Method for cooperative control and evolution of heterogeneous mobile agents

Description

A cooperative control and evolution method for heterogeneous mobile intelligent agents Technical Field

[0001] This invention relates to a method for cooperative control and evolution of heterogeneous mobile intelligent agents, belonging to the field of mobile intelligent agent formation and cooperative control technology. Background Technology

[0002] The core idea of ​​mobile agent systems is to integrate the operational characteristics of both artificial and autonomous mobile agents when achieving desired formation movement, aiming to accomplish integrated collaborative control and formation management tasks. Due to its wide application in traffic flow control, aerial vehicle formation, and space exploration, it has received considerable attention. However, most previous studies have not adequately considered the impact of individual agent emotions and uncertainties in the external environment on the operation of multi-agent collaborative control systems. In practical applications, individual emotions and uncertain environments can not only cause agents to deviate from their desired movement paths but also adversely affect the collaborative formation operation of multiple agents. Therefore, research on multi-agent collaborative control in uncertain environments has extremely important theoretical and practical value.

[0003] The information disclosed in this background section is intended only to enhance the understanding of the overall background of this utility model and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0004] The technical problem to be solved by this invention is that the existing technology does not fully consider the influence of individual emotional factors of artificial mobile intelligent agents and uncertain factors in the local environment on the collaborative control of multiple agents, resulting in the collaborative control and evolution of heterogeneous mobile intelligent agent systems failing to approximate the real situation.

[0005] To solve the above-mentioned technical problems, the present invention is implemented using the following technical solution.

[0006] This invention provides a method for cooperative control and evolution of heterogeneous mobile intelligent agents, comprising:

[0007] The artificial mobile agent cells and the automatic mobile agent cells are mixed in a preset ratio using a continuous cellular automaton, and artificial mobile agents and automatic mobile agents are generated through an iterative process.

[0008] An emotion recognition module is embedded in the artificial mobile intelligent agent to obtain emotion cues of different granularities based on fuzzy theory.

[0009] Based on the emotional cues of different granularities, the evolution rules of the artificial mobile agent are constructed, and the state of the artificial mobile agent is updated.

[0010] The evolution rules of the artificial mobile agent include acceleration rules, deceleration rules, random slowing rules that introduce a random slowing probability function, and position update rules;

[0011] The position, velocity, and acceleration of the autonomous mobile agent are obtained. Based on the improved interaction potential energy field function, the evolution rules of the autonomous mobile agent are constructed, and the state of the autonomous mobile agent is updated.

[0012] The evolution rules for the autonomous mobile intelligent agent include acceleration rules, deceleration rules, and position update rules;

[0013] The acceleration rules are used to adjust the speed of automated or artificial mobile agents.

[0014] The deceleration rule is used to avoid collisions between automated mobile agents and artificial mobile agents;

[0015] The random slowing rule, which introduces a random slowing probability function, is used to randomly slow down an artificial mobile agent based on an emotion influence factor and a random slowing probability function.

[0016] The location update rule is used to determine the location of an automated or manually operated mobile agent.

[0017] The movement and path of the automated mobile agent are controlled by the field force planning method. The movement path of the artificial mobile agent is planned by combining the movement and path of the automated mobile agent with emotional cues of different granularities in the operation scenario of the artificial mobile agent, and utilizing the perception information sharing mechanism of the automated mobile agent.

[0018] Based on the aforementioned heterogeneous mobile intelligent agent cooperative control and evolution method, the emotion cognition module includes an emotion perception layer and a feature fusion network. The emotion perception layer adopts a dual-channel fusion attention mechanism network structure. According to fuzzy theory, methods for obtaining emotional cues at different granularities include:

[0019] The emotion perception layer is used to capture and extract character emotion cues and scene emotion cues in the running scene through the character channel and scene channel respectively, forming a preliminary feature vector;

[0020] Fuzzy theory is used to quantify the emotion values ​​of continuous dimensions in the initial feature vector to obtain the emotion influencing factor.

[0021] The emotion-influencing factors are input into the feature fusion network for fusion processing to obtain emotion cues at different granularities.

[0022] Based on the aforementioned heterogeneous mobile intelligent agent cooperative control and evolution method, a method for quantifying the emotion values ​​of continuous dimensions in the initial feature vector using fuzzy theory to obtain emotion influencing factors includes:

[0023] Based on the Mamdani model, a three-valued input and single-valued output fuzzy inference model of emotion is constructed, with emotional pleasure, emotional arousal and emotional dominance as input variables and emotional influence factors as output variables.

[0024] Based on the emotional metrics of emotional pleasure, emotional arousal, and emotional dominance, fuzzy sets of input variables are constructed respectively, including fuzzy set 1, fuzzy set 2, and fuzzy set 3 for emotional pleasure, fuzzy set 1, fuzzy set 2, and fuzzy set 3 for emotional arousal, and fuzzy set 1, fuzzy set 2, and fuzzy set 3 for emotional dominance;

[0025] Construct fuzzy sets of output variables, including fuzzy set 1 of emotion factors, fuzzy set 2 of emotion factors, and fuzzy set 3 of emotion factors;

[0026] The fuzzy sets of input and output variables are fuzzified using Gaussian membership functions.

[0027] By analyzing data samples of emotional pleasure, emotional arousal, and emotional dominance in the Emotic dataset, a base of artificial empirical rules that can reflect the relationship between input and output variables is obtained.

[0028] Based on a human-based rule library, a fuzzy rule matrix for emotion representation is constructed.

[0029] The continuous sentiment values ​​in the initial feature vector are converted into the membership degree of the fuzzy set of the input set through fuzzification.

[0030] Based on the emotion representation fuzzy rule matrix, a fuzzy inference engine is used to map the input fuzzy set to the output fuzzy set, and calculations are performed to obtain the final output fuzzy set.

[0031] The centroid method is used to defuzzify the final output fuzzy set to obtain the emotion influence factor.

[0032] Based on the aforementioned heterogeneous mobile agent cooperative control and evolution method, and according to the artificial experience rule base, a fuzzy rule matrix for emotion representation is constructed. The constructed fuzzy rule matrix for emotion representation is represented as follows:

[0033] In the emotion representation fuzzy rule matrix, the first three columns represent the fuzzy set indices corresponding to the input variables of emotional pleasure, emotional arousal, and emotional dominance, respectively; the fourth column represents the fuzzy set index corresponding to the output variable of emotional influence factor; the fifth column represents the rule weights of the emotion representation fuzzy rule matrix; and the sixth column represents the connectives of the rules in the emotion representation fuzzy rule matrix. When the rule weight is 1, the logical connective is "AND"; when the rule weight is 2, the logical connective is "OR".

