determine several executable tasks based on the guidance information.

[0083] In this embodiment, the assistance value of each group is calculated, all candidate groups are sorted, and then the group with the highest assistance value is selected for assistance. Subsequently, based on emotion-based request for help, the robot interacts with the selected assistance recipient, attempting to obtain the necessary information from them. While communicating with the selected assistance recipient, the robot maintains the recipient's emotional willingness value, ensuring that the recipient is willing to provide assistance throughout the entire communication process, thereby reducing discomfort caused by the robot autonomously seeking help. The emotional willingness score is calculated based on the facial expressions, verbal semantics, and body movements of the person seeking help. Face detection and facial emotion recognition are performed on potential help recipients to determine their facial expressions. A score is determined based on pre-defined facial expression classifications. A pre-defined semantic emotion score is used to determine the emotional score of the verbal semantics of the potential help recipient. A pre-defined body movement score is used to determine the emotional score of the body movements of the potential help recipient. Based on the scores for facial expressions, verbal semantics, and body movements, an emotional willingness score is determined to characterize whether the potential help recipient is willing to provide help. If the emotional willingness score is less than or equal to a preset emotional willingness threshold, interaction with the potential help recipient is stopped, the recipient is moved away, and a new potential help recipient is identified for interaction to obtain relevant guidance information. If the emotional willingness score is greater than the preset emotional willingness threshold, interaction with the potential help recipient continues to obtain relevant guidance information. The specific formula for calculating the emotional willingness score is as follows:

[0084] ;

[0085] in, This represents the emotional willingness value. The score corresponds to the facial expression; Sentiment scores for discourse semantics; The emotional score for body movements is given; w1, w2, and w3 are the weights of each factor, which can be set to 0.3, 0.3, and 0.4 respectively.

[0086] Specifically, The system assesses the emotional willingness of those receiving assistance by measuring their facial expressions. Based on deep learning-based face detection and emotion recognition, it categorizes the current face into seven main types: anger, disgust, fear, happiness, sadness, surprise, and neutral. Different scores are assigned to different expressions.

[0087] ;

[0088] It is a sentiment score of discourse semantics, which measures the emotional attitude of the recipient in the language expression. It can be analyzed using natural language processing models:

[0089] ;

[0090] It is an emotional score of body language, measuring the emotional attitude in the body language of the person being helped. Body language can be identified through computer vision-based body posture detection.

[0091] ;

[0092] When V emotion ≤T emotion When the robot expresses gratitude and ceases communication, it actively moves away from the person it was helping. Here, an emotional willingness threshold T is preset. emotion It can be set to 0.4.

[0093] After the robot completes its interaction with the helper, it needs to process and execute information, transforming the guidance steps provided by the helper into executable task instructions and then carrying them out. The specific logic for information processing and execution is as follows: Figure 3 As shown, the robot understands the helper's guidance steps and extracts key information. From the guidance, it extracts core actions, goals, and conditions, identifying the main tasks to be performed; task decomposition and standardized instructions. Complex steps are broken down into smaller, more specific executable tasks, ensuring each task is independent and clear, and defining the format of task instructions to ensure uniformity; simultaneously, it determines whether the standardized instructions are within the robot's capabilities, and if not, adjusts the tasks to suit the robot's functional capabilities; based on the relationships between tasks, necessary logical judgments and execution sequences are added to ensure the robot's task flow is coherent. Then, based on the complete task list, the robot executes several executable tasks. In this way, by evaluating and selecting the most suitable helper, the cost of seeking assistance is minimized. The human-computer interaction experience is enhanced; when the robot actively communicates with humans, it considers human emotional feedback as an interaction strategy, proactively terminating communication if the human shows negative emotions, improving the interactive experience and increasing the human's willingness to assist the robot.

[0094] Step S14: After executing several executable tasks, determine whether the target task is completed. If not, jump back to the step of constructing a spatial map within the target area until the target task is completed.

