Group adaptive behavior control method, device and equipment based on visual perception
By obtaining visual image information within the 360-degree field of sight of individuals in unmanned clusters, visual perception functions and decision equations are constructed, and the problem of simple communication and motion patterns in the existing technology of unmanned cluster systems is solved, and the external stimulation is achieved Deep adaptive behavior and efficient adaptability.
Patent Information
- Application Number
- CN202210808707.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-11
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2042-07-11
AI Technical Summary
The existing unmanned cluster system based on visual perception relies on communication during the construction process and can only reproduce simple cluster motion patterns, and fails to deeply explore group adaptive behaviors that adapt to different external stimuli.
By obtaining visual image information within the 360-degree field of sight of individuals in the group, a visual perception function is constructed, the self-propelling force and position force are determined, and the speed decision equation is formulated to achieve the update of individual motion state and the acquisition of position information.
It realizes group adaptive behavior under different external stimuli, improves the adaptability and behavioral ability of unmanned clusters to stimuli, and is in line with the visual perception method of biological individuals.
Smart Images

Figure CN115202392B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image vision technology, and in particular to a method, device and equipment for controlling group adaptive behavior based on visual perception. Background Art
[0002] In recent years, unmanned swarm systems have been widely used in military and civilian fields, especially in the field of Internet of Things, due to their cost advantages, robust self-healing, and capacity multiplication. With the rapid development of Internet of Things technology, unmanned swarm systems have been used in information collection, transmission, and processing, thereby realizing environmental exploration, relay communication, and disaster monitoring. There is no doubt that unmanned swarm systems have become a key node in Internet of Things technology. However, with the popular use of unmanned swarm systems in the Internet of Things, the requirements for unmanned swarm systems are also constantly increasing. Facing different task requirements, unmanned swarm systems need to effectively respond to complex and changing external stimuli to adapt to different task environments.
[0003] In order to meet the adaptive requirements of unmanned swarms to different external stimuli, the inherent mechanism of biological group behavior is very useful for the construction of unmanned swarm systems with adaptive capabilities. Inspired by Geisler et al.'s work on visual detection in the visual cortex of higher animals, Pearce et al. first proposed a swarm motion model based on visual perception for bird flocks to control their density. This type of model abandons the original information exchange method that relies on communication between individuals. Individuals only obtain relative information about their neighbors through vision and make decisions based on this. Bastien et al. designed repulsion and attraction interactions between individuals using visual perception functions representing whether the visual field is blocked in all directions as input, realized 6 swarm motion modes and clarified the parameter range of each mode. Regarding crowd behavior, Dachner et al. found through virtual reality technology that individuals will make adaptive responses to visual occlusion changes of neighbors in different directions. Based on this, a crowd motion model was proposed to control the speed and direction of individuals by changing the relative direction and occlusion of neighbors in the individual's field of view. Inspired by fish schools, Berlinger et al. used micro underwater robots to realize the task sequence of searching for targets and gathering towards targets and the vortex motion mode. In their underwater robot system, each robot carries two light-emitting diodes, so that the robot can deduce the relative position and relative distance of its neighbors based on the position of the diodes obtained by the camera, which can be used as the input of the cluster model. In addition, for fish schools, Harpaz et al. found through data analysis that fish decide to turn left or right to get closer or farther away from their neighbors based on the difference in binocular visual occlusion, and this interaction method is different between juveniles and adult fish.
[0004] Although existing methods can effectively reproduce various cluster motion patterns of biological groups and migrate them to unmanned clusters, existing methods still have many shortcomings. On the one hand, the existing classical methods are far from the actual perception mode of biological groups, and the construction process of unmanned clusters needs to be based on communication dependence. On the other hand, the existing vision-based clustering methods only stay at the stage of reproducing simple consistent movement and vortex and other motion patterns, and have not conducted in-depth exploration of unmanned cluster mission scenarios to construct adaptive behaviors of groups under different external stimuli. Summary of the invention
[0005] Based on this, it is necessary to provide a group adaptive behavior control method, device and equipment based on visual perception to address the above technical problems.
[0006] A group adaptive behavior control method based on visual perception, the method comprising:
[0007] Obtain visual image information of other individuals and external stimuli within the field of view of the current individual in the group; the visual image information is the line of sight at each relative orientation in the individual reference coordinate system; the individual reference coordinate system is constructed with the speed of the current individual as the 0 degree direction of the individual relative orientation and the counterclockwise direction as the positive direction of the relative orientation.
[0008] The visual perception function of the current individual is determined according to the visual image information.
[0009] According to the current individual speed and the expected speed, the self-propulsion force of the current individual is determined.