[0034] Among them, the rule in the first row of the emotion representation fuzzy rule matrix is: when the input emotion pleasure degree belongs to the fuzzy set of emotion pleasure degree one, the input emotion arousal degree belongs to the fuzzy set of emotion arousal degree three, and the input emotion dominance degree belongs to the fuzzy set of emotion dominance degree three, the output emotion factor fuzzy set one is output. The rule weight in the first row is 1, and the logical connector is "AND".

[0035] The rule in the second row of the fuzzy rule matrix is: when the input emotional pleasure degree belongs to the second fuzzy set of emotional pleasure degree, the input emotional arousal degree belongs to the first fuzzy set of emotional arousal degree, and the input emotional dominance degree belongs to the third fuzzy set of emotional dominance degree, the output emotional factor fuzzy set 2 is given. The rule weight in the second row is 1, and the logical connector is "AND".

[0036] The rule in the third row of the fuzzy rule matrix is: when the input emotional pleasure degree belongs to the first fuzzy set of emotional pleasure degree, the input emotional arousal degree belongs to the second fuzzy set of emotional arousal degree, and the input emotional dominance degree belongs to the first fuzzy set of emotional dominance degree, the output emotional factor fuzzy set three is given. The rule weight in the third row is 1, and the logical connector is "AND".

[0037] Based on the aforementioned heterogeneous mobile intelligent agent cooperative control and evolution method, when the operating scenario is road traffic flow, the continuous cellular automaton uses vehicles as cells and generates manually driven vehicles and autonomous connected vehicles through an iterative process. The state information σ of the continuous cellular automaton... i (t), represented as:

[0038] Where, x n (t), ν n (t) and a n (t) represent the position, velocity, and acceleration of vehicle n at the current time t, respectively. n Let AFF represent the ideal state vector of vehicle n. n This represents the driver's emotional state vector for vehicle n. Let AFF represent the expected speed of vehicle n, the expected following distance of vehicle n, and the safe time interval of vehicle n, respectively. n _V(t), AFF n _A(t) and AFF n_D(t) represent the measures of the driver's emotional pleasure, emotional arousal, and emotional dominance at the current time t.

[0039] The continuous cellular automaton uses vehicles as cells and generates manually driven vehicles and autonomous connected vehicles through an iterative process. The manually driven vehicle a... n (t) is represented as:

[0040] Where A0 represents the maximum acceleration of the vehicle, λ represents the vehicle acceleration exponent, and s n (t) and Δν(t) represent the relative distance and relative speed between the preceding vehicle n+1 and the current vehicle n, respectively; B represents the absolute value of the vehicle's comfortable deceleration; S0 represents the stationary safety distance; v n+1 (t) represents the speed of the preceding vehicle n+1 at the current time t.

[0041] Based on the aforementioned heterogeneous mobile agent cooperative control and evolution method, the centroid method is used to defuzzify the final output fuzzy set to obtain the emotion influence factor. The obtained emotion influence factor k is expressed as: k = f(AFF) n _V(t),AFF n _A(t),AFF n _D(t)) (4);

[0042] Among them, AFF n _V(t), AFF n _A(t) and AFF n _D(t) represent the measures of the driver's emotional pleasure, emotional arousal, and emotional dominance at the current time t.

[0043] Based on the aforementioned heterogeneous mobile agent cooperative control and evolution method, the evolution rules of the artificial mobile agent include acceleration rules, deceleration rules, random slowing rules with a random slowing probability function, and position update rules; wherein, the acceleration rule of the artificial mobile agent is expressed as: v n (t+1)=min(v n (t)+a n (t),v max (5);

[0044] Among them, v n (t+1) represents the speed of vehicle n at the current time t, ν n (t) represents the speed of vehicle n at the current time t, a n (t) represents the acceleration of vehicle n at the current time t, v max This indicates the maximum speed limit for the road.

[0045] The deceleration rule for the artificial mobile agent is expressed as: d safe =s n (t)-s0 (6);

[0046] Where, d safe Indicates the safe following distance, s n (t) represents the relative distance between the preceding vehicle n+1 and the current vehicle n, and s0 represents the stationary safe distance.

[0047] Based on the emotional influence factors of driver n in this vehicle and the random slowing probability function, driver n in this vehicle has p n The system randomly decelerates with a probability of (t+1), where p n (t+1) represents the random slowing probability of vehicle n. The random slowing rule introduced by the random slowing probability function is expressed as: v n (t+1)=max(v n (t)-c,0) (7);

[0048] Among them, v n (t+1) represents the speed of vehicle n at the current time t, ν n (t) represents the velocity of vehicle n at the current time t, and c represents the deceleration value;

[0049] The position x of car n at current time t n (t) and velocity v n (t) together determine the position x of this car at the next time t+1. n (t+1);

[0050] The expression for the location update rule of the artificial mobile agent is: x n (t+1)=x n (t)+v n (t+1) (8);

[0051] Where, x n (t+1) represents the position of the vehicle at the next time step (t+1), x n (t) represents the position of vehicle n at the current time t, v n (t) represents the speed of car n at the current time t.

[0052] Based on the aforementioned heterogeneous mobile intelligent agent cooperative control and evolution method, the evolution rules of the autonomous mobile intelligent agent include acceleration rules, deceleration rules, and position update rules;

[0053] The acceleration rule for the autonomous mobile agent is expressed as follows:

[0054] Among them, v n(t+1) represents the speed of vehicle n at the current time t, ν n (t) represents the velocity of vehicle n at the current time t, v max The maximum speed limit on the road is represented by 'a', the acceleration of vehicle n calculated using the double integral equation of motion is represented by 'm', and the mass of vehicle n is represented by 'd'. safe F represents the safe following distance, and F represents the total virtual force.

[0055] The deceleration rule for the automatic mobile intelligent agent is: when the repulsive force generated by the virtual potential field of the current vehicle n+1 is greater than the attractive force, the total virtual force on the current vehicle n is manifested as a repulsive force;

[0056] The location update rules for automated mobile agents are consistent with those for human-made mobile agents.

[0057] Based on the aforementioned heterogeneous mobile intelligent agent cooperative control and evolution method, a method for controlling the motion and motion path of an autonomous mobile intelligent agent through field force planning includes:

[0058] The position, velocity, and acceleration of the autonomous mobile agent are acquired in real time through its sensors, and the interaction potential energy field function is defined.

[0059] The interaction potential energy field function is improved by introducing virtual forces of position, velocity, and acceleration.

[0060] Based on the improved interaction potential energy field function, the virtual forces from other agents acting on each autonomously moving agent are calculated, including position virtual force, velocity virtual force and acceleration virtual force.

[0061] The total virtual force of each autonomous mobile agent is obtained by vector synthesis of all virtual forces acting on it.

[0062] Using total virtual force as a control signal, the driving speed and direction of the autonomous mobile intelligent agent are adjusted through a control algorithm.

[0063] The virtual force of the potential energy field is used to plan the driving path of an autonomous mobile intelligent agent.

