Emotional robot mechanical arm trajectory generation method, device, equipment and storage medium

Abstract

The application discloses a kind of emotional robot mechanical arm trajectory generation method, device, equipment and storage medium, involve artificial intelligence technical field, including: human emotion, man-machine distance and environmental temperature are mapped to VA (Valence, Arousal) emotional model, obtain the value of emotional information Valence and Arousal;According to their values, the kinematic characteristic mapping is used to obtain the motion trajectory variation of mechanical arm under current emotional state;And by modifying the original trajectory of mechanical arm obtains new motion trajectory, to realize the real-time emotional expression of mechanical arm.The application can generate the motion trajectory of emotional robot mechanical arm according to current environment and real-time emotion, realize natural and harmonious human-computer interaction.

Description

Technical Field

[0001] The present invention relates to the field of automatic control of human-machine interaction of robotic arms, and in particular to a method, device, equipment and storage medium for generating trajectories of robotic arms of an emotional robot. Background Art

[0002] With the rapid development of intelligent robotics, natural interaction between humans and robots is becoming increasingly important. Emotion is essential for social interaction between humans and robots, and the emotional expression of robots, as a crucial means of achieving long-term human-robot interaction, is attracting increasing attention. Emotional interaction is the core and foundation of natural human-robot interaction. It processes emotional information during human-robot interaction, imbues robots with emotional and humanistic characteristics, and provides a corresponding emotional interaction experience, enabling robots to communicate emotionally. Given the significant progress in emotion recognition technology, integrating environmental and emotional information into the motion trajectory of a robotic arm, enabling it to express the user's emotions in different environments, can not only enrich cognitive and emotional interaction between humans and robots, but also better meet the application needs of natural human-robot interaction.

[0003] Current methods for generating emotion-based robotic arm trajectories primarily rely on identifying different human activities to derive different emotions and generate corresponding movements. These methods fail to consider the impact of environmental factors on emotional states, and are unable to adjust the robotic arm's motion state along a specific trajectory in real time based on human emotions to express different emotions. Some researchers have attempted to use generative adversarial networks to generate robotic arm motion from human arm motion, but such networks are complex to build, and the robotic arm is subject to kinematic and dynamic constraints, making the generated motion unsuitable for robotic arm control. Natural human-computer interaction systems with flexible and easy-to-use operation are becoming a widespread demand in the robotic arm application market.

[0004] Therefore, considering the influence of environmental factors and adjusting the motion state of the robotic arm under a specific trajectory according to human emotions so that it can express different emotions is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a method, device, equipment and storage medium for generating the trajectory of an emotional robot manipulator. The technical solution is implemented based on the kinematic feature mapping of emotional information.

[0006] The specific technical solution is as follows: human emotions, human-machine distance and ambient temperature are used to generate emotional states, and emotional information is converted into motion characteristics of the robotic arm through kinematic feature mapping, thereby generating the motion trajectory of the emotional robot arm.

[0007] According to a first aspect of the present invention, the present invention provides a method for generating a trajectory of an emotional robot manipulator, comprising the following steps:

[0008] S1: Map human emotions into the value VA of the VA emotion model through the emotion model mapping rules h ; Get the current human-machine distance and ambient temperature, and map the human-machine distance and ambient temperature into the value VA of the VA emotion model through the environmental fuzzy inference engine e ;

[0009] S2: VA is calculated by linear weighting method h and VA e Processing is performed to obtain the value VAc of the VA emotion model of the current overall emotional state;

[0010] S3: The value of the VA emotional model based on the current overall emotional state c , using the mapping of the robot arm's kinematic characteristics, the VA c Mapped into the change in motion trajectory of each joint of the robotic arm;

[0011] S4: Modify the original trajectory of the robotic arm according to the change in the motion trajectory of each joint of the robotic arm to generate a motion trajectory with emotion.

[0012] Preferably, in step S1, Kinect and a temperature sensor are used to obtain the human-machine distance and the ambient temperature respectively.

[0013] Furthermore, the acquired human emotions are output as the value VA of the VA emotion model through the emotion model mapping rule. h , including the corresponding Valence value V h and Arousal value A h .

[0014] Furthermore, the obtained human-machine distance and ambient temperature are mapped into the value VA of the VA emotion model through the environmental fuzzy inference engine. e , including the corresponding Valence value V e and Arousal value A e .