[0010] According to the visual perception function, the position force of the current individual is determined.
[0011] A speed decision equation of the current individual is determined according to the self-propulsion force and the position force.
[0012] According to the speed decision equation of the current individual, the speed information of the current individual at the current moment is determined.
[0013] According to the speed information at the current moment, the motion state of the current individual is updated to obtain the position information of the current individual at the next moment.
[0014] In one embodiment, the visual image information is obtained by the current individual based on the counterclockwise direction as the positive direction, using the visual perception method with the current individual's own position as the center and the current individual's speed as the 0 degree direction of the individual's relative direction to obtain the visual distance information of each relative direction within a 360-degree range, and the current individual distinguishes the visual distance information of each relative direction of other individuals and external stimuli; according to the visual image information, determining the visual perception function of the current individual includes:
[0015] The visual distance information at infinity and the visual distance information of external stimuli greater than the threshold for distinguishing repulsion and attraction are deleted to obtain the visual perception function of the current individual.
[0016] In one embodiment, determining the self-propulsion force of the current individual according to the current individual speed and the expected speed includes:
[0017] According to the current individual speed and expected speed, the self-propulsion force of the current individual is determined as:
[0018]
[0019] Among them, F ind is the self-propulsion force, γ is the self-propulsion constant, v o is the expected velocity, v i (t) is the velocity of individual i at the current time t.
[0020] In one embodiment, the position force of the current individual includes the position force generated by the current individual under the influence of other individuals and external stimulus visual distance information within the visual field; the position force is divided into repulsive force and attractive force; according to the visual perception function, determining the position force of the current individual includes:
[0021] According to the visual perception function, the position force of the current individual is determined as:
[0022]
[0023] Among them, F pos [D i (φ i , t)] is the position force of the current individual i, D i (φ i , t) is the visual perception function obtained by the current individual i at the current time t, d is the threshold for distinguishing repulsion and attraction, λ is the balance parameter of attraction and repulsion, α and β are used to control the speed v of the current individual respectively i and the velocity direction ψ i Change, φ i is the relative position of the current individual i, by setting c0sφ i and sinφ i As a factor of the position force, we consider the position force on the velocity v i and the velocity direction ψ i The impact of change.
[0024] When the repulsive force and attractive force distinction threshold is greater than the relative position φ of the current individual i at the current time t iWhen the viewing distance information of the visual perception function is in the relative position, the position force generated by the viewing distance information of the relative position on the current individual i is a repulsive force; because the viewing distance information of the external stimulus that is greater than the threshold for distinguishing between repulsive force and attractive force is deleted in the process of obtaining the visual perception function, the position force generated by the viewing distance information of the external stimulus on the current individual is only a repulsive force.
[0025] When the repulsive force and attractive force distinction threshold is less than the relative position φ of the current individual i at the current time t i When the viewing distance information of the visual perception function is , the position force generated by the viewing distance information of the relative position on the current individual i is attractive.
[0026] In one embodiment, the speed decision equation of the current individual is determined according to the self-propulsion force and the position force, including:
[0027] According to the self-propulsion force and the position force, the speed decision equation of the current individual is determined as:
[0028]
[0029] in, is the speed change of the current individual, F ind (v i ) is the self-propulsion force of the current individual i, F pos [D i (φ i , t)] is the position force of the current individual i, D i (φ i , t) is the visual perception function obtained by the current individual i at the current time t, φ i is the relative position of the current individual i, v i (t) is the velocity of individual i at the current time t.
[0030] In one embodiment, determining the speed information of the current individual at the current moment according to the speed decision equation of the current individual includes:
[0031] The speed decision equation of the current individual is projected in the direction parallel to the speed and in the direction perpendicular to the speed to obtain the speed magnitude decision equation and direction decision equation of the current individual.
[0032] The speed decision equation of the current individual is:
[0033]
[0034] The direction decision equation of the current individual is:
[0035]
[0036] in, is the unit vector parallel to the velocity of the current individual i at the current time t, The unit vector perpendicular to the velocity of the current individual i at the current time t, v o is the expected velocity, v i (t) is the speed of the current individual i at the current time t, α and β are the speed v of the current individual respectively. i and the velocity direction ψ i The change control constant of i is the relative position of the current individual i; D i (φ i , t) is the visual perception function obtained by the current individual i at the current time t, v i (t) is the velocity of the current individual i at the current time t, d is the threshold for distinguishing between repulsion and attraction, λ is the balance parameter between attraction and repulsion, ψ i (t) is the velocity direction of the current individual i at the current time t.
