Evaluation method for collaborative operation of multiple weeding robots based on matter-element theory

Abstract

The invention discloses a matter-element theory-based multi-weeding-robot collaborative operation evaluation method. The method comprises the following steps of 1, constructing an evaluation index system of multi-weeding-robot collaborative operation; step 2, obtaining subjective weight and objective weight of each evaluation index by adopting an order relation analysis method and a CRITIC method respectively; 3, performing joint weighting by adopting a combined weighting method to obtain a combined weight of each evaluation index; and 4, constructing a multi-weeding-robot collaborative operation evaluation model by adopting a matter element analysis method, and determining the evaluation grade of the multi-weeding-robot collaborative operation. The method is smaller in subjectivity, not only can evaluate a certain single index, but also can correspondingly evaluate the overall index.

Description

Technical Field

[0001] The invention relates to the field of robot operation evaluation methods, and in particular to a method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory. Background Art

[0002] The collaborative operation of multiple weeding robots can improve work efficiency. By working simultaneously with multiple weeding robots, weeding tasks can be completed more quickly because each weeding robot can focus on different areas or tasks, reducing the workload of a single weeding robot. The collaborative operation of multiple weeding robots saves time and human resources. When faced with a large area covered with weeds, a single weeding robot may take a long time to complete the task, while multiple weeding robots working simultaneously can shorten the working time and reduce the demand for human resources. The collaborative operation of multiple weeding robots is an effective strategy that can improve efficiency, save time and manpower, and adapt to different types of weed removal needs. Therefore, how to optimize the resource utilization and energy consumption of multiple weeding robots has become a problem that needs to be solved urgently.

[0003] The existing methods for evaluating the economic benefits of agricultural machinery operations can only evaluate the final results, but cannot evaluate each indicator accordingly. The existing methods for evaluating the economic benefits of agricultural machinery operations cannot evaluate the current results based on historical data, and subjectivity has a greater impact on the evaluation results. In addition, it is impossible to accurately identify the key factors that affect the resource utilization and energy consumption of the multi-weeding robot collaborative work system. Summary of the invention

[0004] The present invention provides a method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory, so as to solve the problems that the evaluation of agricultural machinery operation in the prior art cannot be performed according to indicators and the subjectivity has a great influence on the evaluation results.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] A method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory comprises the following steps:

[0007] Step 1: construct an evaluation index system for collaborative operation of multiple weeding robots, wherein the evaluation index system includes multiple evaluation indexes, and multiple evaluation levels are set for each evaluation index;

[0008] Step 2: Use the ordinal relationship analysis method to subjectively weight each evaluation indicator constructed in step 1 to obtain the subjective weight, and use the CRITIC method to objectively weight each evaluation indicator constructed in step 1 to obtain the objective weight;

[0009] Step 3: Based on the subjective weight and objective weight of each evaluation indicator obtained in step 2, a combined weighting method is used to perform joint weighting to obtain a combined weight of each evaluation indicator;

[0010] Step 4: Based on the combined weight of each evaluation index obtained in step 3, a matter-element analysis method is used to construct an evaluation model for collaborative operation of multiple weeding robots, and the evaluation level of the collaborative operation of multiple weeding robots is determined using the evaluation model for collaborative operation of multiple weeding robots.

[0011] In the further step 1, the evaluation index system constructed includes five first-level evaluation indicators, namely working environment A, safety B, trajectory planning C, energy consumption D and weeding E. Each first-level rating indicator has several second-level evaluation indicators, among which:

[0012] The secondary evaluation indicators under working environment A are distance from residential area A1 and difficulty of energy supply A2;

[0013] The secondary evaluation indicators under safety B are the number of collisions B1 and the number of sinking or rollovers B2;

[0014] The secondary evaluation indicators under trajectory planning situation C are area coverage C1, path repetition rate C2, and total travel C3;

[0015] The secondary evaluation indicators under energy consumption D are fuel consumption per kilometer D1 and electricity consumption per kilometer D2;

[0016] The secondary evaluation indicators under weeding condition E are crop injury rate E1, weed removal rate E2 and weeding rate E3.

[0017] In the further step 1, an evaluation level is set for each evaluation indicator, which is divided into level I good, level II better, level III average, level IV poor, and level V poor.