[0015] Furthermore, in step S2, the VA is weighted by a linear weighting method. h and VA e The specific calculation formula is as follows:

[0016] V c =αV h +βV e

[0017] A c =αA h +βA e

[0018] Where: Vc and A c The Valence value and Arousal value represent the current overall emotional state, collectively referred to as VA c , α and β are both constants greater than 0 and less than 1, representing the influence of human emotions and environmental conditions on the overall emotional state, respectively.

[0019] Furthermore, in step S3, the current value VA of the VA emotion model is c Mapped into the change in the motion trajectory of each joint of the robotic arm, the mapping from emotional information to the kinematic characteristics of the robotic arm is realized, and the change in the motion trajectory of each joint of the robotic arm θ′ i (t) is determined by the following formula:

[0020]

[0021]

[0022] Where: θ′ i (t) is the change in the motion trajectory of joint i with emotional information at time t, Δθ i (t) is the difference between the maximum rotation angle and the minimum rotation angle of joint i, m i is a random number between [0,0.2], is the position offset caused by the instability of joint motion, and ω is the angular velocity of the robot arm joint motor.

[0023] Furthermore, in step S4, the trajectory change θ′ obtained in step S3 is i (t) to modify the given original trajectory θ 0i (t), thus obtaining the motion trajectory θ with emotion i (t), to realize the emotional expression of the robot arm, the motion range of each joint needs to meet the motion constraints of the robot arm, and the motion trajectory θ with emotion i (t) is determined by the following formula:

[0024] θ i (t) = θ 0i (t)+θ′ i (t)

[0025] stθ imin <θ 0i (t)<θ imax

[0026] Where: θ i (t) is the motion trajectory of joint i with emotion, θ 0i (t) is the original trajectory of joint i, θ imin and θ imaxThe minimum and maximum rotation angles of joint i respectively.

[0027] According to a second aspect of the present invention, the present invention provides a device for generating a trajectory of an emotional robot manipulator, comprising the following modules:

[0028] Emotion mapping and fuzzy reasoning module, used to map human emotions into the value VA of VA emotion model through emotion model mapping rules h ; Get the current human-machine distance and ambient temperature, and map the human-machine distance and ambient temperature into the value VA of the VA emotion model through the environmental fuzzy inference engine e ;

[0029] Linear weighting module, used to use linear weighting method to VA h and VA e Processing is performed to obtain the value VA of the VA emotional model of the current overall emotional state c ;

[0030] Motion feature mapping module, used to calculate the value of the VA emotion model according to the current overall emotional state c , using the mapping of the robot arm's kinematic characteristics, the VA c Mapped into the change in motion trajectory of each joint of the robotic arm;

[0031] The emotional trajectory modification and generation module is used to modify the original trajectory of the robotic arm according to the change in the motion trajectory of each joint of the robotic arm and generate a motion trajectory with emotion.

[0032] According to the third aspect of the present invention, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for generating the trajectory of an emotional robot arm are implemented.

[0033] According to a fourth aspect of the present invention, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for generating the trajectory of an emotional robot arm.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] (1) The present invention provides a method for generating trajectory of an emotional robot arm. First, human emotions, the distance between the human and the robot, and the ambient temperature are mapped into a VA emotion model. This model can quantify the relationship between emotions and continuous dimensions, which is beneficial for solving the overall emotional state and realizing the kinematic feature mapping of the robot arm through specific numerical values.

[0036] (2) The present invention proposes a method for generating the trajectory of an emotional robot arm, which proposes a holistic emotion calculation method that uses human emotion, human-machine distance, and ambient temperature as input. This algorithm considers the impact of human activities and environmental factors on emotional state, solving the problem of previous methods that only consider the impact of human activities on emotions.

[0037] (3) The present invention proposes a method for generating trajectory of an emotional robot arm, and proposes an algorithm for mapping emotional information to the kinematic characteristics of the robot arm, which maps the values ​​of Valence and Arousal V in the VA emotional model of the current overall emotional state to ... c and A c , mapped to the trajectory changes of each joint of the robotic arm, and then generating the motion trajectory of the robotic arm, so that the movements of the robotic arm can express different emotions and increase the emotional interaction between people and robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0039] Figure 1 Schematic diagram of the principle of a method for generating a trajectory of an emotional robot arm in an embodiment of the present invention;

[0040] Figure 2 The mapping of the six basic emotions in the VA emotion model in the embodiment of the present invention;

[0041] Figure 3 is the membership function of the distance between a person and a robot in the environmental fuzzy reasoner in an embodiment of the present invention;

[0042] Figure 4 is the membership function of temperature in the environmental fuzzy inference device in the embodiment of the present invention;

[0043] Figure 5 The figure shows how the values ​​of Valence and Arousal in the environmental fuzzy inference engine change with the distance between the human and the machine and the temperature in the embodiment of the present invention.