[0037] In one embodiment, the motion state of the current individual is updated according to the speed information at the current moment to obtain the position information of the current individual at the next moment, including:
[0038] According to the speed magnitude change value and speed direction change value of the current individual, the position change of the current individual is determined to obtain the position driving equation of the current individual; the position driving equation of the current individual is:
[0039]
[0040]
[0041] in, The current position change of individual i.
[0042] A group adaptive behavior control device based on visual perception, the device comprising:
[0043] The visual perception module is used to obtain the visual image information of other individuals and external stimuli within the field of view of the current individual in the group; the visual image information is the visual distance at each relative orientation in the individual reference coordinate system; the individual reference coordinate system is constructed with the speed of the current individual as the 0 degree direction of the individual relative orientation and the counterclockwise direction as the positive direction of the relative orientation.
[0044] The visual image information processing module is used to determine the visual perception function of the current individual according to the visual image information.
[0045] The decision module is used to determine the self-propulsion force of the current individual according to the speed of the current individual and the expected speed; determine the position force of the current individual according to the visual perception function; determine the speed decision equation of the current individual according to the self-propulsion force and the position force; and determine the speed information of the current individual at the current moment according to the speed decision equation of the current individual.
[0046] The driving module is used to update the motion state of the current individual according to the speed information to obtain the position information of the current individual at the next moment.
[0047] In one of the embodiments, the visual image information is obtained by the current individual based on the counterclockwise direction as the positive direction, using a visual perception method with the current individual's own position as the center and the current individual's speed as the 0-degree direction of the individual's relative direction to obtain the line of sight information of each relative direction within a 360-degree range, and the current individual distinguishes the line of sight information of each relative direction of other individuals and external stimuli; the visual image information processing module is also used to delete the line of sight information at infinity and the line of sight information of external stimuli greater than the repulsion and attraction distinction threshold, to obtain the visual perception function of the current individual.
[0048] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.
[0049] The above-mentioned method, device and equipment for controlling adaptive group behavior based on visual perception include: obtaining visual image information of other individuals and external stimuli within the visual range of the current individual in the group at the current position; determining the visual perception function of the current individual according to the visual image information; determining the self-propulsion force of the current individual according to the speed and expected speed of the current individual; determining the position force of the current individual according to the visual perception function; determining the speed decision equation of the current individual according to the self-propulsion force and the position force; determining the speed information of the current individual at the current moment according to the speed decision equation of the current individual; updating the motion state of the current individual according to the speed information at the current moment, and obtaining the position information of the current individual at the next moment. This method starts from the visual perception of biological individuals, uses visual information as input to construct an interaction mode between individuals, realizes adaptive group behavior under different external stimuli, and improves the adaptive behavior and ability of unmanned clusters to stimuli. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] Figure 1 is a flow chart of a group adaptive behavior control method based on visual perception in one embodiment;
[0051] Figure 2 A schematic diagram of an individual reference coordinate system in another embodiment;
[0052] Figure 3 is N different individuals in a 2-dimensional space in another embodiment;
[0053] Figure 4 It is a schematic diagram of obtaining the visual distance information corresponding to each relative orientation of the surrounding 360 degrees by the current individual in another embodiment;
[0054] Figure 5 A schematic diagram of a visual perception function for obtaining a high-order method of individual information in another embodiment;
[0055] Figure 6 A schematic diagram of a visual perception function for acquiring low-order individual information in another embodiment;
[0056] Figure 7 A schematic diagram of position force magnitudes corresponding to different relative distances under different parameters λ when d=2 in one embodiment;
[0057] Figure 8 In another embodiment, the speed direction and speed magnitude decision under the repulsive force generated by the current individual observing the viewing distance information of a single neighbor at different relative positions, wherein (a) is the effect of the repulsive force on the speed direction, and (b) is the effect of the repulsive force on the speed magnitude;
[0058] Fig. 9 In another embodiment, the speed direction decision is made under the effect of attraction generated by the current individual observing the visual distance information of a single neighbor at different relative positions;
[0059] Fig.10 In another embodiment, the speed size decision is made under the effect of attraction generated by the current individual observing the visual distance information of a single neighbor at different relative positions;
[0060] Fig.11 is a structural block diagram of a group adaptive behavior control device based on visual perception in one embodiment;
[0061] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0063] In one embodiment, Figure 1 As shown, a group adaptive behavior control method based on visual perception is provided, and the method comprises the following steps:
[0064] Step 100: Obtain visual image information of other individuals and external stimuli within the visual range of the current individual in the group at the current position.
[0065] The visual image information is the visual distance at each relative position in the individual reference coordinate system; the individual reference coordinate system is constructed with the current individual speed as the 0 degree direction of the individual relative position and the counterclockwise direction as the positive direction of the relative position. Figure 2 As shown. The individual takes its own speed direction as the reference direction and obtains the relative orientation φ i The corresponding distance information.
