Interactive design method of intelligent display robot

Abstract

The invention relates to the technical field of intelligent display, and particularly discloses an interactive design method for an intelligent display robot, and the method comprises the steps: multi-modal perception data collection, user state analysis, display content adjustment, robot posture adjustment, and interactive response and optimization. According to the scheme, the layout optimization model with the visual focus as the guide is established, the high-importance content module is driven to actively approach the current watching area of the user, the information searching time is remarkably shortened, the cognitive load of the user is estimated in real time, the global information presentation density is dynamically adjusted, and the visual fatigue of the user is effectively reduced; through multi-modal perception fusion and a dynamic posture self-adaptive mechanism, intelligent cooperative adjustment of screen postures, positions and display contents is realized, and the comfort and naturalness of user interaction are remarkably improved; interactive decision making is carried out through multi-channel adaptive response and personalized strategy optimization, intelligent channel optimization of scene, user and cognition three-dimensional driving is achieved, and the interaction efficiency and the user satisfaction degree are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent display technology, specifically to an interactive design method for an intelligent display robot. Background Technology

[0002] With the increasing prevalence of intelligent devices in daily life, users have higher and higher requirements for the functionality of display devices. Fixed display devices can no longer meet users' personalized and dynamic viewing needs in different scenarios. Traditional display interfaces have a fixed layout, constant information density, and monotonous visual style; moreover, the position of the display device is fixed, and users need to actively adjust their own position or the angle of the device to obtain the best viewing experience, lacking the ability to adapt to user behavior and environmental conditions; general intelligent display devices have simple interaction methods and lack the comprehensive perception and response capabilities to user interaction preferences and multi-tasking scenarios. Summary of the Invention

[0003] To address the above issues and overcome the shortcomings of existing technologies, this invention provides an interactive design method for intelligent display robots. Addressing the problems of fixed layouts, constant information density, and monotonous visual styles in traditional display interfaces, this solution establishes a layout optimization model guided by visual focus. This model drives highly important content modules to actively move closer to the user's current gaze area, significantly shortening information search time, estimating user cognitive load in real time, and dynamically adjusting the overall information presentation density, effectively reducing user visual fatigue. Regarding the issue of fixed display device positions requiring users to actively adjust their position or device angle for optimal viewing experience and lacking adaptability to user behavior and environmental conditions, this solution utilizes multimodal perception fusion and dynamic posture adaptation mechanisms to achieve intelligent collaborative adjustment of screen posture, position, and displayed content, significantly improving the comfort and naturalness of user interaction. Finally, addressing the issue of limited interaction methods in general intelligent display devices and the lack of comprehensive perception and response capabilities to user interaction preferences and multi-task scenarios, this solution uses multi-channel adaptive response and personalized strategy optimization for interaction decision-making. This achieves intelligent channel optimization driven by three dimensions: scene, user, and cognition, effectively improving interaction efficiency and user satisfaction.

[0004] The technical solution adopted in this invention is as follows: This invention provides an interactive design method for an intelligent display robot, which includes the following steps:

[0005] Step S1: Multimodal perception data acquisition, which includes user data, environmental data, and robot data;

[0006] Step S2: User status analysis, confirming user identity based on user data, and identifying the user's real-time cognitive load index during interaction with the robot;

[0007] Step S3: Adjust the displayed content. Based on the user's cognitive load index and environmental data, define the content modules in the robot's display screen and dynamically adjust the optimal content layout.

[0008] Step S4: Robot posture adjustment, dynamically adjust the robot's movement trajectory and the angle of the display screen based on user data and robot data;

[0009] Step S5: Interaction Response and Optimization. Calculate user interaction satisfaction, select the robot's optimal interaction channel based on current environmental data, collect user feedback, and continuously optimize the robot's posture and position parameters, as well as the optimal content layout.

[0010] Further, in step S2, the user state parsing specifically includes the following steps:

[0011] Step S21: User identification, extract the user's skeletal key points from the user data to confirm the user's identity;

[0012] Step S22: Multi-dimensional feature extraction. Extract multi-dimensional feature vectors from the interaction task for users whose identities have been confirmed, including visual load coefficient, emotional load coefficient, physiological load coefficient, intent load index, and performance load index, in the following form: ;

[0013] In the formula, Represents a multi-dimensional feature vector. These represent the visual load coefficient, emotional load coefficient, physiological load coefficient, intention load index, and performance load index, respectively.