[0044] Figure 6 The motion trajectory of the end joint of the 3-DOF robotic arm under different emotions in an embodiment of the present invention;

[0045] Figure 7 The motion trajectory of each joint of the 3-DOF robotic arm under the happy emotion in the embodiment of the present invention;

[0046] Figure 8 This is a structural diagram of a device for generating a trajectory of an emotional robot arm in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] Various exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention.

[0048] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0049] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0050] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0051] Technologies, methods and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, such technologies, methods and equipment should be considered part of the authorization specification.

[0052] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0053] Example 1

[0054] Reference Figure 1 ,This paper proposes a trajectory generation method for an emotional robot manipulator,based on the kinematic feature mapping of emotional information, which enables the emotional robot manipulator to express the current overall emotion,specifically including the following processes:

[0055] Step S1: Refer to Figure 2 , human emotions are mapped to the value VA of the VA (Valence, Arousal) emotion model through the emotion model mapping rule h (Including V h and A h ), and the corresponding rules are shown in Table 1.

[0056] Table 1 VA h Emotion model mapping rule table

[0057]

[0058] The human-machine distance and ambient temperature are mapped to the value VA of the VA emotion model through the environmental fuzzy reasoner. e (Including V e and A e), simulating the impact of human activities and environmental conditions on the emotional state of the robotic arm. In the VA emotional model, Valence corresponds to positive and negative emotions, and Arousal corresponds to the high and low energy of emotions. Mapping discrete emotions to continuous dimensions is conducive to quantitative operations. The emotional model mapping rule outputs the six human emotions obtained as the value VA of the VA emotional model. h The input of the environmental fuzzy inference system is the distance between the human and the robot and the temperature of the environment, which are close, suitable, far, cold, comfortable, and hot. According to the actual life scene, the fuzzy inference system should be more positive and have greater energy when the temperature is suitable and the distance is moderate, with a peak value; as the temperature and the distance between the human and the robot change, the emotion has V e and A e The membership functions of the human-machine distance and the ambient temperature are both Gaussian distributions, such as Figure 3 and Figure 4 As shown in the figure, the horizontal axes are the human-machine distance (distance) and the ambient temperature (temperature), and the vertical axes are the corresponding membership function values ​​(Degree of membership). Figure 3 、 4 In the middle, the fuzzy set {Low, Middle, Far}, the fuzzy set {Cold, Comfortable, Hot}. The fuzzy set {Low, Middle, High} is used to represent V e With A e The fuzzy quantity of , respectively, uses 9 fuzzy reasoning rules to reason, and its fuzzy reasoning table is shown in Table 2 and Table 3. Finally, the inferred V e With A e The fuzzy value is defuzzified and digitized using the centroid method to obtain the value V of the VA emotional model. e and A e . Reference Figure 5 , where (a) and (b) represent V e With A e Variation with distance, (c) and (d) represent V e With A e Changes with temperature.

[0059] Table 2 V e Fuzzy inference table of value environment fuzzy inference system

[0060]

[0061] Table 3 A e Fuzzy inference table of value environment fuzzy inference system

[0062]

[0063] Step S2: The VA obtained in step S1 h with VA e The value of is converted into the value of the VA emotion model of the current overall emotional state of the robotic arm through a linear weighted method. c , V c and A c The value of can be determined according to formula (1):

[0064]

[0065] In formula (1): V c and A c The values ​​of Valence and Arousal respectively represent the current overall emotional state. α and β are both constants greater than 0 and less than 1. They respectively represent the impact of human emotions and environmental conditions on the overall emotional state. In practical applications, the values ​​of weights α and β can be set based on the experience of professional and technical personnel. In this embodiment, α = 0.3, β = 0.1 are set and simulation research is carried out. The experimental results are as follows: Figure 6 and Figure 7 shown. Figure 6 is the motion trajectory of the end joint of the 3-DOF manipulator in the states of happy, angry, and sad, Figure 6 It can be seen that happiness and sadness have opposite Valence values ​​and the same Arousal value, so the offset of their trajectories is the same but in opposite directions; Figure 7 Figure 2 shows the motion trajectories of the joints (joint 1, joint 2, and joint 3) of a 3-DOF robotic arm under the emotion of happiness. Joint 1 is the end joint of the robotic arm and has greater expressive power, resulting in more kinetic energy and a larger offset.