[0066] Among them, the group is an unmanned cluster system, which can be a group composed of multiple drones or a group composed of multiple task robots. No specific restrictions are made here. Taking the task robot group as an example, the task robots include the current task robot and other task robots within the field of view of the current task robot; the current task robot performs adaptive behavior control based on the visual distance information obtained from other task robots and external stimuli. A camera can be set on the task robot to obtain environmental image information. The camera can rotate in various degrees of freedom to obtain the surrounding environmental information. In addition, there can be multiple cameras, each responsible for determining the visual distance information within the field of view, so as to obtain the visual distance information of the 360-degree field of view through splicing. Therefore, there are many ways to obtain visual image information of other individuals within the field of view. This embodiment does not make specific restrictions on the steps of obtaining visual image information.
[0067] In this embodiment, a 2D space at position r is considered. i N moving circular individuals with a diameter of BL, the current individual velocity vector v i It can be decomposed into the velocity magnitude v i and the velocity direction ψ i ,like Figure 3 shown. Figure 3 The dynamics of individual i in is represented by the position r i and speed v i is described, and its velocity direction ψ i is the angle between the velocity vector and the horizontal axis.
[0068] Step 102: Determine the visual perception function of the current individual according to the visual image information.
[0069] Specifically, the visual perception function is the relative position φ obtained by the current individual i at time t i The visual distance information does not include the visual distance information at infinity and the visual distance information of external stimuli greater than the threshold for distinguishing repulsion and attraction.
[0070] Step 104: Determine the self-propulsion force of the current individual according to the current individual speed and the expected speed.
[0071] Step 106: Determine the position force of the current individual according to the visual perception function.
[0072] Specifically, the position force of the current individual refers to the attraction or repulsion generated by the visual distance information of other individuals within the current individual's field of view, and the repulsion generated by the visual distance information of external stimuli observed within the current individual's field of view.
[0073] Set a threshold for distinguishing between repulsive force and attractive force, compare the visual perception function at each relative position with the threshold for distinguishing between repulsive force and attractive force, obtain a comparison result, and determine the type of position force generated by the relative position sight distance information on the current individual according to the relative position sight distances within the current individual's field of vision and the comparison result. Specifically: when the visual perception function at a relative position is greater than the threshold for distinguishing between repulsive force and attractive force, the position force of the position sight distance information on the current individual is attractive force; when the visual perception function at a relative position is less than the threshold for distinguishing between repulsive force and attractive force, the position force of the position sight distance information on the current individual is repulsive force.
[0074] Step 108: Determine the speed decision equation of the current individual according to the self-propulsion force and the position force.
[0075] Step 110: Determine the speed information of the current individual at the current moment according to the speed decision equation of the current individual.
[0076] Step 112: Update the motion state of the current individual according to the speed information at the current moment, and obtain the position information of the current individual at the next moment.
[0077] In the above-mentioned group adaptive behavior control method based on visual perception, the method includes: obtaining visual image information of other individuals and external stimuli within the visual range of the current individual in the group at the current position; determining the visual perception function of the current individual based on the visual image information; determining the self-propulsion force of the current individual based on the speed and expected speed of the current individual; determining the position force of the current individual based on the visual perception function; determining the speed decision equation of the current individual based on the self-propulsion force and the position force; determining the speed information of the current individual at the current moment based on the speed decision equation of the current individual; updating the motion state of the current individual based on the speed information at the current moment to obtain the position information of the current individual at the next moment. This method starts from the visual perception of biological individuals, uses visual information as input to construct an interaction mode between individuals, realizes group adaptive behavior under different external stimuli, and improves the adaptive behavior and ability of unmanned clusters to stimuli.
[0078] In one of the embodiments, the visual image information is obtained by the current individual based on the counterclockwise direction as the positive direction, using a visual perception method with the current individual's own position as the center and the current individual's speed as the 0-degree direction of the individual's relative direction to obtain the line of sight information of each relative direction within a 360-degree range, and the current individual distinguishes the line of sight information of each relative direction of other individuals and external stimuli; step 102 includes: obtaining visual information of other individuals and external stimuli based on the visual image information; deleting the line of sight information at infinity and the line of sight information of external stimuli greater than the repulsion and attraction distinction threshold, and obtaining the visual perception function of the current individual.
[0079]
[0080] in and are parallel and perpendicular to v respectively. i The unit vector of .