[0018] In the further step 2, the process of the ordinal relationship analysis method is as follows: first, the relevant experts rank the importance of each evaluation indicator; then, according to the ranking results, the importance of two adjacent evaluation indicators is compared, and the importance ratio is scientifically scored, and this importance ratio is the weight ratio. According to the obtained score, the subjective weight of each evaluation indicator is calculated.

[0019] In the further step 2, the CRITIC method process is as follows: first, normalize each evaluation indicator to the same range to form the original data matrix; then, determine the information carrying capacity of each evaluation indicator based on the degree of correlation and comparability between each evaluation indicator and other indicators; finally, determine the objective weight of each evaluation indicator based on the information carrying capacity and the value of each evaluation indicator in the original data matrix.

[0020] In the further step 4, the process of the matter-element analysis method is as follows: first, determine the evaluation matter-element in the collaborative operation of multiple weeding robots, and the evaluation matter-element includes: matter-element name, which is the first-level evaluation index in this method; evaluation object characteristics, which is the second-level evaluation index in this method; value, which is the corresponding measurement value of the second-level evaluation index, obtained by actual detection. Then, based on the determined evaluation matter-element, determine the classical domain and the section domain; then, calculate the correlation function according to the classical domain and the section domain; finally, combine the calculation results of the correlation function and the combined weights of each evaluation index to establish a collaborative operation evaluation model for multiple weeding robots to determine the evaluation level of the collaborative operation of multiple weeding robots.

[0021] The present invention proposes a method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory, aiming to achieve comprehensive optimization of the collaborative operation system of multiple weeding robots. The method decomposes the collaborative operation system of multiple weeding robots into multiple primary indicators, and models and optimizes the matter-element in each primary indicator to achieve the evaluation of resource utilization and energy consumption of the entire system. The comprehensive weight of the evaluation index is determined by combining the ordinal relationship analysis method and the CRITIC method. The ordinal relationship analysis method establishes the ordinal relationship between the indicators by comparing the importance between them. This method can obtain the relative importance ranking between the indicators through expert judgment or questionnaire survey, and the indicators can be divided into grades according to their importance according to the opinions of experts or respondents. The CRITIC method (i.e., CRiteria Importance Through IntercriteriaCorrelation) calculates the correlation between the indicators to determine their relative importance in the decision-making process. Specifically, the CRITIC method calculates the intercriteria coefficient between the indicators to quantify the degree of correlation between them. The higher the correlation coefficient, the stronger the correlation between the indicators and the greater their importance.

[0022] Compared with the prior art, the present invention has the following advantages:

[0023] The method for evaluating the collaborative operation of multiple weeding robots based on the matter-element theory provided by the present invention is based on five primary indicators: working environment, safety, trajectory planning, energy consumption and weeding, and establishes an evaluation index system for the collaborative operation of multiple weeding robots. The order relationship analysis method and the CRITIC method are combined to weight each indicator, and then the combined weighting method is used to determine the weight of the evaluation index of the collaborative operation of multiple weeding robots. The combined weighting is less subjective and can overcome the problem that the weights obtained by the objective method are too different from the reality.

[0024] Compared with the existing agricultural machinery operation economic benefit evaluation method, the advantage of the present invention is that it can not only evaluate a single indicator, but also have a corresponding evaluation of the overall indicator. The collaborative operation of multiple weeding robots can be evaluated based on historical experience, reducing the influence of subjectivity on the evaluation results. The present invention can effectively evaluate the resource utilization and energy consumption of the collaborative work system of multiple weeding robots, and find out the key factors to improve its efficiency and performance. It provides important ideas and methods for the evaluation and optimization of multi-agent collaborative work. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a flow chart for evaluating the collaborative operation of multiple weeding robots according to the present invention.

[0026] Figure 2 This is an evaluation index system for collaborative operation of multiple weeding robots of the present invention.

[0027] Figure 3 This is a flow chart of collaborative operation of multiple weeding robots.

[0028] Figure 4 This is the subjective rating scale given by six experts.

[0029] Figure 5 A summary of the original data.

[0030] Figure 6 Calculate objective weight results for the CRITIC method.

[0031] Figure 7 Calculate the combined weight.