[0095] In this embodiment, after executing several executable tasks, it is determined whether the target task is completed. If not, the robot jumps back to the step of constructing a spatial map within the target area. Furthermore, if the number of times the robot executes the step of jumping back to construct the spatial map within the target area equals a preset threshold, and the target task is still not completed, the robot seeks assistance from maintenance personnel to complete the target task. Specifically, after the robot completes the sub-task list obtained through "autonomous help seeking," if it still cannot complete the overall task, the robot will continue to optimize and re-enter the "autonomous help seeking" mode. Considering the robot's current limitations, the number of continuous optimization rounds can be set. In a specific embodiment, this is set to 5 rounds. If 5 rounds of help seeking still do not yield complete information to complete the task, the robot remains stationary for a period of time before continuing to seek help or directly seeking assistance from maintenance personnel. In this way, by designing a strategy for continuous help seeking, the robot can dynamically adjust its strategy even when the help seeking fails, demonstrating strong robustness and task adaptability.

[0096] In summary, during the execution of the target task, the robot in this application first determines the confidence level of the success rate of the target task. Based on the relationship between the confidence level and a preset confidence threshold, it determines whether the robot needs to seek external assistance. If so, a spatial map within the target area is constructed, and a group of objects that can provide assistance is identified and located. Based on the spatial map and the object group, several groups of candidate objects for assistance are determined, and the assistance level value corresponding to each candidate object is determined. Then, the target candidate object corresponding to the highest assistance level value is determined, and interaction is performed with the target candidate object to obtain corresponding guidance information. Based on the guidance information, several executable tasks are determined. Finally, after executing several executable tasks, it is determined whether the target task is completed. If not, the robot returns to the step of constructing the spatial map within the target area until the target task is completed. Therefore, this application uses confidence level to determine whether the robot can complete the task independently. If it cannot complete the task, it seeks external assistance, enabling the robot to autonomously seek external assistance, efficiently integrate the obtained assistance information to complete the task, and improve the reliability of task completion. Simultaneously, by using assistance scores to identify potential help recipients during the process of seeking external help, the efficiency of help selection is optimized. Furthermore, by evaluating and selecting the most suitable help recipient, the cost of seeking assistance is minimized. This, in turn, improves the efficiency and success rate of task completion.

[0097] As described in the previous embodiment, this application determines whether the robot needs external assistance based on the relationship between the confidence level and a preset confidence threshold. Next, the process of determining the confidence level for the success rate of the target task will be explained in detail. See [link to relevant documentation]. Figure 4As shown, this embodiment of the invention discloses a specific method for completing a robot task, including:

[0098] Step S21: Determine the reliability of each sensor data based on the signal strength, signal quality, and signal integrity of each sensor of the robot.

[0099] In this embodiment, the reliability of each sensor in the robot includes the sensor's signal strength, signal quality, and signal integrity. Signal strength indicates whether the sensor's data frame rate meets specifications, and whether signal transmission is intermittent due to wiring issues, resulting in a frame rate that does not meet specifications. Signal quality indicates the signal-to-noise ratio (SNR), whether it meets standard requirements, and whether it has significantly decreased. Signal integrity indicates whether there are local gaps in the signal at its resolution, and the proportion of the effective range to the total range. Sensor reliability varies under different signal strengths, signal qualities, and signal integrity conditions. Different reliability values ​​can be pre-set based on various conditions corresponding to these values, and then the sensor reliability can be directly determined based on the values ​​corresponding to different conditions.

[0100] Step S22: Determine the sensor data confidence level, which characterizes the integrity and accuracy of the sensor data, based on the preset sensor weights corresponding to each sensor of the robot and the reliability of the sensor data.

[0101] In this embodiment, the sensor data confidence level, which characterizes the integrity and accuracy of the sensor data, is determined based on the preset sensor weights corresponding to each sensor of the robot and the reliability of the sensor data. Specifically, Reflecting the completeness and accuracy of sensor data, it is obtained by a weighted sum of the sensor data quality required to complete the current task, with a value range of [0, 1]:

[0102] ;

[0103] in, Let be the weight of the i-th sensor; Let be the reliability of the i-th sensor; N is the number of sensors; Sensor data confidence level is used to characterize the integrity and accuracy of sensor data.

[0104] Step S23: Determine the battery confidence level, which is used to characterize the health of the battery, by measuring the battery capacity, power loss rate, and voltage of the robot's battery.

[0105] In this embodiment, This reflects the battery's health status, indicating its impact on system reliability and task completion capability, and is determined by capacity. Power loss rate ,Voltage Three factors determine:

[0106] ;

[0107] in, This reflects whether the battery can provide enough energy to complete the current task. If the battery capacity meets the expected capacity and has a certain margin, it means that the battery capacity is sufficient; otherwise, there is a risk that the battery capacity will not be able to complete the task.