[0081] Specifically, in the individual reference coordinate system, the current individual takes the counterclockwise direction as the positive direction (φ i >0) Use visual perception to obtain the surrounding φ centered on itself i ∈[-π,π] The relative distances of the relative directions within the range, such as Figure 4 As shown, the dark gray and light gray areas represent the repulsive area and the attractive area, respectively. Then, in the judgment process, the current individual screens the information, removes the visual distance information of the infinite distance and the external stimuli greater than the repulsive force and attractive force distinction threshold, and obtains Figure 5 or Figure 6 The visual perception function D shown i (φ i , t). Among them, Figure 5 Represents a higher-order observation method for organisms, in which individuals can distinguish between individuals; correspondingly, Figure 6 It is a low-level observation method of organisms, in which individuals cannot distinguish each other. In this method, individuals only distinguish between objects of different categories, but not between different objects of the same category, that is, individuals only distinguish between external stimuli and other individuals.
[0082] In one embodiment, step 104 includes: determining the self-propulsion force of the current individual according to the current individual speed and the expected speed as:
[0083]
[0084] Among them, F ind is the self-propulsion force, γ is the self-propulsion constant, v o is the expected velocity, v i(t) is the speed of the current individual i at the current time t. Self-driving F ind Represented by a linear function.
[0085] In one embodiment, the position force of the current individual includes the position force generated by the current individual under the relative position distance information within the visual field; the position force is divided into repulsive force and attractive force; step 106 includes: according to the visual perception function, determining the position force of the current individual as:
[0086]
[0087] Among them, F pos [D i (φ i , t)] is the position force of the current individual i, D i (φ i , t) is the visual perception function obtained by the current individual i at the current time t, d is the threshold for distinguishing repulsion and attraction, λ is the balance parameter of attraction and repulsion, α and β are used to control the speed v of the current individual respectively i and the velocity direction ψ i Change; φ i is the relative position of the current individual i, by setting cosφ i and sinφ i As a factor of the position force, we consider the position force on the velocity v i and the velocity direction ψ i The impact of change.
[0088] When the threshold for distinguishing repulsion and attraction is greater than the relative position φ of the current individual i at the current time t i When the visual distance information of the visual perception function is at the relative position φ, the position force generated by the visual distance information of the relative position on the current individual i is a repulsive force; because the visual distance information of the external stimulus greater than the repulsive force and attractive force distinction threshold is deleted during the visual perception function acquisition process, the position force generated by the visual distance information of the external stimulus on the current individual is a repulsive force; when the repulsive force and attractive force distinction threshold is less than the relative position φ of the current individual i at the current time t i When the viewing distance information of the visual perception function is , the position force generated by the viewing distance information of the relative position on the current individual i is attractive.
[0089] Specifically, the position force F pos The visual perception function D obtained at the current time t i (φ i , t) is the input, by setting D i (φ i , t)-d item, distinguishing the repulsion and attraction of individuals to different distance information. i (φi , t)<d, the individual's relative position φ i The information generated by the exclusion decision corresponds to Figure 4 The dark gray area in i (φ i , t)>d, the individual's relative position φ i The information generated by attracting decisions corresponds to Figure 4 The light grey area in Figure 7 As shown, by setting D i (φ i , t) -λ The λ in the term balances the repulsive and attractive forces. Figure 7 When d=2, the position force corresponding to different relative distances under different parameters λ, where dark gray and light gray correspond to repulsive force and attractive force, respectively.
[0090] In addition, in order to consider the change in speed and direction of the current individual, all orientation information is used in and Projection in the direction cosφ i and sinφ i As the position force F pos By modeling this positional force, individuals observe single neighbors at different locations and distances, producing Figure 8-Figure 10 The speed direction and speed magnitude shown are determined by Figure 8-Figure 10 It indicates the influence of the repulsive force and attractive force on the velocity direction and velocity magnitude of a single neighbor individual. Figure 8 (a) is the effect of repulsive force on the direction of velocity, Figure 8 (b) shows the effect of repulsive force on speed. Under the action of repulsive force, facing the neighbor on the left or right, the current individual turns right or left; facing the neighbor in front or behind, the current individual slows down or speeds up. On the contrary, under the action of attractive force, the current individual gets the opposite decision result.
[0091] Preferably, the distance distinction threshold d=2 for repulsion and attraction is set. When the distance between individuals (visual perception function) is less than d, due to the repulsive force, the current individual i makes a right turn or a left turn decision for the neighbor on the left or right side, and makes a deceleration or acceleration decision for the neighbor in front or behind. On the contrary, when the distance between individuals is greater than d, due to the attraction, the current individual i makes the opposite decision. When the current individual makes a decision, the information observed by other individuals will be based on D. i (φ i , t) and d produce repulsive or attractive forces; while the visual perception function only contains D i (φ i, t)<d, so it will only produce repulsive force.