[0014] Step S23: Adaptive weight calculation, using a multilayer perceptron to dynamically calculate the weights of features in each dimension, using the following formula: ;

[0015] In the formula, Represents feature weights, Indicates the feature dimension index. This represents the natural exponential function. This represents a multilayer perceptron. Representing feature dimension, Historical context features representing multi-dimensional feature vectors;

[0016] Step S24: Calculate the cognitive load index. Calculate the user's cognitive load index during the interactive task using the following formula: ;

[0017] In the formula, This represents the user's cognitive load index.

[0018] Furthermore, in step S3, the adjustment of the displayed content specifically includes the following steps:

[0019] Step S31: Content Module Definition. Define the set of content modules for the robot's display interface, and set the importance weight, initial position, baseline size, and information content of each content module, in the following format: ;

[0020] In the formula, Represents a collection of content modules. Indicates the number of content modules. This indicates a content module;

[0021] Step S32: Adaptive density adjustment. Based on the user's real-time cognitive load index, dynamically adjust the presentation density of content modules and calculate the global density adjustment factor using the following formula: ;

[0022] In the formula, This represents the global density adjustment factor. Indicates the adjustment coefficient;

[0023] Step S33: Style and color adaptation. Adjust the colors, font size, and animation styles of the display interface based on the global density adjustment factor and environmental data.

[0024] Step S34: Solving for the optimal content layout. Define the set of all content module positions on the display interface as the content layout. Perform global optimization on the positions of the content modules to calculate the optimal content layout. The formula used is as follows: ;

[0025] In the formula, This indicates the optimal content layout. It is a minimum value function. Indicates content layout, , Indicates the index of the content module. , These represent the content modules respectively. and The center position coordinates, Indicates the importance weight of the content module. Indicates the coordinates of the user's visual focus. This represents the cost of the distance between a content module and the user's visual focus. Represents the regularization coefficient. This represents the visual complexity penalty term;

[0026] Step S35: Display interface generation. Based on the optimal content layout and the colors, font sizes, and animation styles of the display interface, render and output to the robot's display screen.

[0027] Furthermore, in step S4, the robot posture adjustment specifically includes the following steps:

[0028] Step S41: Estimate the user's relative position by extracting the user's eye height from the user data and converting it to the robot's display screen coordinate system;

[0029] Step S42: Calculate the optimal viewing area. Calculate the optimal tilt angle of the display screen using the following formula: ;

[0030] In the formula, This indicates the optimal tilt angle of the display screen. It is the arctangent function. Indicates the user's eye height. Indicates the height of the screen center. This represents the horizontal vector from the user to the screen. The user's head posture compensation coefficient. Indicates the user's head tilt angle. This represents the user's personalized angle offset. This represents the correction factor for the user's cognitive load index.

[0031] Step S43: Robot state definition, defining the robot's adjustable posture state and translation position state, using the following formulas: ; ;

[0032] In the formula, Indicates time, Indicates an adjustable attitude state. This indicates the optimal screen tilt angle in real time. This indicates the real-time center height of the screen. Indicates the movement location status. This represents the coordinates of the robot chassis on a two-dimensional plane. Indicates the orientation angle of the robot's chassis;

[0033] Step S44: Smooth trajectory planning. Plan the robot's movement trajectory, define constraints based on robot data, construct a cost function, and calculate the robot's optimal trajectory within a future time window. The formula used is as follows: ;

[0034] In the formula, This represents the robot's movement trajectory. Representing the trajectory The comfort cost function, This represents the robot's movement time window. This represents the attitude adjustment cost. This represents the cost of location relocation. Indicates the weighting coefficient;

[0035] Step S45: Dynamic obstacle avoidance, real-time detection of obstacles on the robot's movement trajectory, setting three levels of safety distances: warning, obstacle avoidance, and emergency stop, and defining the obstacle avoidance strategy.