[0032] Figure 8 It is the correlation degree and evaluation level of the secondary indicators.

[0033] Fig. 9 It is the correlation degree and evaluation level of the first-level indicators.

[0034] Fig.10 It is the weighted comprehensive correlation and evaluation level. DETAILED DESCRIPTION

[0035] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0036] This embodiment discloses a method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory. Before the collaborative operation of multiple weeding robots described in this embodiment, the number of weeding robots to be used and the area of ​​cultivated land are determined. This embodiment is described by taking five weeding robots and 260 square meters of cultivated land to be weeded as an example. The collaborative operation process of multiple weeding robots described in this embodiment is as follows:

[0037] First, the upper computer will divide the task area within the working range of the cultivated land, and then issue instructions to all weeding robots, explaining the tasks and assigned areas. After receiving the instructions, each weeding robot will confirm the task and assigned area, and confirm receipt of the instructions to the upper computer. Next, each weeding robot will prepare the equipment, including checking the blades, oil level and fuel. The weeding robot is then started and tested for operation. If the equipment is normal, weeding work will begin. The upper computer will monitor the status of each weeding robot and update the position of the weeding robot in real time to ensure that each weeding robot can cooperate well. The collaborative operation process of multiple weeding robots is as follows: Figure 3 shown.

[0038] like Figure 1 As shown, the method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory in this embodiment includes the following steps:

[0039] Step 1: Construct an evaluation index system for collaborative operation of multiple weeding robots. The evaluation index system includes multiple evaluation indicators, and multiple evaluation levels are set for each evaluation indicator.

[0040] like Figure 2 As shown, in this embodiment, the evaluation index system constructed includes five first-level evaluation indicators, namely, working environment A, safety B, trajectory planning C, energy consumption D and weeding E. Each first-level rating indicator has several second-level evaluation indicators, among which:

[0041] The secondary evaluation indicators under working environment A are distance from residential area A1 and difficulty of energy supply A2.

[0042] The secondary evaluation indicators under safety B are the number of collisions B1 and the number of entrapments or rollovers B2.

[0043] The secondary evaluation indicators under trajectory planning situation C are area coverage C1, path repetition rate C2, and total travel C3.

[0044] The secondary evaluation indicators under energy consumption D are fuel consumption per kilometer D1 and electricity consumption per kilometer D2.

[0045] The secondary evaluation indicators under weeding condition E are crop injury rate E1, weed removal rate E2 and weeding rate E3.

[0046] The evaluation level set for each evaluation indicator is divided into Level I: good, Level II: better, Level III: average, Level IV: poor, and Level V: bad. Therefore, the evaluation level that can be determined for each evaluation indicator (including the first-level evaluation indicator and the second-level evaluation indicator) is any level from Level I to Level V.

[0047] Step 2: Use the ordinal relationship analysis method to subjectively weight each evaluation indicator constructed in step 1 to obtain the subjective weight. The ordinal relationship analysis method process is as follows:

[0048] First, relevant experts ranked the importance of each evaluation indicator;

[0049] Then, the importance of two adjacent evaluation indicators is compared according to the ranking results, and relevant experts will conduct scientific scoring, which is the weight ratio. According to the weight ratio, the subjective weight of the first-level evaluation indicator and the subjective weight of the second-level indicator are determined, and finally the comprehensive subjective weight is determined.

[0050] The subjective weight of each evaluation indicator is calculated according to the following formula:

[0051]

[0052] W n-1 =r k W n (2)

[0053] In formula (1) and (2): r k =W n-1 / W n is the weight ratio, that is, the importance ratio (k=n, n-1, ... 2); n is the number of evaluation indicators. In the calculation of the first-level indicators in this embodiment, n=5, including 5 first-level evaluation indicators. In the calculation of the second-level indicators, the value of n is based on the number of indicators under each first-level indicator; W n is the subjective weight of the nth indicator, W n-1 is the subjective weight of the n-1th indicator; r i is the ratio of subjective weights. The components of the corresponding weight vector obtained after G1 method sorting are expressed as P i .