[0064] Based on the aforementioned heterogeneous mobile intelligent agent cooperative control and evolution method, the position virtual force includes position virtual attraction and position virtual repulsion, the velocity virtual force includes velocity virtual attraction and velocity virtual repulsion, and the acceleration virtual force includes acceleration virtual attraction and acceleration virtual repulsion.

[0065] The virtual repulsion force F at the location rep-d Represented as:

[0066] Where, k rep-dThe virtual repulsive potential energy coefficient represents the location, r represents the distance from the automatically connected vehicle to the target point, and r0 represents the range of influence of the repulsive potential field. This represents the distance vector from the automatically connected vehicle to the target point. This represents the magnitude of the distance vector from the automatically connected vehicle to the target point.

[0067] The virtual gravity F at the location att-d Represented as: F att-d =k att-d r g (11);

[0068] Where, k att-d The virtual gravitational potential energy coefficient at position, r g This indicates the distance from the automatically connected vehicle to the target point.

[0069] The virtual repulsion force F of velocity rep-v Represented as:

[0070] Where, k rep-v The velocity virtual repulsive potential energy coefficient is represented by r, where r represents the distance from the automatically connected vehicle to the target point, and r0 represents the range of influence of the repulsive potential field. This represents the speed difference vector between the vehicle in front and the vehicle in front. This represents the magnitude of the velocity difference vector between the vehicle in front and the vehicle itself.

[0071] The virtual gravity F of the velocity att-v Represented as: F att-v =tanh(k att-v ||Δv e ||)r g (13);

[0072] Where, k att-v The velocity virtual gravitational potential energy coefficient, Δv e r represents the speed difference between the desired speed and the current speed. g Let tanh represent the distance from the automatically connected vehicle to the target point, and tanh represent the hyperbolic tangent function. ||Δv e || represents the magnitude of the velocity difference vector between the desired velocity and the current velocity.

[0073] The virtual repulsive force F of acceleration rep-a Represented as:

[0074] Where, k rep-a The variable represents the virtual repulsive potential energy coefficient of acceleration, r represents the distance from the automatically connected vehicle to the target point, and r0 represents the range of influence of the repulsive potential field. This represents the vector of acceleration differences between the vehicle in front and the vehicle in front. This represents the magnitude of the acceleration difference vector between the vehicle in front and the vehicle itself.

[0075] The acceleration virtual gravity F att-a Represented as: F att-a =tanh(k att-a ||Δa e ||)r g (15);

[0076] Where, k att-a Δa represents the virtual gravitational potential energy coefficient of acceleration. e r represents the difference between the desired acceleration and the current acceleration. g ||Δa represents the distance from the automatically connected vehicle to the target point. e || represents the magnitude of the vector difference between the desired acceleration and the current acceleration.

[0077] This invention improves the realism and accuracy of collaborative control of heterogeneous mobile intelligent agents by introducing an emotion-influencing factor, accurately quantifying continuous-dimensional emotion values ​​and integrating them into a random slowing probability function, making the behavior of artificial mobile intelligent agents more realistic.

[0078] Meanwhile, the method based on potential energy field virtual force transforms the position, velocity, and acceleration information of the autonomous mobile intelligent agent into virtual field force, and effectively controls its motion through field force planning, thereby enhancing the autonomous decision-making and path planning capabilities of the autonomous mobile intelligent agent.

[0079] This invention addresses the challenge of collaborative control in complex environments by significantly improving the adaptability and overall intelligence of collaborative control of heterogeneous mobile intelligent agents through emotion recognition, deceleration rules, and potential energy field optimization.

[0080] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0081] This invention embeds an emotion recognition module into an artificial mobile agent, utilizing fuzzy theory to process emotional cues of different granularities. This enables the agent to perceive and understand emotional information in complex environments. The evolutionary rules constructed based on emotional cues of different granularities make the behavior of the artificial mobile agent more flexible and varied. In particular, the introduction of a randomized slowing probability function and an emotion influence factor allows for dynamic adjustment of movement speed according to emotional state. This not only increases the diversity of the agent's behavior but also enhances its survivability and adaptability in complex environments.

[0082] This invention effectively achieves dynamic collision avoidance and cooperative movement among agents by modeling virtual repulsive and gravitational fields and constructing evolutionary rules for autonomous mobile agents based on an improved interaction potential energy field function. Furthermore, this invention utilizes field force planning methods to control the movement and path of autonomous mobile agents, and combines a sensory information sharing mechanism and emotional cues to plan more rational and efficient movement paths for artificial mobile agents. This solves the problem in existing technologies where the influence of individual emotional factors of artificial mobile agents and uncertainties in the local environment on the cooperative control of multiple agents is not fully considered, resulting in the cooperative control and evolution of heterogeneous mobile agent systems failing to approximate real-world conditions. Attached Figure Description

[0083] Figure 1 is a structural schematic diagram of the heterogeneous mobile intelligent agent provided in an embodiment of the present invention;

[0084] Figure 2 is a schematic diagram of the construction process of the emotion fuzzy reasoning model provided in an embodiment of the present invention;

[0085] Figure 3 is a simulation diagram of the virtual force model of the potential energy field in the operation scenario of the heterogeneous mobile intelligent agent cooperative control provided in the embodiment of the present invention. Detailed Implementation

[0086] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0087] Example 1

[0088] As shown in Figure 1, this embodiment introduces a method for cooperative control and evolution of heterogeneous mobile intelligent agents, including:

[0089] Step 1: Use a continuous cellular automaton to mix artificial and automatic mobile agent cells according to a preset ratio, and generate artificial and automatic mobile agents through an iterative process;

[0090] By using a continuous cellular automata model, artificial and automated mobile agents are mixed in a preset ratio to simulate heterogeneous mobile agents in a real interactive environment. This provides a basic simulation environment for subsequent collaborative control research, making the experimental results closer to actual application scenarios and enhancing the practicality and reliability of the research.

[0091] Step 2: Embed an emotion recognition module into the artificial mobile intelligent agent to obtain emotion cues of different granularities based on fuzzy theory;

[0092] By embedding an emotion cognition module, we can acquire and quantify the emotional cues of artificial mobile agents using fuzzy theory. Emotional cues can affect the movement of artificial mobile agents. Considering emotional cues of different granularities can make the behavioral decisions of artificial mobile agents more in line with the actual situation of humans, improve the realism and accuracy of the simulation model, and introduce a new dimension—emotional factors—for the collaborative control of heterogeneous agents.

[0093] Step 3: Based on the emotional cues of different granularities, construct the evolution rules of the artificial mobile agent and update the state of the artificial mobile agent;

[0094] The evolution rules of the artificial mobile agent include acceleration rules, deceleration rules, random slowing rules that introduce a random slowing probability function, and position update rules;

[0095] Step 4: Construct evolutionary rules for the artificial mobile agent based on emotional cues, including acceleration rules, deceleration rules, random slowing rules, and position update rules, in order to update the state of the artificial mobile agent.