[0036] Furthermore, in step S5, the interactive response and optimization specifically includes the following steps:

[0037] Step S51: Interaction satisfaction assessment, based on multi-dimensional feature vectors to provide feedback scores for interaction tasks, and calculate user satisfaction with each interaction task;

[0038] Step S52: Interaction Channel Optimization. Define the robot's set of interaction channels. Select the optimal interaction channel based on current environmental data, user cognitive load index, and historical interaction satisfaction. The formula used is as follows: ;

[0039] In the formula, Indicates the interaction channel. Represents environmental data. Indicative of cognitive load index With the environment Select Channel The probability, Indicates channel In the environment The applicability rating below, Indicates user's channel Interaction satisfaction and These are the weighting coefficients for scenario applicability and interaction satisfaction, respectively. Indicates the total number of channels. Indicates the interactive channel index;

[0040] Step S53: Response strategy optimization. Adjust the robot's posture and position parameters, as well as the display parameters of the optimal content layout, according to the optimal interaction channel. Associate the interaction history with the weight of each interaction channel based on the user's identity.

[0041] The beneficial effects achieved by the present invention using the above solution are as follows:

[0042] (1) In response to the problems of fixed layout, constant information density and monotonous visual style in traditional display interfaces, this solution establishes a layout optimization model guided by visual focus, drives high-importance content modules to actively move closer to the user's current gaze area, significantly shortens information search time, estimates user cognitive load in real time, and dynamically adjusts the global information presentation density, effectively reducing user visual fatigue.

[0043] (2) In response to the problem that the display device is fixed in position and users need to actively adjust their own position or device angle to obtain the best viewing experience, and lack the ability to adapt to user behavior and environmental conditions, this solution realizes intelligent collaborative adjustment of screen posture, position and display content through multimodal perception fusion and dynamic posture adaptation mechanism, which significantly improves the comfort and naturalness of user interaction.

[0044] (3) In view of the problem that general intelligent display devices have a single interaction mode and lack comprehensive perception and response capabilities for user interaction preferences and multi-task scenarios, this solution makes interaction decisions through multi-channel adaptive response and personalized strategy optimization, realizes intelligent channel selection driven by three dimensions of scenario, user and cognition, and effectively improves interaction efficiency and user satisfaction. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating the interactive design method for an intelligent display robot proposed in this invention.

[0046] Figure 2 This is a flowchart illustrating step S2;

[0047] Figure 3 This is a flowchart illustrating step S3;

[0048] Figure 4 This is a flowchart illustrating step S4.

[0049] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. Detailed Implementation

[0050] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0051] Example 1, see Figure 1 The present invention provides an interactive design method for an intelligent display robot, the method comprising the following steps:

[0052] Step S1: Multimodal perception data acquisition, which includes user data, environmental data, and robot data;

[0053] Step S2: User status analysis, confirming user identity based on user data, and identifying the user's real-time cognitive load index during interaction with the robot;

[0054] Step S3: Adjust the displayed content. Based on the user's cognitive load index and environmental data, define the content modules in the robot's display screen and dynamically adjust the optimal content layout.

[0055] Step S4: Robot posture adjustment, dynamically adjust the robot's movement trajectory and the angle of the display screen based on user data and robot data;

[0056] Step S5: Interaction Response and Optimization. Calculate user interaction satisfaction, select the robot's optimal interaction channel based on current environmental data, collect user feedback, and continuously optimize the robot's posture and position parameters, as well as the optimal content layout.

[0057] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the multimodal sensing data specifically includes:

[0058] User data: posture data, facial data, gaze data, gesture data, voice data, heart rate variability data, and skin conductance data;

[0059] Environmental data: ambient light data, ambient noise data, indoor maps;

[0060] Robot data: pose data, dynamics data, energy data.

[0061] Example 3, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S2, the user state parsing specifically includes the following steps:

[0062] Step S21: User identification. The OpenPose algorithm is used to extract skeletal key points from the user's pose data and combine them with facial data to confirm the user's identity.

[0063] Step S22: Multi-dimensional feature extraction. Extract multi-dimensional feature vectors from the interaction task for users whose identities have been confirmed, including visual load coefficient, emotional load coefficient, physiological load coefficient, intent load index, and performance load index, in the following form: ;

[0064] In the formula, Represents a multi-dimensional feature vector. These represent the visual load coefficient, emotional load coefficient, physiological load coefficient, intention load index, and performance load index, respectively.