[0108] ;

[0109] in, This refers to the current battery capacity. For capacity; This is for the projected battery capacity.

[0110] Battery drain rate describes the rate at which a battery's charge decreases during use. Standard drain rates are statistically available. By comparing the current drain rate with the standard rate, it's possible to determine if it conforms to the standard pattern. The difference between the two curves reflects the battery drain rate. V norm This refers to the standardized value of the battery's operating voltage. Based on the upper and lower limits of the battery's design voltage, the actual voltage is normalized to a range of 0 and 1. Here, w_b c w_b d w_b v It can be set to 0.4, 0.25, or 0.35.

[0111] Step S24: Determine the ground complexity based on the number of obstacles, terrain undulation, and width of the travel path in the robot's current environment; determine the environmental confidence level to characterize the complexity of the current environment using the environmental conditions corresponding to the robot's current environment and the ground complexity; the environmental conditions include light intensity, temperature, humidity, and wind speed.

[0112] In this embodiment, This reflects the complexity of the robot's current environment, determined by factors such as lighting, temperature, humidity, wind, and the complexity of the ground.

[0113] ;

[0114] in, This reflects the impact of current lighting conditions on the robot; suitable lighting conditions help sensors and cameras function properly.

[0115] ;

[0116] Where L is the light intensity, [llow , l high The optimal light conditions are when the light level is below 1. lower or higher than l higher At that time, the lighting conditions were considered completely unsuitable.

[0117] f temp This reflects the impact of temperature on the robot's internal components and battery. A suitable temperature range can ensure the robot's normal operation. The formula can be referenced. The formula for f. hum This reflects the impact of humidity on the operational reliability of robot electronic components. Both excessively high and low humidity levels can damage internal electronic components. The formula can be referenced below. The formula for f. wind This reflects the impact of wind speed on the robot's stability; the formula can be found here. The formula is as follows. Considering the influence of various factors on the robot, the weights can be set as w_e1=0.2, w_e2=0.2, w_e3=0.15, w_e4=0.15, w_e5=0.3.

[0118] Next, the complexity of the road surface is decomposed into multiple influencing factors: the number of obstacles, the terrain undulation, and the width of the passage, and a confidence level calculation is performed on the complexity of the robot's working road surface.

[0119] ;

[0120] in, The confidence level for ground complexity; Confidence level reflecting the number of obstacles on the current road surface:

[0121] ;

[0122] Where n is the number of obstacles detected; n max The maximum number of obstacles allowed to appear is preset.

[0123] f terrain This reflects the degree of terrain undulation on the working surface. When the terrain is flat, f terrain =1; when the terrain is highly undulating, such as with many slopes or irregular ground, f terrain =0; For terrain with slight bullying, f is calculated based on slope and irregularity. terrain It decreases linearly between 0 and 1. width This reflects the width of the path; the wider the path, the higher the score, and the narrower the path, the lower the score.

[0124]

[0125] Where w is the path width; w min Minimum path width; w max This represents the maximum path width.

[0126] Step S25: Based on the vector corresponding to the environmental data detected by the robot and the environmental data required to complete the target task, determine the target confidence level used to characterize the degree of support of the environmental data for the target task.

[0127] In this embodiment, This refers to the degree to which currently perceived data supports decision-making for the current task. This applies in situations such as the loss of environmental markers, like road signs, or the inability to detect tools needed for the next task, such as a #5 screw. When it is determined that the current perception data is insufficient to meet the necessary data for task decision-making. It will be very low to activate the "self-help mode".

[0128] ;

[0129] Among them, D sensor D represents the perceived actual dependency vector. task This represents the dependency vector required for the task. The higher the correlation, the better the perceptual data matches the task requirements. The larger the value, the greater the dependency vector D required for the task. task This is a dependency vector composed of the number of environmental objectives required in the current task planning. For example, the current task requires satisfying four conditions: "1. Walk 50 meters, 2. Detect an intersection, 3. Detect a traffic light, 4. The traffic light turns red," before turning right and continuing to walk. A dependency data vector [1, 3, 1, 1] can be established based on the degree of dependency of the conditions. The perceived actual dependency vector D... sensor This refers to the dependency vectors that the robot has already detected and satisfied. For example, if no traffic lights are detected, then the current actual dependency vector D is... sensor It is [1, 3, 0, 0]. At this point...