[0096] The aforementioned rules enable the behavior of artificial mobile agents to dynamically adjust according to emotional changes, increasing the complexity and realism of the simulation environment. At the same time, the stochastic slowing rule introduces uncertainty, making behavior more unpredictable.

[0097] Step 5: Obtain the position, velocity, and acceleration of the autonomous mobile agent; construct the evolution rules of the autonomous mobile agent based on the improved interaction potential energy field function; and update the state of the autonomous mobile agent.

[0098] Based on the improved interaction potential energy field function, acceleration rules, deceleration rules, and position update rules of the autonomous mobile agent are constructed to optimize the motion path and obstacle avoidance ability of the autonomous mobile agent, thereby improving the adaptability and safety of the autonomous mobile agent in complex environments and enabling the autonomous mobile agent to cope with various situations more intelligently, such as avoiding pedestrians and adjusting speed.

[0099] The evolution rules for the autonomous mobile intelligent agent include acceleration rules, deceleration rules, and position update rules;

[0100] The acceleration rules are used to adjust the speed of automated or artificial mobile agents.

[0101] The deceleration rule is used to avoid collisions between automated mobile agents and artificial mobile agents.

[0102] Acceleration rules are used to adjust the speed of the agent to match its motion requirements, while deceleration rules are used to avoid collisions and ensure safety. Together, they maintain the stability and safety of the simulation environment, reduce the occurrence of collision events, and improve the efficiency of the agent's movement.

[0103] The introduced random slowing-down rule, based on an emotion-influenced factor and the random slowing-down probability function, is used to randomly decelerate the artificial mobile agent. By using the emotion-influenced factor and the random slowing-down probability function to randomly decelerate the artificial mobile agent, the realism and unpredictability of the simulation environment are increased, simulating the random behavioral patterns of humans or organisms under the influence of emotions.

[0104] The position update rule is used to determine the position of either an automatically moving agent or a manually moving agent. Updating the agent's position based on speed and direction propels it to move within the simulation environment, enabling continuous movement and interaction of the agent in virtual space and providing a foundation for subsequent path planning and decision-making.

[0105] Step 6: Control the movement and path of the automated mobile agent through the field force planning method, and use the perception information sharing mechanism of the automated mobile agent, combined with the movement and path of the automated mobile agent and the emotional cues of different granularities in the operation scenario of the artificial mobile agent, to plan the movement path of the artificial mobile agent.

[0106] By modeling virtual repulsive and gravitational fields to control the movement path of automated mobile agents, and utilizing a perceptual information sharing mechanism combined with emotional cues of different granularities to plan the movement path of artificial mobile agents, the path planning efficiency and obstacle avoidance capabilities of automated mobile agents are improved, while making the movement paths of artificial mobile agents more rational and safer.

[0107] Example 2

[0108] Based on the same inventive concept as Embodiment 1, this embodiment introduces a specific application example of a heterogeneous mobile intelligent agent cooperative control and evolution method.

[0109] This embodiment uses traffic flow control as an example. Road traffic flow is composed of a mix of connected and automated vehicles (CAVs) and human-driven vehicles (HDVs), sharing road resources. Compared to HDVs, CAVs have a shorter reaction time. During operation, CAVs automatically maintain a headway with the vehicle in front. Furthermore, CAVs possess environmental perception and autonomous driving capabilities, supporting more flexible and intelligent decision-making. HDVs, with an embedded emotion recognition module, generate driving strategies incorporating driver emotion factors. The combination of HDVs and CAVs can simulate near-realistic mixed traffic flow characteristics.

[0110] When the operating scenario is road traffic flow, the continuous cellular automaton uses vehicles as cells and mixes the HDV cells of manually driven vehicles and CAV cells of autonomous connected vehicles according to a preset ratio. Through an iterative process, it generates manually driven vehicles and autonomous connected vehicles.

[0111] The state information σ of the continuous cellular automaton i (t), represented as:

[0112] Where, x n (t), ν n (t) and a n (t) represent the position, velocity, and acceleration of vehicle n at the current time t, respectively. n Let AFF represent the ideal state vector of vehicle n. n This represents the driver's emotional state vector for vehicle n. Let AFF represent the expected speed of vehicle n, the expected following distance of vehicle n, and the safe time interval of vehicle n, respectively. n _V(t), AFF n _A(t) and AFF n _D(t) represent the measures of the driver's emotional pleasure, emotional arousal, and emotional dominance at the current time t.

[0113] Among them, the acceleration a of the vehicle n at the current time t is... n (t) is represented as:

[0114] Where A0 represents the maximum acceleration of the vehicle, λ represents the vehicle acceleration exponent, and s n (t) and Δν(t) represent the relative distance and relative speed between the preceding vehicle n+1 and the current vehicle n, respectively; B represents the absolute value of the vehicle's comfortable deceleration; S0 represents the stationary safety distance; v n+1 (t) represents the speed of the preceding vehicle n+1 at the current time t.

[0115] Here, "n" refers to a manually driven vehicle (HDV) or a networked automated vehicle (CAV) that is operating in mixed traffic flow.

[0116] An emotion recognition module is embedded in the HDV (High-Definition Vehicle) body of the artificially driven vehicle to obtain emotional cues of different granularities based on fuzzy theory; the specific steps include:

[0117] (1) The emotion perception layer is used to capture and extract the emotional cues of the characters and the emotional cues of the scene in the running scene through the character channel and the scene channel respectively, forming a preliminary feature vector.

[0118] (2) The emotion values ​​of continuous dimensions in the preliminary feature vector are quantified using fuzzy theory to obtain the emotion influence factor, as shown in Figure 2. The specific steps include:

[0119] Based on the Mamdani model, a three-valued input and single-valued output fuzzy inference model of emotion is constructed, with emotional pleasure, emotional arousal and emotional dominance as input variables and emotional influence factors as output variables.

[0120] Based on the emotional metrics of emotional pleasure, emotional arousal, and emotional dominance, fuzzy sets of input variables are constructed respectively, including fuzzy set 1, fuzzy set 2, and fuzzy set 3 for emotional pleasure, fuzzy set 1, fuzzy set 2, and fuzzy set 3 for emotional arousal, and fuzzy set 1, fuzzy set 2, and fuzzy set 3 for emotional dominance;

[0121] Construct fuzzy sets of output variables, including fuzzy set 1 of emotion factors, fuzzy set 2 of emotion factors, and fuzzy set 3 of emotion factors;

[0122] The fuzzy sets of input and output variables are fuzzified using Gaussian membership functions.

[0123] By analyzing data samples of emotional pleasure, emotional arousal, and emotional dominance in the Emotic dataset, a base of artificial empirical rules that can reflect the relationship between input and output variables is obtained.