[0065] Step S23: Adaptive weight calculation, using a multilayer perceptron to dynamically calculate the weights of features in each dimension, using the following formula: ;

[0066] In the formula, Represents feature weights, Indicates the feature dimension index. This represents the natural exponential function. This represents a multilayer perceptron. Representing feature dimension, Historical context features representing multi-dimensional feature vectors;

[0067] Step S24: Calculate the cognitive load index. Calculate the user's cognitive load index during the interactive task using the following formula: ;

[0068] In the formula, This represents the user's cognitive load index.

[0069] Example 4, see Figure 1 This embodiment is based on the above embodiment. In step S22, the multi-dimensional feature vector is specifically:

[0070] Based on the user's posture data, facial data, and gaze data, the gaze point dispersion and blink frequency deviation are calculated to estimate the user's gaze direction and generate a visual load coefficient.

[0071] The user's facial data, gesture data, and voice data are comprehensively analyzed to extract the user's emotional load coefficient.

[0072] The user's physiological load coefficient is calculated based on heart rate variability data and skin conductance data;

[0073] Using users' visual load characteristics, emotional load coefficients, and physiological load indicators as behavioral features, a spatiotemporal graph is constructed to capture users' interaction intentions. Nodes represent users' behavioral features at each moment, and edges represent temporal continuity and spatial correlation. The behavioral features are mapped to basic load values, and users' intention load indicators are extracted.

[0074] Statistical analysis of error rate and average response time in recent user-robot interaction tasks, outputting performance load metrics.

[0075] Example 5, see Figure 1 and Figure 3This embodiment is based on the above embodiment. In step S3, the adjustment of the displayed content specifically includes the following steps:

[0076] Step S31: Content Module Definition. Define the set of content modules for the robot's display interface, and set the importance weight, initial position, baseline size, and information content of each content module, in the following format: ;

[0077] In the formula, Represents a collection of content modules. Indicates the number of content modules. This indicates a content module;

[0078] Step S32: Adaptive density adjustment. Based on the user's real-time cognitive load index, dynamically adjust the presentation density of content modules and calculate the global density adjustment factor using the following formula: ;

[0079] In the formula, This represents the global density adjustment factor. Indicates the adjustment coefficient;

[0080] Step S33: Style and color adaptation. Adjust the colors, font size, and animation styles of the display interface based on the global density adjustment factor and environmental data.

[0081] Step S34: Solving for the optimal content layout. Define the set of all content module positions on the display interface as the content layout. Perform global optimization on the positions of the content modules to calculate the optimal content layout. The formula used is as follows: ;

[0082] In the formula, This indicates the optimal content layout. It is a minimum value function. Indicates content layout, , Indicates the index of the content module. , These represent the content modules respectively. and The center position coordinates, Indicates the importance weight of the content module. Indicates the coordinates of the user's visual focus. This represents the cost of the distance between a content module and the user's visual focus. Represents the regularization coefficient. This represents the visual complexity penalty term;

[0083] Step S35: Display interface generation. Based on the optimal content layout and the colors, font sizes, and animation styles of the display interface, render and output to the robot's display screen.

[0084] By performing the aforementioned operations, this solution addresses the problems of traditional display interfaces having fixed layouts, constant information density, and monotonous visual styles. It establishes a layout optimization model guided by visual focus, driving highly important content modules to actively move closer to the user's current gaze area, significantly shortening information search time, estimating the user's cognitive load in real time, and dynamically adjusting the global information presentation density, effectively reducing the user's visual fatigue.

[0085] Example 6, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In step S4, the robot posture adjustment specifically includes the following steps:

[0086] Step S41: Estimate the user's relative position by extracting the user's eye height from the pose data and gaze data, and converting it to the robot's display screen coordinate system;

[0087] Step S42: Calculate the optimal viewing area. Calculate the optimal tilt angle of the display screen using the following formula: ;

[0088] In the formula, This indicates the optimal tilt angle of the display screen. It is the arctangent function. Indicates the user's eye height. Indicates the height of the screen center. This represents the horizontal vector from the user to the screen. The user's head posture compensation coefficient. Indicates the user's head tilt angle. This represents the user's personalized angle offset. This represents the correction factor for the user's cognitive load index.