[0066] Step S3: VA emotional model value V of the current overall emotional state obtained in step S2 c and A c , using the robot arm kinematic feature mapping, VA c The value of is mapped to the movement speed of the robot arm joint. In the VA emotion model, the valence dimension (Valence) represents the positive and negative emotional state. Positive emotions will have a larger movement amplitude and faster movement speed, and will bring instability. The instability is constructed through the Fourier series; the arousal dimension (Arousal) represents the energy level of the emotional state. The higher the energy, the larger the range of movement, and the lower the energy, the smaller the angle of movement. Furthermore, the movement trajectory change θ′ of each moving joint of the robot arm caused by the change in emotion is i(t) can be expressed by the values ​​of Valence and Arousal, and the motion change of each joint can be determined according to formula (2) and formula (3):

[0067]

[0068]

[0069] In formula (2) and formula (3): θ′ i (t) is the change in the trajectory of joint i with emotional information at time t, Δθ i (t) is the difference between the maximum rotation angle and the minimum rotation angle of joint i, m i is a random number between [0,0.2], is the position offset caused by the instability of joint motion, and ω is the angular velocity of the robot arm joint motor.

[0070] Step S4: Let the original trajectory of the robot arm be expressed as the joint angle θ 0i (t) = {θ 01 ,θ 02 ,…,θ 0n}, according to the motion trajectory change θ′ of each joint obtained in step S3 i (t) to modify the given original trajectory θ 0i (t), the modified robot arm motion trajectory θ i (t) can express the overall emotional state of the current robotic arm. The motion of each joint of the robotic arm must satisfy the kinematic constraints, and the motion trajectory θ with emotion i (t) can be determined by formula (4):

[0071] θ i (t) = θ 0i (t)+θ′ i (t) (4)

[0072] stθ imin <θ 0i (t)<θ imax

[0073] In formula (4): θ i (t) is the motion trajectory of joint i with emotion, θ 0i (t) is the original trajectory of joint i, θ imin and θ imax The minimum rotation angle and maximum rotation angle of joint i are respectively. In this embodiment, the rotation angle range of joint 1 and joint 3 of the three-degree-of-freedom robotic arm is 0-90°, and the rotation angle range of joint 2 is -90° to 90°.

[0074] Example 2:

[0075] In order to implement the method for generating the trajectory of the manipulator arm of the emotional robot described in the first embodiment, this embodiment provides a device for generating the trajectory of the manipulator arm of the emotional robot, referring to Figure 8 , the device includes the following modules:

[0076] Emotional mapping and fuzzy reasoning module 1 is used to map human emotions into the value VA of the VA emotional model through the emotion model mapping rules h ; Get the current human-machine distance and ambient temperature, and map the human-machine distance and ambient temperature into the value VA of the VA emotion model through the environmental fuzzy inference engine e ;

[0077] Linear weighting module 2 is used to adjust the VA h and VA e Processing is performed to obtain the value VAc of the VA emotion model of the current overall emotional state;

[0078] The motion feature mapping module 3 is used to map the value VAc of the VA emotion model of the current overall emotional state into the change of the motion trajectory of each joint of the robotic arm using the mapping of the kinematic characteristics of the robotic arm;

[0079] The emotional trajectory modification and generation module 4 is used to modify the original trajectory of the robotic arm according to the change in the motion trajectory of each joint of the robotic arm, and generate a motion trajectory with emotion.

[0080] Example 3:

[0081] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, the steps of the emotional robot arm trajectory generation method described in Example 1 are implemented, and the same technical effects can be achieved, which will not be repeated here.

[0082] Example 4:

[0083] This embodiment provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for generating the trajectory of the emotional robot arm described in Example 1 are implemented, and the same technical effects can be achieved, which will not be repeated here.

[0084] The above-mentioned embodiments of the present application provide a method and device for generating trajectory of emotional robot manipulator, equipment and storage medium, relate to the technical field of artificial intelligence, and include: mapping human emotion, human-machine distance and environmental temperature to a VA (Valence, Arousal) emotional model to obtain values of emotional information Valence and Arousal; according to the values, a kinematic feature mapping is used to obtain a motion trajectory change amount of the manipulator under a current emotional state; and a new motion trajectory is obtained by modifying an original trajectory of the manipulator, so that real-time emotional expression of the manipulator is realized. The present application can generate a motion trajectory of an emotional robot manipulator according to a current environment and real-time emotion, and realize natural and harmonious human-machine interaction.