[0124] Based on a human-made experience rule base, a fuzzy rule matrix for emotion representation is constructed, and the constructed fuzzy rule matrix for emotion representation is represented as follows:

[0125] In the emotion representation fuzzy rule matrix, the first three columns represent the fuzzy set indices corresponding to the input variables of emotional pleasure, emotional arousal, and emotional dominance, respectively; the fourth column represents the fuzzy set index corresponding to the output variable of emotional influence factor; the fifth column represents the rule weights of the emotion representation fuzzy rule matrix; and the sixth column represents the connectives of the rules in the emotion representation fuzzy rule matrix. When the rule weight is 1, the logical connective is "AND"; when the rule weight is 2, the logical connective is "OR".

[0126] Among them, the rule in the first row of the emotion representation fuzzy rule matrix is: when the input emotion pleasure degree belongs to the fuzzy set of emotion pleasure degree one, the input emotion arousal degree belongs to the fuzzy set of emotion arousal degree three, and the input emotion dominance degree belongs to the fuzzy set of emotion dominance degree three, the output emotion factor fuzzy set one is output. The rule weight in the first row is 1, and the logical connector is "AND".

[0127] The rule in the second row of the fuzzy rule matrix is: when the input emotional pleasure degree belongs to the second fuzzy set of emotional pleasure degree, the input emotional arousal degree belongs to the first fuzzy set of emotional arousal degree, and the input emotional dominance degree belongs to the third fuzzy set of emotional dominance degree, the output emotional factor fuzzy set 2 is given. The rule weight in the second row is 1, and the logical connector is "AND".

[0128] The rule in the third row of the fuzzy rule matrix is: when the input emotional pleasure degree belongs to the first fuzzy set of emotional pleasure degree, the input emotional arousal degree belongs to the second fuzzy set of emotional arousal degree, and the input emotional dominance degree belongs to the first fuzzy set of emotional dominance degree, the output emotional factor fuzzy set three is given. The rule weight in the third row is 1, and the logical connector is "AND".

[0129] The continuous sentiment values ​​in the initial feature vector are converted into the membership degree of the fuzzy set of the input set through fuzzification.

[0130] Based on the emotion representation fuzzy rule matrix, a fuzzy inference engine is used to map the input fuzzy set to the output fuzzy set, and calculations are performed to obtain the final output fuzzy set.

[0131] The centroid method is used to defuzzify the final output fuzzy set to obtain the emotion influence factor, which is expressed as: k = f(AFF) n _V(t),AFF n _A(t),AFF n _D(t));

[0132] Where k represents the emotion influencing factor, AFF n _V(t), AFF n _A(t) and AFF n _D(t) represent the measures of the driver's emotional pleasure, emotional arousal, and emotional dominance at the current time t.

[0133] (3) Input the emotion influencing factors into the feature fusion network and perform fusion processing to obtain emotion cues of different granularities.

[0134] Based on the emotional cues of different granularities, evolutionary rules for artificial mobile agents are constructed, and the state of artificial mobile agents is updated.

[0135] The evolution rules of the artificial mobile agent include acceleration rules, deceleration rules, random slowing rules with the introduction of a random slowing probability function, and position update rules.

[0136] The acceleration rules for the constructed artificial mobile agent are expressed as: v n (t+1)=min(v n (t)+a n (t),vmax );

[0137] Among them, v n (t+1) represents the speed of vehicle n at time t, ν n (t) represents the speed of vehicle n at time t, a n (t) represents the acceleration of vehicle n at time t, v max This indicates the maximum speed limit for the road.

[0138] The deceleration rule for the constructed artificial mobile agent is expressed as: d safe =s n (t)-s0;

[0139] Where, d safe Indicates the safe following distance, s n (t) represents the relative distance between the preceding vehicle n+1 and the current vehicle n, and s0 represents the stationary safe distance.

[0140] Considering that driver emotions can affect the operation of the HDV (High-Depth Vehicle), based on the emotional influence factor of driver n in this vehicle and the random slowing probability function, driver n in this vehicle has p n The system randomly decelerates with a probability of (t+1), where p n (t+1) represents the random slowing probability of vehicle n. The random slowing rule constructed by introducing the random slowing probability function is expressed as: v n (t+1)=max(v n (t)-c,0);

[0141] Among them, v n (t+1) represents the speed of vehicle n at time t, ν n (t) represents the velocity of vehicle n at time t, and c represents the deceleration value;

[0142] The position x of car n at current time t n (t) and velocity v n (t) together determine the position x of this car at the next time t+1. n (t+1), the expression for the position update rule of the constructed artificial mobile agent is: x n (t+1)=x n (t)+v n (t+1);

[0143] Where, x n (t+1) represents the position of the vehicle at the next time step (t+1), x n (t) represents the position of vehicle n at the current time t, v n (t) represents the speed of car n at the current time t.

[0144] The process involves acquiring the position, velocity, and acceleration of an autonomous mobile agent, constructing evolutionary rules based on an improved interaction potential energy field function, and updating the agent's state. Specific steps include:

[0145] Define a virtual potential energy field and control the movement and path of an automated mobile intelligent agent through a field force planning method. The virtual potential energy field contains virtual potential energy field forces, which are generated by the potential energy gradient in the potential energy field.

[0146] A virtual potential energy field typically consists of two parts: an attractive field generated by the target point and a repulsive field generated by the obstacle.

[0147] As shown in Figure 3, the virtual forces of the potential energy field can be classified into position virtual forces, velocity virtual forces and acceleration virtual forces according to their generation mechanism. The virtual forces of the potential energy field can be classified into position virtual attraction and position virtual repulsion, velocity virtual attraction and velocity virtual repulsion, and acceleration virtual attraction and acceleration virtual repulsion according to their interaction relationship.

[0148] The virtual location repulsion field U rep-d Represented as:

[0149] The velocity repulsion field U rep-v Represented as:

[0150] The acceleration repulsion field U rep-a Represented as:

[0151] Where r represents the distance from the automatically connected vehicle to the target point, r0 represents the range of influence of the repulsive potential field, Δv represents the speed difference between the preceding vehicle and the current vehicle, Δa represents the acceleration difference between the preceding vehicle and the current vehicle, and k rep-d k represents the virtual repulsive potential energy coefficient at position. rep-v k represents the velocity virtual repulsive potential energy coefficient. rep-a This represents the virtual repulsive potential energy coefficient of acceleration.

[0152] Since the vehicle always expects to travel at its maximum speed, if it does not reach the maximum expected speed, it will accelerate until it reaches the speed and then move at a constant speed.