[0089] Step S43: Robot state definition, defining the robot's adjustable posture state and translation position state, using the following formulas: ; ;

[0090] In the formula, Indicates time, Indicates an adjustable attitude state. This indicates the optimal screen tilt angle in real time. This indicates the real-time center height of the screen. Indicates the movement location status. This represents the coordinates of the robot chassis on a two-dimensional plane. Indicates the orientation angle of the robot's chassis;

[0091] Step S44: Smooth trajectory planning. Plan the robot's movement trajectory, define constraints based on the robot's dynamics and energy data, construct a cost function, and calculate the robot's optimal trajectory within a future time window. The formula used is as follows: ;

[0092] In the formula, This represents the robot's movement trajectory. Representing the trajectory The comfort cost function, This represents the robot's movement time window. This represents the attitude adjustment cost. This represents the cost of location relocation. Indicates the weighting coefficient;

[0093] Step S45: Dynamic obstacle avoidance. Combine the indoor map to detect obstacles on the robot's movement trajectory in real time, set three layers of safety distances: warning, obstacle avoidance, and emergency stop, and define the obstacle avoidance strategy: when an obstacle is detected to enter the obstacle avoidance area, local trajectory replanning is performed, and the movement intention is conveyed to the user through the display screen during the movement.

[0094] By performing the aforementioned operations, this solution addresses the issue that users need to actively adjust their position or device angle to obtain the best viewing experience when the display device is in a fixed position, and that the solution lacks the ability to adapt to user behavior and environmental conditions. This solution achieves intelligent collaborative adjustment of screen posture, position, and displayed content through multimodal perception fusion and dynamic posture adaptation mechanisms, significantly improving the comfort and naturalness of user interaction.

[0095] Example 7, see Figure 1 This embodiment is based on the above embodiment. In step S5, the interactive response and optimization specifically includes the following steps:

[0096] Step S51: Interaction satisfaction assessment. Feedback scores for the interaction task are generated based on multi-dimensional feature vectors. The user's satisfaction with each interaction task is calculated using the following formula: ;

[0097] In the formula, Indicates satisfaction with the interaction. This represents the total number of dimensions of the multi-dimensional feature vector. This represents the feedback scores for each dimension of features. This represents the dynamic weights of each dimension learned based on the attention mechanism;

[0098] Step S52: Interaction Channel Optimization. Define the robot's set of interaction channels, including voice interaction, gesture interaction, touch interaction, gaze interaction, and physiological feedback. Select the optimal interaction channel based on current environmental data, the user's cognitive load index, and historical interaction satisfaction. The formula used is as follows: ;

[0099] In the formula, Indicates the interaction channel. Represents environmental data. Indicative of cognitive load index With the environment Select Channel The probability, Indicates channel In the environment The applicability rating below, Indicates user's channel Interaction satisfaction and These are the weighting coefficients for scenario applicability and interaction satisfaction, respectively. Indicates the total number of channels. Indicates the interactive channel index;

[0100] Step S53: Response strategy optimization. Adjust the robot's posture and position parameters, as well as the display parameters of the optimal content layout, according to the optimal interaction channel. Associate the interaction history with the weight of each interaction channel based on the user's identity.

[0101] By performing the aforementioned operations, this solution addresses the problem that general smart display devices have a single interaction method and lack comprehensive perception and response capabilities for user interaction preferences and multi-task scenarios. It makes interaction decisions through multi-channel adaptive response and personalized strategy optimization, realizing intelligent channel optimization driven by three dimensions of scenario, user, and cognition, effectively improving interaction efficiency and user satisfaction.

[0102] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0103] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0104] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. An interactive design method for an intelligent display robot, characterized in that: The method includes the following steps: Step S1: Multimodal perception data acquisition, which includes user data, environmental data, and robot data; Step S2: User status analysis, confirming user identity based on user data, and identifying the user's real-time cognitive load index during interaction with the robot; Step S3: Adjust the displayed content. Based on the user's cognitive load index and environmental data, define the content modules in the robot's display screen and dynamically adjust the optimal content layout. Step S4: Robot posture adjustment, dynamically adjust the robot's movement trajectory and the angle of the display screen based on user data and robot data; Step S5: Interaction Response and Optimization. Calculate user interaction satisfaction, select the robot's optimal interaction channel based on current environmental data, collect user feedback, and continuously optimize the robot's posture and position parameters, as well as the optimal content layout.