[0054] In this embodiment, industry experts are invited to rank the importance of the primary evaluation indicators and the secondary evaluation indicators and score the importance ratio. The expert scoring results are as follows: Figure 4 Then the scoring results of expert 1 for the first-level evaluation indicators are processed as follows, and the scores of other experts and experts for the second-level evaluation indicators are processed in the same way:

[0055]

[0056] W4=r5W5=0.973×0.219=0.213

[0057] W3=r4W4=0.944×0.213=0.201

[0058] W2=r3W3=0.970×0.201=0.195

[0059] W1=r2W2=0.882×0.195=0.172

[0060] The six expert subjective weights calculated in this way are averaged to reduce the deviation caused by the subjective factors of the expert group. The secondary indicators are calculated in the same way. The results are as follows: Figure 7 As shown:

[0061] Working environment A=(0.172+0.193+0.102+0.051+0.099+0.098) / 6=0.1192.

[0062] Safety B = (0.195 + 0.183 + 0.109 + 0.107 + 0.157 + 0.187) / 6 = 0.1563.

[0063] Trajectory planning index C = (0.213 + 0.103 + 0.183 + 0.244 + 0.189 + 0.145) / 6 = 0.1795.

[0064] Energy consumption D = (0.201 + 0.205 + 0.292 + 0.295 + 0.242 + 0.233) / 6 = 0.2447.

[0065] Weed control situation E = (0.219 + 0.316 + 0.314 + 0.303 + 0.313 + 0.337) / 6 = 0.3003.

[0066] In this embodiment, the CRITIC method is also used to objectively weight each evaluation indicator constructed in step 1 to obtain an objective weight. The CRITIC method process is as follows:

[0067] First, data standardization is performed to normalize each evaluation index to the same range to form the original data matrix. Since the evaluation criteria and magnitude of each evaluation index are different, it is necessary to compare each evaluation index to the same range. Suppose there are m objects to be evaluated and n evaluation indexes, then the value of the jth index of the i-th group of data is x ij , thus forming the original data matrix X = (x ij ) m×n .

[0068] Normalization formula for the smaller the better indicator

[0069] Normalization formula for the larger the better indicator

[0070] Among them, max(x j ) represents the maximum value of the evaluation index j, min(x j ) represents the minimum value of the evaluation index j.

[0071] Then, the information carrying capacity of each evaluation indicator is determined according to the correlation and comparability of each evaluation indicator with other indicators. Suppose the information carrying capacity of evaluation indicator j is C j , then C j =σ j f j Where f j It represents the contradiction between the evaluation index j and other evaluation indexes, that is, the correlation between different evaluation indexes; σ j It represents the standard deviation, which can be used to represent the comparativeness of j evaluation indicators, and:

[0072]

[0073]

[0074]

[0075] In formulas (3), (4), and (5): r ij It represents the Pearson correlation coefficient between evaluation index i and evaluation index j, which is a linear correlation function; Indicates that the index x ij The average value from the 1st to the nth group.

[0076] Finally, the objective weight of each evaluation index is determined according to the information carrying capacity and the value of each evaluation index in the original data matrix. j The larger the objective weight w is, the j The larger the value, the objective weight calculation formula is as follows:

[0077]

[0078] In this embodiment, the objective weight is calculated based on the above formula according to the original data obtained from the experiment. The original data is summarized as follows: Figure 5 According to the calculation method of CRITIC method, the following can be obtained: Figure 6 CRITIC weight calculation results.

[0079] Step 3: Based on the subjective weight and objective weight of each evaluation indicator obtained in step 2, a combined weighting method is used to perform joint weighting to obtain the combined weight of each evaluation indicator.

[0080] The combined weight is to combine the subjective weight and the objective weight, and use the linear weighting method to get the final weight. The combined weight method is less subjective and can overcome the problem that the weight obtained by the objective method is too different from the reality.

[0081] The formula for calculating the combined weight is:

[0082] w i =αw 1 +βw 2 (7)

[0083] The formula for assigning subjective and objective weights is:

[0084]

[0085] In formulas (7) and (8): w i represents the combined weight; w 1 represents the subjective weight calculated in step 2; w 2 represents the objective weight calculated in step 3; n is the number of evaluation indicators; α represents the proportion of subjective weight in the comprehensive weight, and β represents the proportion of objective weight in the comprehensive weight; P i is the component of the corresponding weight vector obtained after sorting by the G1 method.