[0130] .

[0131] Step S26: Determine the confidence level of the target task completion success rate based on the confidence level of the sensor data, the confidence level of the battery, the confidence level of the environment, and the confidence level of the target.

[0132] In this embodiment, the confidence level calculation formula is as follows:

[0133] ;

[0134] in, Confidence level; Confidence level of sensor data; Battery confidence level; For environmental confidence; Target confidence level; The target threshold (the red line threshold for a single factor, when the confidence level of any factor is ≤) At that time, the robot initiates an "autonomous assistance-seeking" mode based on this factor to solve the current factor problem. (This can be a uniform value, or a redline threshold can be set for each factor); w1, w2, w3, and w4 are preset weight values, i.e., the weights of each factor, reflecting the degree of influence of these factors on the confidence level, and the sum of the weights is 1. In a specific embodiment, for an indoor working environment, w1, w2, w3, and w4 can be set to 0.3, 0.2, 0.2, and 0.3 respectively. For an outdoor working environment, w1, w2, w3, and w4 can be set to 0.3, 0.15, 0.15, and 0.4 respectively. The weights can also be dynamically adjusted using an environmental awareness model.

[0135] In this way, this application calculates confidence based on the weights of multiple factors (sensor integrity, environmental complexity, battery health, etc.) and dynamically adjusts the decision-making logic, which can adapt to various scenarios.

[0136] See Figure 5 As shown, an embodiment of the present invention discloses a robot task completion device, comprising:

[0137] The judgment module 11 is used to determine the confidence level of the success rate of the target task during the execution of the target task, and to determine whether the robot needs to seek external assistance based on the relationship between the confidence level and the preset confidence threshold.

[0138] The assistance value determination module 12 is used to construct a spatial map within the target range if the condition is met, identify and locate the group of objects that can provide assistance, determine several groups of candidate objects that can be helped based on the spatial map and the group of objects, and determine the assistance value corresponding to each candidate object that can be helped.

[0139] The executable task determination module 13 is used to determine the target candidate object for help corresponding to the highest assistance value, interact with the target candidate object for help to obtain corresponding guidance information, and determine several executable tasks based on the guidance information.

[0140] The jump module 14 is used to determine whether the target task has been completed after executing several executable tasks. If it has not been completed, it will jump back to the step of constructing a spatial map within the target range until the target task is completed.

[0141] In summary, during the execution of the target task, the robot in this application first determines the confidence level of the success rate of the target task. Based on the relationship between the confidence level and a preset confidence threshold, it determines whether the robot needs to seek external assistance. If so, a spatial map within the target area is constructed, and a group of objects that can provide assistance is identified and located. Based on the spatial map and the object group, several groups of candidate objects for assistance are determined, and the assistance level value corresponding to each candidate object is determined. Then, the target candidate object corresponding to the highest assistance level value is determined, and interaction is performed with the target candidate object to obtain corresponding guidance information. Based on the guidance information, several executable tasks are determined. Finally, after executing several executable tasks, it is determined whether the target task is completed. If not, the robot returns to the step of constructing the spatial map within the target area until the target task is completed. Therefore, this application uses confidence level to determine whether the robot can complete the task independently. If it cannot complete the task, it seeks external assistance, enabling the robot to autonomously seek external assistance, efficiently integrate the obtained assistance information to complete the task, and improve the reliability of task completion. Simultaneously, by using assistance scores to identify potential help recipients during the process of seeking external help, the efficiency of help selection is optimized. Furthermore, by evaluating and selecting the most suitable help recipient, the cost of seeking assistance is minimized. This, in turn, improves the efficiency and success rate of task completion.

[0142] In some specific embodiments, the judgment module 11 can be used to determine the reliability of each sensor data based on the signal strength, signal quality, and signal integrity of each sensor of the robot; determine the sensor data confidence level, which characterizes the integrity and accuracy of the sensor data, based on the preset sensor weights corresponding to each sensor of the robot and the reliability of the sensor data; determine the battery confidence level, which characterizes the battery health level, based on the battery capacity, power loss rate, and voltage of the robot; determine the ground complexity based on the number of obstacles, terrain undulation, and width of the travel path in the robot's current environment; determine the environmental confidence level, which characterizes the complexity of the current environment, using the environmental conditions corresponding to the robot's current environment and the ground complexity; the environmental conditions include light intensity, temperature, humidity, and wind speed; determine the target confidence level, which characterizes the degree of support of the environmental data for the target task, based on the vector corresponding to the environmental data detected by the robot and the environmental data required to complete the target task; and determine the confidence level of the target task completion success rate based on the sensor data confidence level, the battery confidence level, the environmental confidence level, and the target confidence level.