2. The interactive design method for an intelligent display robot according to claim 1, characterized in that: In step S21, the user state parsing includes the following steps: Step S21: User identification, extract the user's skeletal key points from the user data to confirm the user's identity; Step S22: Multi-dimensional feature extraction. Extract multi-dimensional feature vectors from the interaction task for users whose identities have been confirmed, including visual load coefficient, emotional load coefficient, physiological load coefficient, intention load index and performance load index. Step S23: Adaptive weight calculation, using a multilayer perceptron to dynamically calculate the weights of features in each dimension; Step S24: Calculate the cognitive load index. Calculate the user's cognitive load index during the interactive task using the following formula: ； In the formula, Represents a multi-dimensional feature vector. Indicates the feature dimension index. Represents feature weights, This represents the user's cognitive load index.

3. The interactive design method for an intelligent display robot according to claim 1, characterized in that: In step S3, the adjustment of the displayed content includes the following steps: Step S31: Content module definition, define the set of content modules for the robot display interface, and set the importance weight, initial position, baseline size and information content of each content module; Step S32: Adaptive density adjustment. Based on the user's real-time cognitive load index, dynamically adjust the presentation density of content modules and calculate the global density adjustment factor using the following formula: ； In the formula, Represents the global density adjustment factor. Indicates the adjustment coefficient; Step S33: Style and color adaptation. Adjust the colors, font size, and animation styles of the display interface based on the global density adjustment factor and environmental data. Step S34: Solving for the optimal content layout. Define the set of all content module positions on the display interface as the content layout. Perform global optimization on the positions of the content modules to calculate the optimal content layout. The formula used is as follows: ； In the formula, This indicates the optimal content layout. It is a minimum value function. Indicates content layout, , Indicates the index of the content module. , These represent the content modules respectively. and The center position coordinates, Indicates the importance weight of the content module. Indicates the coordinates of the user's visual focus. This represents the cost of the distance between a content module and the user's visual focus. Represents the regularization coefficient. This represents the visual complexity penalty term; Step S35: Display interface generation. Based on the optimal content layout and the colors, font sizes, and animation styles of the display interface, render and output to the robot's display screen.

4. The interaction design method for an intelligent display robot according to claim 1, characterized in that: In step S4, the robot posture adjustment specifically includes the following steps: Step S41: Estimate the user's relative position by extracting the user's eye height from the user data and converting it to the robot's display screen coordinate system; Step S42: Calculate the optimal viewing area by calculating the optimal tilt angle of the display screen; Step S43: Robot state definition, defining the robot's adjustable posture state and movement position state; Step S44: Smooth trajectory planning. Plan the robot's movement trajectory, define constraints based on robot data, construct a cost function, and calculate the robot's optimal trajectory within a future time window. The formula used is as follows: ； In the formula, This represents the robot's movement trajectory. Representing the trajectory The comfort cost function, This represents the robot's movement time window. This represents the attitude adjustment cost. This represents the cost of location relocation. Indicates the weighting coefficient; Step S45: Dynamic obstacle avoidance, real-time detection of obstacles on the robot's movement trajectory, setting three levels of safety distances: warning, obstacle avoidance, and emergency stop, and defining the obstacle avoidance strategy.

5. The interactive design method for an intelligent display robot according to claim 1, characterized in that: In step S5, the interactive response and optimization specifically includes the following steps: Step S51: Interaction satisfaction assessment, based on multi-dimensional feature vectors to provide feedback scores for interaction tasks, and calculate the user's interaction satisfaction for each interaction task; Step S52: Optimize the interaction channel. Define the set of robot interaction channels and select the optimal interaction channel based on current environmental data, user cognitive load index, and historical interaction satisfaction. Step S53: Response strategy optimization. Adjust the robot's posture and position parameters, as well as the display parameters of the optimal content layout, according to the optimal interaction channel. Associate the interaction history with the weight of each interaction channel based on the user's identity.

Images