[0153] Therefore, the gravitational field U at the virtual location att-d Represented as:

[0154] Therefore, the virtual velocity gravitational field U att-v Represented as:

[0155] Therefore, the gravitational field U of the virtual acceleration att-aRepresented as:

[0156] Where, r g Δv represents the distance from the automatically connected vehicle to the target point. e Δa represents the speed difference between the desired speed and the current speed. e k represents the difference between the expected acceleration and the current acceleration. att-d k represents the virtual gravitational potential energy coefficient at position. att-v k represents the velocity virtual gravitational potential energy coefficient. att-a This represents the virtual gravitational potential energy coefficient for acceleration.

[0157] Since the motion planning of an automated connected vehicle in a potential energy field is related to the virtual potential energy force, the relationship between the virtual potential energy force and the potential energy field can be expressed as:

[0158] Among them, F i Represents the potential energy field U i The virtual force generated at index i has a negative sign indicating that the direction of the virtual force in the potential energy field extends from the high potential energy to the low potential energy. This represents the gradient function.

[0159] The virtual force of position includes virtual attraction and virtual repulsion, the virtual force of velocity includes virtual attraction and virtual repulsion, and the virtual force of acceleration includes virtual attraction and virtual repulsion.

[0160] Based on the relationship between the virtual force of the potential energy field and the potential energy field, the virtual repulsive force F at the location is... rep-d Represented as:

[0161] Where, k rep-d The virtual repulsive potential energy coefficient represents the location, r represents the distance from the automatically connected vehicle to the target point, and r0 represents the range of influence of the repulsive potential field. This represents the distance vector from the automatically connected vehicle to the target point. This represents the magnitude of the distance vector from the automatically connected vehicle to the target point.

[0162] The virtual gravity F at the location att-d Represented as: F att-d =k att-d r g (11);

[0163] Where, k att-d The virtual gravitational potential energy coefficient at position, r g This indicates the distance from the automatically connected vehicle to the target point.

[0164] The virtual repulsion force F of velocityrep-v Represented as:

[0165] Where, k rep-v The velocity virtual repulsive potential energy coefficient is represented by r, where r represents the distance from the automatically connected vehicle to the target point, and r0 represents the range of influence of the repulsive potential field. This represents the speed difference vector between the vehicle in front and the vehicle in front. This represents the magnitude of the velocity difference vector between the vehicle in front and the vehicle itself.

[0166] The virtual gravity F of the velocity att-v Represented as: F att-v =tanh(k att-v ||Δv e ||)r g (13);

[0167] Where, k att-v The velocity virtual gravitational potential energy coefficient, Δv e r represents the speed difference between the desired speed and the current speed. g Let tanh represent the distance from the automatically connected vehicle to the target point, and tanh represent the hyperbolic tangent function. ||Δv e || represents the magnitude of the velocity difference vector between the desired velocity and the current velocity.

[0168] The virtual repulsive force F of acceleration rep-a Represented as:

[0169] Where, k rep-a The variable represents the virtual repulsive potential energy coefficient of acceleration, r represents the distance from the automatically connected vehicle to the target point, and r0 represents the range of influence of the repulsive potential field. This represents the vector of acceleration differences between the vehicle in front and the vehicle in front. This represents the magnitude of the acceleration difference vector between the vehicle in front and the vehicle itself.

[0170] The acceleration virtual gravity F att-a Represented as: F att-a =tanh(k att-a ||Δa e ||)r g (15);

[0171] Where, k att-a Δa represents the virtual gravitational potential energy coefficient of acceleration. e r represents the difference between the desired acceleration and the current acceleration. g ||Δa represents the distance from the automatically connected vehicle to the target point. e || represents the magnitude of the vector difference between the desired acceleration and the current acceleration.

[0172] The position, velocity, and acceleration of the autonomous mobile agent are acquired in real time through its sensors, and the interaction potential energy field function is defined.

[0173] The interaction potential energy field function is improved by introducing virtual forces of position, velocity, and acceleration.

[0174] Based on the improved interaction potential field function, an evolution rule for the autonomous mobile agent is constructed, and the state of the autonomous mobile agent is updated.

[0175] The evolution rules of the autonomous mobile intelligent agent include acceleration rules, deceleration rules, and position update rules;

[0176] The acceleration rule for the autonomous mobile agent is expressed as follows:

[0177] Among them, v n (t+1) represents the speed of vehicle n at time t, ν n (t) represents the velocity of vehicle n at time t, v max The maximum speed limit on the road is represented by 'a', the acceleration of vehicle n calculated using the double integral equation of motion is represented by 'm', and the mass of vehicle n is represented by 'd'. safe F represents the safe following distance, and F represents the total virtual force.

[0178] The deceleration rule for the automatic mobile intelligent agent is: when the repulsive force generated by the virtual potential field of the current vehicle n+1 is greater than the attractive force, the total virtual force on the current vehicle n is manifested as a repulsive force;

[0179] The location update rules for automated mobile agents are consistent with those for human-made mobile agents.

[0180] The movement and path of the automated mobile agent are controlled by the field force planning method. The movement path of the artificial mobile agent is planned by combining the movement and path of the automated mobile agent with emotional cues of different granularities in the operation scenario of the artificial mobile agent, and utilizing the perception information sharing mechanism of the automated mobile agent.

[0181] Among them, the methods for controlling the motion and movement path of an automated mobile intelligent agent through field force planning include:

[0182] Based on the improved interaction potential energy field function, the virtual forces from other agents acting on each autonomously moving agent are calculated, including position virtual force, velocity virtual force and acceleration virtual force.

[0183] The total virtual force of each autonomous mobile agent is obtained by vector synthesis of all virtual forces acting on it.

[0184] Using total virtual force as a control signal, the driving speed and direction of the autonomous mobile intelligent agent are adjusted through a control algorithm.

[0185] The virtual force of the potential energy field is used to plan the driving path of an autonomous mobile intelligent agent.

[0186] In summary, this invention, by introducing an emotion-influencing factor, accurately quantifies continuous-dimensional emotion values ​​and integrates them into a random slowing probability function, thereby improving the realism and accuracy of collaborative control of heterogeneous mobile intelligent agents and making the behavior of artificial mobile intelligent agents more realistic. Simultaneously, the method based on potential energy field virtual force transforms the position, velocity, and acceleration information of the autonomous mobile intelligent agent into virtual field forces, effectively controlling its motion through field force planning, thus enhancing the autonomous decision-making and path planning capabilities of the autonomous mobile intelligent agent. Addressing the challenge of collaborative control in complex environments, this invention significantly improves the adaptability and overall intelligence of collaborative control of heterogeneous mobile intelligent agents through emotion recognition, deceleration rules, and potential energy field optimization.