[0143] In some specific embodiments, the judgment module 11 can be used to determine the confidence level of the target task completion success rate based on the confidence level of the sensor data, the battery confidence level, the environmental confidence level, and the target confidence level using a confidence level calculation formula; the confidence level calculation formula is:

[0144] ;

[0145] in, The confidence level; The confidence level of the sensor data; The confidence level of the battery; The confidence level of the environment; The target confidence level; is the target threshold; w1, w2, w3, and w4 are preset weight values.

[0146] In some specific embodiments, the judgment module 11 can be used to determine that the robot needs to seek external assistance if the confidence level is less than or equal to the preset confidence threshold; and to determine that the robot does not need to seek external assistance if the confidence level is greater than the preset confidence threshold.

[0147] In some specific embodiments, the assistance value determination module 12 can be used to construct group structure data based on the spatial map and the information corresponding to the object groups; the group structure data includes data defining the labels of each object group, the surrounding map of each object group, the minimum cost path from the robot to each object group, the age of each object group, and the social role of each object group; and determining several groups of candidate objects for assistance based on the group structure data.

[0148] In some specific embodiments, the assistance value determination module 12 can be used to determine the social attributes of the candidate for assistance based on their clothing and facial expressions; the social attributes include any one or a combination of children, teenagers, middle-aged people, elderly people, primary and secondary school students, high school students, and social service workers; determine the appearance affinity value of the candidate for assistance based on preset scores corresponding to each social attribute; determine the behavior value of the candidate for assistance based on their walking speed and body movements; the body movements include any one or a combination of empty hands, carrying items, and making a phone call; the carrying items movements include several categories of carrying items based on the estimated weight of the items; determine the action cost of the robot reaching the candidate for assistance based on the distance between the robot and the candidate for assistance; and determine the assistance value of each candidate for assistance based on their appearance affinity value, behavior value, and action cost.

[0149] In some specific embodiments, the device can also be used to perform face detection and facial emotion recognition on the target candidate for help, determine the facial expression of the target candidate for help, determine the score corresponding to the facial expression based on the score corresponding to the pre-determined facial expression classification; determine the emotional score of the speech semantics of the target candidate for help based on the pre-determined semantic emotion score; determine the emotional score of the body movements of the target candidate for help through the pre-determined body movement score; determine an emotional willingness value to characterize whether the target candidate for help is willing to provide help based on the score corresponding to the facial expression, the emotional score of the speech semantics, and the emotional score of the body movements; if the emotional willingness value is less than or equal to a preset emotional willingness threshold, then stop interacting with the target candidate for help, move away from the target candidate for help, and re-determine a new candidate for help to interact with in order to obtain corresponding guidance information; if the emotional willingness value is greater than the preset emotional willingness threshold, then interact with the target candidate for help to obtain corresponding guidance information.

[0150] In some specific embodiments, the device can also be used to request assistance from maintenance personnel to complete the target task if the number of times the operation of re-jumping to the spatial map within the target area is equal to a preset threshold and the target task is not completed.

[0151] Furthermore, embodiments of this application also disclose an electronic device, Figure 6 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0152] Figure 6 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the robot task completion method disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0153] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0154] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored thereon can include an operating system 221, computer programs 222, etc., and the storage method can be temporary storage or permanent storage.

[0155] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the robot task completion method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include a computer program capable of performing other specific tasks.