[0085] It should be noted that in this document, the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or system that includes a series of elements not only includes those elements, but also includes other elements not explicitly listed, or inherent to such a process, method, article or system. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of another identical element in the process, method, article or system that includes the element.

[0086] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. In the unit claims of several devices, several of these devices can be embodied by the same hardware item. The use of the words first, second, and third does not represent any order, and these words can be interpreted as identifiers.

[0087] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, which is made by using the content of the present application specification and drawings, is also included in the patent protection scope of the present application.

Claims

1. A method for generating trajectory of an emotional robot manipulator, characterized in that: The following steps are involved: S1: Map human emotions into The value of the sentiment model ; Get the current human-machine distance and ambient temperature, and map the human-machine distance and ambient temperature into The value of the sentiment model ; S2: Through the linear weighting method and Processing to obtain the current overall emotional state The value of the sentiment model ; S3: Based on the current overall emotional state The value of the sentiment model , using the mapping of the robot arm's kinematic characteristics, Mapped into the change in motion trajectory of each joint of the robotic arm; S4: Modify the original trajectory of the robotic arm according to the change in the motion trajectory of each joint of the robotic arm to generate a motion trajectory with emotion; The acquired human emotions are output as The value of the sentiment model , including the corresponding value and value ; The obtained human-machine distance and ambient temperature are mapped into The value of the sentiment model , including the corresponding value and value .

2. The method for generating trajectory of an emotional robot manipulator according to claim 1, characterized in that: In step S1, use The human-machine distance and ambient temperature are obtained by the temperature sensor respectively.

3. The method for generating trajectory of an emotional robot arm according to claim 1, characterized in that: In step S2, the linear weighted method is used to and The specific calculation formula is as follows: Where: and Represents the current overall emotional state Value and Value, collectively known as , and Both are constants greater than 0 and less than 1, representing the impact of human emotions and environmental conditions on the overall emotional state.

4. The method for generating trajectory of an emotional robot arm according to claim 3, characterized in that: In step S3, Current value of the sentiment model Mapped into the change in the motion trajectory of each joint of the robotic arm, realizing the mapping from emotional information to the kinematic characteristics of the robotic arm, the change in the motion trajectory of each joint of the robotic arm Determined by the following formula: Where: For joints exist The change in the motion trajectory with emotional information at each moment, It's a joint The difference between the maximum rotation angle and the minimum rotation angle, for A random number between is the position offset caused by the instability of joint movement, is the angular velocity of the robot arm joint motor.

5. The method for generating trajectory of an emotional robot arm according to claim 1, characterized in that: In step S4, the trajectory change amount obtained in step S3 is To modify the given original trajectory , thereby obtaining a motion trajectory with emotion To realize the emotional expression of the robot arm, the motion range of each joint needs to meet the motion constraints of the robot arm and have an emotional motion trajectory. Determined by the following formula: Where: For joints A movement with emotions, For joints The original trajectory of and Joints Minimum and maximum rotation angles.

6. A device for generating trajectory of an emotional robot arm, characterized in that: Includes the following modules: Emotional mapping and fuzzy reasoning module is used to map human emotions into The value of the sentiment model ; Get the current human-machine distance and ambient temperature, and map the human-machine distance and ambient temperature into The value of the sentiment model ; Linear weighting module, used to use linear weighting method to and Processing to obtain the current overall emotional state The value of the sentiment model ; Motion feature mapping module is used to The value of the sentiment model , using the mapping of the robot arm's kinematic characteristics, Mapped into the change in motion trajectory of each joint of the robotic arm; The emotional trajectory modification and generation module is used to modify the original trajectory of the robotic arm according to the change in the motion trajectory of each joint of the robotic arm, and generate a motion trajectory with emotion; The acquired human emotions are output as The value of the sentiment model , including the corresponding value and value ; The obtained human-machine distance and ambient temperature are mapped into The value of the sentiment model , including the corresponding value and value .

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for generating the trajectory of an emotional robot arm are implemented as described in any one of claims 1-5.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for generating the trajectory of an emotional robot arm are implemented as described in any one of claims 1 to 5.

Images