[0187] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0189] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0190] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0191] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A method for heterogeneous mobile agent cooperative control and evolution, characterized in that, The application relates to an emotion-cognition-based artificial mobile agent and automatic mobile agent system. The artificial mobile agent and the automatic mobile agent are mixed according to a preset proportion by using a continuous cellular automaton, and the artificial mobile agent and the automatic mobile agent are generated through an iteration process; An emotion-cognition module is embedded in the artificial mobile agent, and different granularity emotion clues are obtained according to fuzzy theory; Evolution rules of the artificial mobile agent are constructed according to the different granularity emotion clues, and the state of the artificial mobile agent is updated; The evolution rules of the artificial mobile agent include acceleration rules, deceleration rules, random slowing rules with a random slowing probability function and position updating rules; The position, speed and acceleration of the automatic mobile agent are obtained, a virtual repulsive force field and a virtual attractive force field are modeled, the position, speed and acceleration of the automatic mobile agent are obtained, evolution rules of the automatic mobile agent are constructed based on an improved interaction potential field function, and the state of the automatic mobile agent is updated; The evolution rules of the automatic mobile agent include acceleration rules, deceleration rules and position updating rules; The acceleration rules are used for adjusting the speed of the automatic mobile agent or the artificial mobile agent; The deceleration rules are used for avoiding collision between the automatic mobile agent and the artificial mobile agent; The random slowing rules with a random slowing probability function are used for slowing down the artificial mobile agent randomly based on an emotion influence factor and a random slowing probability function; The position updating rules are used for determining the position of the automatic mobile agent or the artificial mobile agent. The motion and motion path of the automatic mobile agent are controlled by a field force planning method, the perception information sharing mechanism of the automatic mobile agent is utilized, the motion and motion path of the automatic mobile agent and different granularity emotion clues in the running scene of the artificial mobile agent are combined, and the motion path of the artificial mobile agent is planned.

2. The heterogeneous mobile agent cooperative control and evolution method according to claim 1, characterized in that, The emotion-cognition module includes an emotion perception layer and a feature fusion network, the emotion perception layer adopts a double-channel fusion attention mechanism network structure, and the method for obtaining different granularity emotion clues according to fuzzy theory includes the following steps: The emotion perception layer is used for capturing and extracting character emotion clues and scene emotion clues in a running scene through a character channel and a scene channel respectively, and a preliminary feature vector is formed; Fuzzy theory is used for quantitatively processing continuous dimension emotion values in the preliminary feature vector, and an emotion influence factor is obtained; The emotion influence factor is input into the feature fusion network, fusion processing is conducted, and different granularity emotion clues are obtained.

3. The heterogeneous mobile agent cooperative control and evolution method according to claim 2, wherein, The method for quantitatively processing continuous dimension emotion values in the preliminary feature vector by using fuzzy theory to obtain an emotion influence factor includes the following steps: Based on a Mamdani model, emotion pleasantness, emotion arousal and emotion dominance are taken as input variables, and an emotion influence factor is taken as an output variable, so that a three-value input single-value output emotion fuzzy reasoning model is constructed; According to the emotion metric values of the emotion pleasantness, the emotion arousal and the emotion dominance, input variable fuzzy sets are constructed, including emotion pleasantness fuzzy set one, emotion pleasantness fuzzy set two and emotion pleasantness fuzzy set three, emotion arousal fuzzy set one, emotion arousal fuzzy set two and emotion arousal fuzzy set three, and emotion dominance fuzzy set one, emotion dominance fuzzy set two and emotion dominance fuzzy set three; Output variable fuzzy sets are constructed, including emotion factor fuzzy set one, emotion factor fuzzy set two and emotion factor fuzzy set three; The input variable fuzzy sets and the output variable fuzzy sets are fuzzified by using Gaussian membership functions; Data samples of the emotion pleasantness, the emotion arousal and the emotion dominance in the Emotic dataset are analyzed to obtain an artificial experience rule base capable of reflecting the relationship between the input variables and the output variables; According to the artificial experience rule base, an emotion representation fuzzy rule matrix is constructed; Continuous emotion values in the preliminary feature vector are converted into the membership degrees of the input set fuzzy sets through fuzzification; According to the emotion representation fuzzy rule matrix, the input fuzzy sets are mapped to the output fuzzy sets by using a fuzzy inference engine, calculation is performed, and a final output fuzzy set is obtained; The final output fuzzy set is de-fuzzified by using a centroid method to obtain an emotion influencing factor.

4. The heterogeneous mobile agent cooperative control and evolution method according to claim 3, wherein, According to the artificial experience rule base, a fuzzy rule matrix of emotion representation is constructed, and the constructed fuzzy rule matrix of emotion representation is expressed as: The first three columns of the emotion representation fuzzy rule matrix represent the fuzzy set indexes corresponding to the input variables of the emotion pleasantness, the emotion arousal and the emotion dominance, the fourth column represents the fuzzy set index corresponding to the output variable of the emotion influencing factor, the fifth column represents the rule weight of the emotion representation fuzzy rule matrix, and the sixth column represents the connecting word of the rule of the emotion representation fuzzy rule matrix. When the rule weight is 1, the logical connecting word is "and", and when the rule weight is 2, the logical connecting word is "or"; The rule of the first row of the emotion representation fuzzy rule matrix is that when the input emotion pleasantness belongs to the emotion pleasantness fuzzy set one, the input emotion arousal belongs to the emotion arousal fuzzy set three, and the input emotion dominance belongs to the emotion dominance fuzzy set three, the output is the emotion factor fuzzy set one, the rule weight of the first row is 1, and the logical connecting word is "and"; The rule of the second row of the fuzzy rule matrix is that when the input emotion pleasantness belongs to the emotion pleasantness fuzzy set two, the input emotion arousal belongs to the emotion arousal fuzzy set one, and the input emotion dominance belongs to the emotion dominance fuzzy set three, the output is the emotion factor fuzzy set two, the rule weight of the second row is 1, and the logical connecting word is "and"; The rule of the third row of the fuzzy rule matrix is that when the input emotion pleasantness belongs to the emotion pleasantness fuzzy set one, the input emotion arousal belongs to the emotion arousal fuzzy set two, and the input emotion dominance belongs to the emotion dominance fuzzy set one, the output is the emotion factor fuzzy set three, the rule weight of the third row is 1, and the logical connecting word is "and".

5. The heterogeneous mobile agent cooperative control and evolution method of claim 1, wherein, When the running scene is a road traffic flow, the continuous cellular automaton takes vehicles as cells, generates artificial driving vehicles and automatic networked vehicles through an iterative process, and state information σ of the continuous cellular automaton is i (t) is expressed as: where x n (t), v n (t) and a n (t) represent the position, velocity and acceleration of the ego vehicle n at the current time t, respectively, E n represents the vehicle ideal state vector of the ego vehicle n, AFF n represents the driver emotional state vector of the ego vehicle n, respectively denote the vehicle desired speed of the host vehicle n, the vehicle desired following distance of the host vehicle n and the vehicle safety time gap of the host vehicle n, AFF n _V(t), AFF n _A(t) and AFF n _D(t) respectively denote the measure of the host vehicle n driver's hedonic tone, arousal and dominance at the current time instant t. The continuous cellular automaton takes vehicles as cells, generates artificial driving vehicles and automatic networked vehicles through an iterative process, and controls the artificial driving vehicles a n (t) is represented as: where A0represents the maximum acceleration of the vehicle, λ represents the acceleration index of the vehicle, s n (t) and Δν(t) represent the relative distance and relative speed of the preceding vehicle n+1 and the subject vehicle n, respectively, B represents the absolute value of the comfortable deceleration of the vehicle, S0represents the static safety distance, v n+1 (t) represents the speed of the preceding vehicle n+1 at the current time t.