[0156] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed robot task completion method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0157] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0158] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0159] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0160] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0161] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method of robotic task completion, the method comprising: The method comprises the following steps: During the execution of the target task, the confidence of the success rate of the target task is determined, and it is determined whether the robot needs to seek external assistance according to the size relationship between the confidence and a preset confidence threshold; If yes, a space map in a target range is constructed, a group of objects that can provide assistance is identified and located, and a plurality of groups of assistance candidate objects are determined based on the space map and the group of objects, and an assistance degree value corresponding to each assistance candidate object is determined; The target assistance candidate object corresponding to the highest assistance degree value is determined, and the target assistance candidate object is interacted with to obtain corresponding guidance information, and a plurality of executable tasks are determined based on the guidance information; After the plurality of executable tasks are executed, it is determined whether the target task is completed, and if not, the step of constructing the space map in the target range is re-executed until the target task is completed; The confidence of the success rate of the target task is determined, comprising: The reliability of sensor data is determined based on the signal strength, signal quality and signal integrity of each sensor of the robot; The sensor data confidence representing the integrity and accuracy of the sensor data is determined according to the preset sensor weight corresponding to each sensor of the robot and the reliability of the sensor data; The battery confidence representing the health degree of the battery is determined by the capacity, power-off rate and voltage of the battery of the robot; The ground complexity is determined according to the number of obstacles, the degree of terrain undulation and the width of the driving path of the road surface in the current environment of the robot; The environment confidence representing the complexity of the current environment is determined by the environmental conditions corresponding to the current environment of the robot and the ground complexity; the environmental conditions include light intensity, temperature, humidity and wind speed; The target confidence representing the support degree of the environmental data to the target task is determined based on the vector corresponding to the environmental data detected by the robot and the environmental data required to complete the target task; The confidence of the success rate of the target task is determined based on the sensor data confidence, the battery confidence, the environment confidence and the target confidence; The assistance degree value corresponding to each assistance candidate object is determined, comprising: The social attribute of the assistance candidate object is determined according to the clothing and facial expression of the assistance candidate object; the social attribute includes any one or a combination of several of children, adolescents, middle-aged people, old people, primary and secondary school students, high school students and social service providers; The appearance affinity value of the assistance candidate object is determined by the preset score corresponding to each social attribute; The behavior value of the assistance candidate object is determined according to the walking speed and body movement of the assistance candidate object; the body movement includes any one or a combination of several of empty hands, carrying an object and making a phone call; the carrying object action includes a plurality of carrying object actions divided based on the estimated weight degree; The action cost value of the robot to reach the position of the assistance candidate object is determined based on the distance between the robot and the assistance candidate object. Determine the assistance degree value of each of the help-seeking candidate objects through the appearance affinity value, the behavior value and the action cost value corresponding to each of the help-seeking candidate objects.

2. The robotic task completion method of claim 1, wherein, The confidence of the target task completion success rate is determined based on the sensor data confidence, the battery confidence, the environment confidence and the target confidence, including: The confidence of the target task completion success rate is determined based on the sensor data confidence, the battery confidence, the environment confidence and the target confidence through a confidence calculation formula; the confidence calculation formula is: ； wherein, is the confidence; is the sensor data confidence; is the battery confidence; is the environment confidence; is the target confidence; is a target threshold; is a preset weight value.

3. The robotic task completion method of claim 1, wherein, The confidence of the target task completion success rate is determined based on the sensor data confidence, the battery confidence, the environment confidence and the target confidence through a confidence calculation formula; the confidence calculation formula is: The confidence of the target task completion success rate is determined based on the sensor data confidence, the battery confidence, the environment confidence and the target confidence through a confidence calculation formula; the confidence calculation formula is: The confidence of the target task completion success rate is determined based on the sensor data confidence, the battery confidence, the environment confidence and the target confidence through a confidence calculation formula; the confidence calculation formula is:

4. The robotic task completion method of claim 1, wherein, If the confidence is less than or equal to the preset confidence threshold, it is determined that the robot needs to seek external assistance. If the confidence is greater than the preset confidence threshold, it is determined that the robot does not need to seek external assistance. The confidence of the target task completion success rate is determined based on the sensor data confidence, the battery confidence, the environment confidence and the target confidence, including:

5. The robotic task completion method of claim 1, wherein, Based on the information corresponding to the spatial map and the object group, construct group structure data; the group structure data is data defining the labels of each of the object groups, the surrounding maps of each of the object groups, the minimum cost paths of the robot to each of the object groups, the ages of each of the object groups and the social roles of each of the object groups; Determine a plurality of groups of help-seeking candidate objects according to the group structure data. In the process of interacting with the target help-seeking candidate object to obtain the corresponding guidance information, it further includes: Face detection and facial emotion recognition are performed on the target help-seeking candidate object to determine the facial expression of the target help-seeking candidate object, and a score corresponding to the facial expression is determined based on a pre-determined facial expression classification corresponding score; The semantic sentiment score of the speech semantics of the target help-seeking candidate object is determined based on a pre-determined semantic sentiment score; The emotional score of the body movement of the target help-seeking candidate object is determined through a pre-determined body movement score; The emotional willingness value for representing whether the target help-seeking candidate object is willing to provide help is determined based on the score corresponding to the facial expression, the emotional score of the speech semantics and the emotional score of the body movement; 6. The robotic task completion method of any one of claims 1 to 5, wherein, If the emotional willingness value is less than or equal to a pre-set emotional willingness threshold, stop interacting with the target help-seeking candidate object, move away from the target help-seeking candidate object, and re-determine a new help-seeking candidate object for interaction to obtain the corresponding guidance information; If the emotional willingness value is greater than the pre-set emotional willingness threshold, interact with the target help-seeking candidate object to obtain the corresponding guidance information.

7. A robotic task completion device, comprising: After the step of jumping back to the spatial map within the constructed target range, it further includes: If the number of times of performing the operation of jumping back to the spatial map within the constructed target range is equal to a pre-set number threshold, and the target task is not completed, seek help from an operation and maintenance personnel to complete the target task. Including: The judgment module is configured to determine a confidence degree of a success rate of completing the target task in a process of executing the target task, and determine whether the robot needs to seek external assistance according to a size relationship between the confidence degree and a preset confidence threshold; The assistance degree value determination module is configured to, if yes, construct a space map in a target range, identify and locate a group of objects that can provide assistance, determine a plurality of groups of assistance candidate objects based on the space map and the group of objects, and determine an assistance degree value corresponding to each assistance candidate object; The executable task determination module is configured to determine a target assistance candidate object corresponding to a highest assistance degree value, interact with the target assistance candidate object to obtain corresponding guidance information, and determine a plurality of executable tasks based on the guidance information; The jump module is configured to determine whether the target task is completed after the plurality of executable tasks are executed, and if not, jump back to the step of constructing the space map in the target range until the target task is completed. The judgment module is configured to determine a reliability of sensor data based on signal strength, signal quality and signal integrity of each sensor of the robot, determine a sensor data confidence degree representing integrity and accuracy of the sensor data based on a preset sensor weight corresponding to each sensor of the robot and the reliability of the sensor data, determine a battery confidence degree representing a health degree of a battery of the robot based on a capacity degree, a power failure rate and a voltage of the battery, determine a ground complexity degree based on a number of obstacles on a road surface, a terrain undulation degree and a width of a driving path in a current environment of the robot, determine an environment confidence degree representing a complexity degree of the current environment based on an environment condition corresponding to the current environment of the robot and the ground complexity degree, the environment condition including illumination intensity, temperature, humidity and wind speed, determine a target confidence degree representing a support degree of environment data on the target task based on a vector corresponding to the environment data detected by the robot and environment data required to complete the target task, and determine the confidence degree of the success rate of completing the target task based on the sensor data confidence degree, the battery confidence degree, the environment confidence degree and the target confidence degree. The assistance degree value determination module is configured to determine a social attribute of the assistance candidate object based on clothing and facial expressions of the assistance candidate object, the social attribute including any one or a combination of several of children, teenagers, middle-aged people, old people, primary and secondary school students, high school students and social service providers, and determine an appearance affinity value of the assistance candidate object by a preset score corresponding to each social attribute. According to the walking speed of the help-seeking candidate object and the body movement, a behavior value of the help-seeking candidate object is determined; the body movement includes any one or a combination of several of the following: both hands empty, carrying an object, and making a phone call; the carrying an object includes several types of carrying an object obtained by classifying based on the estimated weight of the object; an action cost value of the robot reaching the position of the help-seeking candidate object is determined based on the distance between the robot and the help-seeking candidate object; and a help degree value of each help-seeking candidate object is determined based on the appearance affinity value, the behavior value, and the action cost value of each help-seeking candidate object.

8. An electronic device, comprising: Comprise: a memory for storing a computer program; a processor for executing the computer program to implement the robot task completion method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, a memory for storing a computer program; wherein the computer program is executed by a processor to implement the robot task completion method according to any one of claims 1 to 6.

Images