[0092] In one embodiment, step 108 includes: determining the speed decision equation of the current individual according to the self-propulsion force and the position force as follows:
[0093]
[0094] in, is the speed change of the current individual, F ind (v i ) is the self-propulsion force of the current individual i, F pos [D i (φ i , t)] is the position force of the current individual i, D i (φ i , t) is the visual perception function obtained by the current individual i at the current time t, φ i is the relative position of the current individual i, v i (t) is the velocity of individual i at the current time t.
[0095] In one of the embodiments, the step: determining the speed information of the current individual at the current moment according to the speed decision equation of the current individual, includes: projecting the speed decision equation of the current individual in the direction parallel to the speed and in the direction perpendicular to the speed to obtain the speed magnitude decision equation and the speed direction decision equation of the current individual.
[0096] The speed decision equation of the current individual is:
[0097]
[0098] The current individual direction decision equation is:
[0099]
[0100] in, is the unit vector parallel to the velocity of the current individual i at the current time t, The unit vector perpendicular to the velocity of the current individual i at the current time t, v o is the expected velocity, v i (t) is the speed of the current individual i at the current time t, α and β are the speed v of the current individual respectively. i and the velocity direction ψ i The change control constant of i is the relative position of the current individual i; D i (φ i , t) is the visual perception function obtained by the current individual i at the current time t, v i(t) is the velocity of the current individual i at the current time t, d is the threshold for distinguishing between repulsion and attraction, λ is the balance parameter between attraction and repulsion, ψ i (t) is the velocity direction of the current individual i at the current time t.
[0101] Specifically, in the field of mechanics, the instantaneous velocity change of an object is determined by the tangential force, while the instantaneous direction change of an object is determined by the normal force. Therefore, the force on the individual is projected in the direction parallel to and perpendicular to the velocity to obtain the velocity magnitude and velocity direction decision equations of the current individual.
[0102] In one embodiment, step 110 includes: updating the motion state of the current individual according to the speed information at the current moment to obtain the position information of the current individual at the next moment; determining the position change of the current individual according to the speed magnitude change value and the speed direction change value of the current individual to obtain the position driving equation of the current individual; the position driving equation of the current individual is:
[0103]
[0104]
[0105] in, The current position change of individual i.
[0106] Specifically, during the decision-making process, the current individual makes a decision on the speed magnitude and speed direction according to the visual perception function. Finally, during the driving process, the current individual moves at this speed.
[0107] In the specific simulation process, the position driving equation, velocity magnitude decision equation and velocity direction decision equation of the current individual are discretized to obtain a discrete expression of the relationship between the individual velocity and position. According to the discrete expression of the relationship between the individual velocity information and the position information, the motion state of the current individual is updated to obtain the position information and velocity information of the current individual at the next moment.
[0108] The discrete expression of the relationship between individual velocity and position is:
[0109]
[0110] Where Δt is the discretized time interval.
[0111] Specifically, in the unmanned swarm designed and constructed through the model equation, individuals observe external information through vision, and are disturbed by external stimuli due to repulsive forces. Individuals will be guided to self-organize and adapt to the external environment through the action of paired repulsive or attractive forces, thereby reaching a new equilibrium state.
[0112] This method fits the actual perception mode of organisms, models the visual perception mode of individual organisms, and uses visual information as input to construct a model to realize the adaptive behavior of the group to external stimuli.
[0113] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.
[0114] In one embodiment, Fig.11 As shown, a group adaptive behavior control device based on visual perception is provided, comprising: a visual perception module, a visual image information processing module, a decision module and a driving module, wherein:
[0115] The visual perception module is used to obtain the visual image information of other individuals and external stimuli within the field of view of the current individual in the group; the visual image information is the line of sight at each relative orientation in the individual reference coordinate system; the individual reference coordinate system is constructed with the speed of the current individual as the 0 degree direction of the individual relative orientation and the counterclockwise direction as the positive direction of the relative orientation.
[0116] A visual image information processing module, used to determine the visual perception function of the current individual according to the visual image information;
[0117] The decision module is used to determine the self-propulsion force of the current individual according to the current individual speed and the expected speed; determine the position force of the current individual according to the visual perception function; determine the speed decision equation of the current individual according to the self-propulsion force and the position force; and determine the speed information of the current individual at the current moment according to the speed decision equation of the current individual.
[0118] The driving module is used to update the motion state of the current individual according to the speed information to obtain the position information of the current individual at the next moment.