6. The heterogeneous mobile agent cooperative control and evolution method according to claim 5, wherein, The final output fuzzy set is de-fuzzified using the centroid method to obtain the emotional impact factor, and the obtained emotional impact factor k is expressed as: k = f(AFF n _V(t), AFF n _A(t), AFF n _D(t)) (4); where AFF n _V(t), AFF n _A(t), and AFF n _D(t) represent the measurement values of the driver's emotional valence, emotional arousal, and emotional dominance at the current time t, respectively.

7. The heterogeneous mobile agent cooperative control and evolution method according to claim 6, wherein, The evolution rules of the artificial mobile agent include acceleration rules, deceleration rules, random slowing rules of introducing a random slowing probability function, and position updating rules; wherein the acceleration rules of the artificial mobile agent are expressed as: v n (t+1) = min(v n (t) + a n (t),v max ) (5); where v n (t + 1) denotes the speed of the ego vehicle n at the current time t, v n (t) denotes the speed of the ego vehicle n at the current time t, a n (t) denotes the acceleration of the ego vehicle n at the current time t, v max denotes the maximum speed limit of the road. The deceleration rule of the artificial mobile agent is expressed as: d safe = s n (t) - s0(6); where d safe safety following distance, s n (t) represents the relative distance between the preceding vehicle n+1 and the subject vehicle n, and s0 represents the static safety distance. Based on the emotion influence factor of the n-th driver of the ego vehicle and the random deceleration probability function, the n-th driver of the ego vehicle has a p n (t+1) probability of random deceleration, wherein p n (t+1) represents the random deceleration probability of the n-th ego vehicle, and the random deceleration rule with the random deceleration probability function is represented as: v n (t+1) = max(v n (t)-c,0) (7). where v n (t + 1) represents the speed of the vehicle n at the current time t, v n (t) represents the speed of the vehicle n at the current time t, and c represents a deceleration value. Position x of the own vehicle n at the current time t n (t) and velocity v n (t) jointly determine the position x of the own vehicle n at the next time t+1 n (t+1); The expression of the position updating rule of the artificial mobile agent is: x n (t+1) = x n (t) + v n (t+1) (8); where x n (t+1) represents the position of the host vehicle n at the next time (t+1), x n (t) represents the position of the host vehicle n at the current time t, v n (t) represents the speed of the host vehicle n at the current time t.

8. The heterogeneous mobile agent cooperative control and evolution method of claim 5, wherein, The evolution rule of the automatic mobile agent includes the acceleration rule, the deceleration rule and the position updating rule; wherein the acceleration rule for automatically moving the agent is represented as: where v n (t + 1) represents the speed of the host vehicle n at the current time t, v n (t) represents the speed of the host vehicle n at the current time t, v max represents the maximum speed limit of the road, a represents the acceleration of the host vehicle n calculated according to the double-integral motion equation, m represents the mass of the host vehicle n, d safe represents the safety following distance, and F represents the total virtual force. The deceleration rule of the automatic mobile agent is that when the repulsive force generated by the virtual potential field of the current vehicle n+1 is greater than the attractive force, the total virtual force acting on the current vehicle n is the repulsive force; The position updating rule of the automatic mobile agent is consistent with the position updating rule of the artificial mobile agent.

9. The heterogeneous mobile agent cooperative control and evolution method of claim 1, wherein, The method for controlling the movement and path of the automatic mobile agent through the field force planning method comprises: According to the improved interaction potential energy field function, the virtual force acting on each automatic mobile agent from other agents is calculated, including position virtual force, speed virtual force and acceleration virtual force; The total virtual force of each automatic mobile agent is obtained by vector synthesis of all virtual forces acting on each automatic mobile agent; The total virtual force is used as a control signal to adjust the driving speed and direction of the automatic mobile agent through a control algorithm; The driving path of the automatic mobile agent is planned by using the potential energy field virtual force.

10. The heterogeneous mobile agent cooperative control and evolution method of claim 9, wherein, The position virtual force includes position virtual attractive force and position virtual repulsive force, the speed virtual force includes speed virtual attractive force and speed virtual repulsive force, and the acceleration virtual force includes acceleration virtual attractive force and acceleration virtual repulsive force. repels the position of the virtual force F rep-d is represented as: where k rep-d represents the position virtual repulsive potential energy coefficient, r represents the distance of the automated networking vehicle to the target point, r0represents the repulsive potential field influence range, a distance vector representing an automated connected vehicle to a target point, The module of the distance vector of the automatic networked vehicle to the target point is represented. The position virtual force F att-d is expressed as: F att-d = k att-d r g ( 11 ); where k att-d represents the position virtual gravitational potential energy coefficient, r g represents the distance of the automated networking vehicle to the target point. The speed virtual repulsive force F rep-v is represented as: where k rep-v represents the speed virtual repulsive potential energy coefficient, r represents the distance of the automated networking vehicle to the target point, r0represents the repulsive potential field influence range, represents a speed difference vector of the preceding vehicle and the host vehicle, The module of the speed difference vector of the front vehicle and the current vehicle is represented. The speed virtual force F att-v is expressed as: F att-v = tanh(k att-v ||Δv e ||)r g (13) ; where k att-v represents the speed virtual gravitational potential energy coefficient, Δv e represents the speed difference between the desired speed and the current speed, r g represents the distance from the automated connected vehicle to the target point, tanh represents the hyperbolic tangent function, ||Δv e || represents the speed difference vector length between the desired speed and the current speed. The acceleration virtual repulsive force F rep-a is expressed as: where k rep-a represents the acceleration virtual repulsive potential energy coefficient, r represents the distance from the target point of the automated networking vehicle, r0represents the repulsive potential field influence range, represents the acceleration difference vector between the preceding vehicle and the host vehicle, The module of the acceleration difference vector of the front vehicle and the current vehicle is represented. The acceleration virtual force F att-a is expressed as: F att-a = tanh(k att-a ||Δa e ||)r g ; (15); where k att-a represents the acceleration virtual gravitational potential energy coefficient, Δa e represents the difference between the desired acceleration and the current acceleration, r g represents the distance of the automated connected vehicle to the target point, ||Δa e || represents the length of the difference vector between the desired acceleration and the current acceleration.

Images