[0086] Step 4: Based on the combined weight of each evaluation index obtained in step 3, the matter-element analysis method is used to construct a collaborative operation evaluation model for multiple weeding robots, and the evaluation level of the collaborative operation of multiple weeding robots is determined using the collaborative operation evaluation model for multiple weeding robots. The process of the matter-element analysis method is as follows:

[0087] First, determine the evaluation object element in the collaborative operation of multiple weeding robots. The evaluation object element includes: object element name N, which is the first-level evaluation index in this method; evaluation object feature C, which is the second-level evaluation index in this method; value V, which is the corresponding measurement value of the second-level evaluation index, obtained by actual detection. The evaluation object element is recorded as R = (N, C, V), which can be expressed as the following matrix:

[0088]

[0089] In formula (9): c1, c2, … c n are multiple features of matter-element N, which are secondary evaluation indicators in this method. n The value corresponding to each feature.

[0090] Then, the classic domain and section domain of each first-level indicator are determined as follows:

[0091]

[0092]

[0093] In formula (10) and (11): R j represents the classic domain of the evaluation index; (a jn ,b jn ) represents the value range of the nth evaluation index under the jth evaluation level; Rp Represents the section domain of the evaluation index, (a pn ,b pn ) represents the value range of the nth feature, that is, the sum of all classical domains; v jn represents the value of the nth evaluation index under the jth evaluation level; v pn Indicates the value range of the evaluation level.

[0094] In this embodiment, the classical domain and section domain of each indicator of the evaluation system are determined as follows:

[0095]

[0096]

[0097] Next, the correlation function is calculated based on the classical domain and the node domain to obtain the correlation degree of the multi-weeding robot collaborative operation evaluation model and determine the safety level of the indicator:

[0098]

[0099]

[0100] In formulas (12) and (13), ρ(v0,v) represents the distance between v0 and the finite interval v within the value range, and ρ(v i ,V pi ),ρ(v i ,V ji ) Similarly; k j (v i ) represents the correlation degree of each indicator; V pi 、V ji are finite intervals of the nodal domain and the classical domain respectively; v i For a finite interval V pi 、V ji v0 is any point in the finite interval v; v is a finite interval containing the point v0; a is the lower limit of the interval, b is the upper limit of the interval; c0 is the value of the point v0 in the finite interval.

[0101] Finally, combining the calculation results of the correlation function and the combined weights of various evaluation indicators, an evaluation model for the collaborative operation of multiple weeding robots is established to determine the evaluation level of the collaborative operation of multiple weeding robots. The evaluation level calculation formula is:

[0102]

[0103] In formula (14): K i represents the comprehensive correlation, w i is the indicator weight.

[0104] This embodiment determines five evaluation levels, namely, I (good), II (better), III (average), IV (poor), and V (bad). In extenics, when the index interval is unbounded, a threshold can be taken in the boundary interval to form a bounded interval, and the threshold taken will not affect the correlation and subsequent calculations. Figure 8 It is the correlation degree of secondary indicators and the corresponding evaluation level based on experimental data.

[0105] After determining the evaluation level of the object element at the indicator layer, reverse analysis is performed step by step towards the target layer. Fig. 9 It is the correlation degree and evaluation level of the first-level indicators. It can be seen that energy replenishment is difficult, the path repetition rate, total travel and crop damage rate are high, and the full coverage trajectory planning algorithm needs to be improved. Energy consumption needs to be improved.

[0106] Based on the matter-element extension model, the maximum correlation principle shows that the evaluation level of the sample multi-weeding robot collaborative operation is III. The comprehensive correlation of each level is as follows: Fig.10 shown.

[0107] In terms of algorithm, the matter-element extension evaluation model is used to calculate the comprehensive correlation and the evaluation level of each level of indicators; the final evaluation result of the collaborative operation of multiple weeding robots is obtained according to the evaluation level of the first-level indicator.

[0108] The overall evaluation of the collaborative operation of multiple weeding robots in this embodiment is average, indicating that the efficiency of the collaborative work system of multiple weeding robots needs to be improved.