[0119] In one of the embodiments, the visual image information is obtained by the current individual based on the counterclockwise direction as the positive direction, using a visual perception method with the current individual's own position as the center and the current individual's speed as the 0-degree direction of the individual's relative direction to obtain the viewing distance information of each relative direction within a 360-degree range, and the current individual distinguishes the viewing distance information of each relative direction of other individuals and external stimuli; the visual image information processing module is also used to delete the viewing distance information at infinity and the viewing distance information of external stimuli greater than the repulsion and attraction distinction threshold, to obtain the visual perception function of the current individual.
[0120] In one embodiment, the decision module is further used to determine the self-propulsion force of the current individual according to the speed of the current individual and the expected speed. The expression of the self-propulsion force of the current individual is shown in formula (2).
[0121] In one embodiment, the position force of the current individual includes the position force generated by the current individual due to the visual distance information of other individuals and external stimuli within the field of view; the position force is divided into repulsive force and attractive force; the decision module is also used to determine the position force of the current individual according to the visual perception function, and the expression of the position force of the current individual is shown in formula (3).
[0122] When the threshold for distinguishing repulsion and attraction is greater than the relative position φ of the current individual i at the current time t i When the visual distance information of the visual perception function is at the relative position φ, the position force generated by the visual distance information of the relative position on the current individual i is a repulsive force; because the visual distance information of the external stimulus greater than the repulsive force and attractive force distinction threshold is deleted during the visual perception function acquisition process, the position force generated by the visual distance information of the external stimulus on the current individual is only a repulsive force; when the repulsive force and attractive force distinction threshold is less than the relative position φ of the current individual i at the current time t i When the viewing distance information of the visual perception function is , the position force generated by the viewing distance information of the relative position on the current individual i is attractive.
[0123] In one embodiment, the decision module is further used to determine the speed decision equation of the current individual according to the self-propulsion force and the position force. The speed decision equation of the current individual is shown in formula (4).
[0124] In one of the embodiments, the decision module is further used to project the speed decision equation of the current individual in a direction parallel to the speed and in a direction perpendicular to the speed to obtain the speed magnitude decision equation and direction decision equation of the current individual.
[0125] The speed decision equation of the current individual is shown in formula (5).
[0126] The current individual direction decision equation is shown in formula (6).
[0127] In one embodiment, the decision module is also used to determine the position change of the current individual according to the speed magnitude change value and the speed direction change value of the current individual, and obtain the position driving equation of the current individual; the position driving equation of the current individual is shown in formula (7).
[0128] For the specific definition of the group adaptive behavior control device based on visual perception, please refer to the definition of the group adaptive behavior control method based on visual perception above, which will not be repeated here. Each module in the above-mentioned group adaptive behavior control device based on visual perception can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0129] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.12 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a group adaptive behavior control method based on visual perception is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.
[0130] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0131] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in the above method embodiment when executing the computer program.
[0132] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0133] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A group adaptive behavior control method based on visual perception, characterized in that: The method comprises: Obtain visual image information of other individuals and external stimuli within the visual range of the current individual in the group; the visual image information is the visual distance at each relative orientation in the individual reference coordinate system; the individual reference coordinate system is constructed with the speed of the current individual as the 0 degree direction of the individual relative orientation and the counterclockwise direction as the positive direction of the relative orientation; Determining a visual perception function of a current individual according to the visual image information; Determine the self-propulsion force of the current individual according to the current individual speed and the expected speed; Determining the position force of the current individual according to the visual perception function; Determine a speed decision equation of the current individual according to the self-propulsion force and the position force; According to the speed decision equation of the current individual, determine the speed information of the current individual at the current moment; According to the speed information at the current moment, the motion state of the current individual is updated to obtain the position information of the current individual at the next moment.
2. The method according to claim 1, characterized in that The visual image information is obtained by the current individual according to the counterclockwise direction as the positive direction, using the visual perception method with the current individual's own position as the center and the current individual's speed as the 0 degree direction of the individual's relative direction to obtain the visual distance information of each relative direction within a 360-degree range, and the current individual distinguishes the visual distance information of each relative direction of other individuals and external stimuli; Determining the visual perception function of the current individual according to the visual image information includes: The visual distance information at infinity and the visual distance information of external stimuli greater than the threshold for distinguishing repulsion and attraction are deleted to obtain the visual perception function of the current individual.
3. The method according to claim 1, characterized in that According to the current individual speed and the expected speed, the self-propulsion force of the current individual is determined, including: According to the current individual speed and expected speed, the self-propulsion force of the current individual is determined as: Among them, F ind is the self-propulsion force, γ is the self-propulsion constant, v o is the expected velocity, v i (t) is the velocity of individual i at the current time t.
4. The method according to claim 1, characterized in that: The position force of the current individual includes the position force generated by the current individual due to the visual distance information of other individuals and external stimuli within the visual field; The position force is divided into repulsive force and attractive force; According to the visual perception function, determining the position force of the current individual includes: According to the visual perception function, the position force of the current individual is determined as: Among them, F pos [D i (φ i ,t)] is the position force of the current individual i, D i (φ i ,t) is the visual perception function obtained by the current individual i at the current time t, d is the threshold for distinguishing repulsion and attraction, λ is the balance parameter of attraction and repulsion, α and β are used to control the speed v of the current individual respectively i and the velocity direction ψ i Change, φ i is the relative position of the current individual i, by setting cosφ i and sinφ i As a factor of the position force, we consider the position force on the velocity v i and the velocity direction ψ i the impact of change; When the repulsive force and attractive force distinction threshold is greater than the relative position φ of the current individual i at the current time t i When the visual distance information of the visual perception function is in the position, the position force generated by the visual distance information of the relative position on the current individual i is a repulsive force; because the visual distance information of the external stimulus greater than the repulsive force and attractive force distinction threshold is deleted during the process of obtaining the visual perception function, the position force generated by the visual distance information of the external stimulus on the current individual is only a repulsive force; When the repulsive force and attractive force distinction threshold is less than the relative position φ of the current individual i at the current time t i When the viewing distance information of the visual perception function is , the position force generated by the viewing distance information of the relative position on the current individual i is attractive.
5. The method according to claim 1, characterized in that According to the self-propulsion force and the position force, a speed decision equation of the current individual is determined, including: According to the self-propulsion force and the position force, the speed decision equation of the current individual is determined as: in, is the speed change of the current individual, F ind (v i ) is the self-propulsion force of the current individual i, F pos [D i (φ i ,t)] is the position force of the current individual i, D i (φ i ,t) is the visual perception function obtained by the current individual i at the current time t, φ i is the relative position of the current individual i, v i (t) is the velocity of individual i at the current time t.
6. The method according to claim 5, characterized in that According to the speed decision equation of the current individual, the speed information of the current individual at the current moment is determined, including: Project the speed decision equation of the current individual in the direction parallel to the speed and in the direction perpendicular to the speed to obtain the speed magnitude decision equation and direction decision equation of the current individual; The speed decision equation of the current individual is: The direction decision equation of the current individual is: in, is the unit vector parallel to the velocity of the current individual i at the current time t, The unit vector perpendicular to the velocity of the current individual i at the current time t, v o is the expected velocity, v i (t) is the speed of the current individual i at the current time t, α and β are the speed v of the current individual respectively. i and the velocity direction ψ i The change control constant of i is the relative position of the current individual i; D i (φ i ,t) is the visual perception function obtained by the current individual i at the current time t, v i (t) is the velocity of the current individual i at the current time t, d is the threshold for distinguishing between repulsion and attraction, λ is the balance parameter between attraction and repulsion, ψ i (t) is the velocity direction of the current individual i at the current time t.
7. The method according to claim 6, characterized in that According to the speed information at the current moment, the motion state of the current individual is updated to obtain the position information of the current individual at the next moment, including: According to the speed magnitude change value and speed direction change value of the current individual, the position change of the current individual is determined to obtain the position driving equation of the current individual; the position driving equation of the current individual is: in, The current position change of individual i.
8. A group adaptive behavior control device based on visual perception, characterized in that: The device comprises: A visual perception module is used to obtain visual image information of other individuals and external stimuli within the visual range of the current individual in the group; the visual image information is the visual distance at each relative orientation in the individual reference coordinate system; the individual reference coordinate system is constructed with the speed of the current individual as the 0 degree direction of the individual relative orientation and the counterclockwise direction as the positive direction of the relative orientation; A visual image information processing module, used to determine the visual perception function of the current individual according to the visual image information; A decision module is used to determine the self-propulsion force of the current individual according to the speed of the current individual and the expected speed; determine the position force of the current individual according to the visual perception function; determine the speed decision equation of the current individual according to the self-propulsion force and the position force; determine the speed information of the current individual at the current moment according to the speed decision equation of the current individual; The driving module is used to update the motion state of the current individual according to the speed information to obtain the position information of the current individual at the next moment.
9. The device according to claim 8, characterized in that The visual image information is obtained by the current individual based on the counterclockwise direction as the positive direction, using a visual perception method with the current individual's own position as the center and the current individual's speed as the 0-degree direction of the individual's relative direction to obtain the viewing distance information of each relative direction within a 360-degree range, and the current individual distinguishes the viewing distance information of each relative direction of other individuals and external stimuli; the visual image information processing module is also used to delete the viewing distance information at infinity and the viewing distance information of external stimuli greater than the repulsion and attraction distinction threshold, so as to obtain the visual perception function of the current individual.
10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