[0109] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. The embodiments described in the present invention are merely descriptions of the preferred embodiments of the present invention, and do not limit the concept and scope of the present invention. The various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction, and such combinations should also be regarded as the contents disclosed in the present disclosure as long as they do not violate the concept of the present invention. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

[0110] The present invention is not limited to the specific details of the above-mentioned embodiments. Within the technical concept of the present invention and without departing from the design concept of the present invention, various modifications and improvements made to the technical solution of the present invention by technical personnel in this field should fall within the protection scope of the present invention. The technical contents for which protection is sought in the present invention have been fully recorded in the claims.

Claims

1. A method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory, characterized in that: The following steps are involved: Step 1: construct an evaluation index system for collaborative operation of multiple weeding robots, wherein the evaluation index system includes multiple first-level evaluation indicators, and each first-level evaluation indicator includes multiple second-level indicators. This method sets multiple evaluation levels for each evaluation indicator, and subdivides the level to which each indicator belongs; Step 2: Use the ordinal relationship analysis method to subjectively weight each evaluation indicator constructed in step 1 to obtain the subjective weight, and use the CRITIC method to objectively weight each evaluation indicator constructed in step 1 to obtain the objective weight; Step 3: Based on the subjective weight and objective weight of each evaluation indicator obtained in step 2, a combined weighting method is used to perform joint weighting to obtain a combined weight of each evaluation indicator; Step 4: Based on the combined weight of each evaluation index obtained in step 3, a matter-element analysis method is used to construct an evaluation model for collaborative operation of multiple weeding robots, and the evaluation level of the collaborative operation of multiple weeding robots is determined using the evaluation model for collaborative operation of multiple weeding robots.

2. The method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory according to claim 1, characterized in that: In step 1, the evaluation index system constructed includes five first-level evaluation indicators, namely working environment A, safety B, trajectory planning C, energy consumption D and weeding E. Each first-level rating indicator has several second-level evaluation indicators, among which: The secondary evaluation indicators under working environment A are distance from residential area A1 and difficulty of energy supply A2; The secondary evaluation indicators under safety B are the number of collisions B1 and the number of sinking or rollovers B2; The secondary evaluation indicators under trajectory planning situation C are area coverage C1, path repetition rate C2, and total travel C3; The secondary evaluation indicators under energy consumption D are fuel consumption per kilometer D1 and electricity consumption per kilometer D2; The secondary evaluation indicators under weeding condition E are crop injury rate E1, weed removal rate E2 and weeding rate E3.

3. The method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory according to claim 1, characterized in that: In step 1, an evaluation level is set for each evaluation indicator, which is divided into level I good, level II good, level III average, level IV poor, and level V poor.

4. The method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory according to claim 1, characterized in that: In step 2, the process of ordinal relation analysis is as follows: first, relevant experts rank the importance of each evaluation indicator; Then, the importance of two adjacent evaluation indicators is compared according to the ranking results, and the importance ratio is scientifically scored. This importance ratio is the weight ratio. According to the obtained score, the subjective weight of each evaluation indicator is calculated.

5. The method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory according to claim 1, characterized in that: In step 2, the CRITIC method process is as follows: first, normalize each evaluation indicator to the same range to form an original data matrix; then, determine the information carrying capacity of each evaluation indicator based on the degree of correlation and comparability between each evaluation indicator and other indicators; finally, determine the objective weight of each evaluation indicator based on the information carrying capacity and the value of each evaluation indicator in the original data matrix.

6. The method for evaluating the collaborative operation of multiple weeding robots based on matter-element theory according to claim 1, characterized in that: In step 4, the process of matter-element analysis is as follows: first, determine the evaluation matter-element in the collaborative operation of multiple weeding robots. The evaluation matter-element includes: matter-element name, which is the first-level evaluation index in this method; evaluation object characteristics, which is the second-level evaluation index in this method; value, which is the corresponding measurement value of the second-level evaluation index, obtained by actual detection. Then, determine the classical domain and the section domain based on the determined evaluation matter-element; then, calculate the correlation function based on the classical domain and the section domain; finally, combine the calculation results of the correlation function and the combined weights of each evaluation index to establish a collaborative operation evaluation model for multiple weeding robots to determine the evaluation level of the collaborative operation of multiple weeding robots.

Images