MULTIMATED COGNITIVE SOCIAL ROBOT ASSISTANT SYSTEM FOR EDUCATION AND GAME PURPOSES.
Patent Information
- Authority / Receiving Office
- TR · TR
- Patent Type
- Applications
- Current Assignee / Owner
- EVREN DAĞLARLI
- Filing Date
- 2026-05-26
- Publication Date
- 2026-06-22
Abstract
Description
1 TARIFF MULTIMATED COGNITIVE SOCIAL ROBOT ASSISTANT SYSTEM FOR EDUCATION AND GAME PURPOSES. Technical Area This invention relates to robotics, social robotics, educational technologies, gamified learning, and human-robot interaction. It relates to the field of interaction and AI-powered autonomous assistant systems. The invention is particularly relevant to this area. Educational, gaming, mentoring, and friendship-like social activities for children, students, and individual users. Configured for interaction; tracked mobile base, head module with display, movable arm 10 and tactile paving, multi-mode sensing units, audio and visual interaction units, user a compact system containing profile memory, cognitive decision-making module and behavior generation module It is geared towards cognitive social robot assistant systems. The invention also includes a tracked mobile base that enables the robot to move stably indoors. Its structure includes a screen-based head module that can display facial expressions to the user, capturing the user's attention at 15 Movable arms and gripper type that allow for steering or interaction with the object. software and hardware that coordinate sensing, decision-making, and motion generation with endpoints It relates to its architecture. State of the Art 20 Current social robot systems offer basic levels of voice or visual interaction with users. some systems can be configured with components such as a movable base, screen, or simple arm movements. It can include. However, in known systems, education includes gamified learning, Personalization based on user profile, multi-mode detection, face animation, gesture generation, and Safe mobile behaviors are performed in an integrated manner on the same compact robot platform. 25 It remains limited. Safe speed and low weight are key considerations, especially for robots intended for children's use, home, classroom, and indoor environments. central, closed track structure, compact form free of sharp edges, force-limited arm. Features such as movement detection, contact detection, obstacle detection, and safe stopping are educational and It is important that it works in conjunction with gamified interaction. Known solutions are often either just 30 They focus on educational software or simply mobile robot hardware; user context, game performance, attention span, emotional response indicators, and previous interaction history It does not offer an integrated structure that adapts the robot's behavior by evaluating them together. Furthermore, even though some known robots use screens for facial expressions, this screen does not allow for facial expressions. The displayed eye, mouth, facial expressions, attention orientation, and speech patterns influence cognitive decision-making. 35 Depending on the interaction context defined by the module, arm movements, vocal responses, and The simultaneous coordination with mobile behaviors is not sufficiently developed. Therefore... 2 the user's age, education level, task achievement, game performance, attention span and a multimodal and secure social environment that can adapt itself based on previous interaction history. A robot assistant system is needed. Purpose of the Invention 5 The primary goal of this invention is a multimodal cognitive social robot assistant system for educational and play purposes. by providing the user's educational progress, game performance, attention span, and preference information, robot behavior based on emotional response indicator and previous interaction history The goal is to make adaptation possible. Another aim of the invention is to create a personality profile that can establish friend-like social interaction with the user. such as form of address, style of speaking, preference recall, and reference to previous interactions. The goal is to create a robot assistant that supports these functions. Another aim of the invention is to create facial avatar animations, including eyes, mouth, and facial expressions, in a head module with a screen. being able to demonstrate mood, attention focus, speech pattern, and anticipation of a response; Pointing, greeting, orienting towards an object, play through movable arm and grasping ends 15 behaviors such as holding an object, showing educational material, and producing social gestures. to accomplish. Another objective of the invention is to allow the robot to approach the user via a tracked mobile base, moving away from the user, following the user, heading towards a designated location, within the playing area Position changes or orientation adjustments based on user input can be performed safely. 20 The goal is to enable him / her to do it. Another purpose of the invention is speed limiting, collision avoidance, obstacle detection, safe stopping, Low-speed orientation control, force-limited arm movement, contact detection, tilt detection, Features such as fall detection and safe distance maintenance make it suitable for children, home, classroom and indoor use. It supports security functions. 25 Another purpose of the invention is to create a local artificial intelligence model, a cloud-based artificial intelligence model, or These elements work together in a multi-layered artificial intelligence architecture, enabling natural language processing and voice commands. recognition, speech synthesis, image processing, face detection, object detection, user tracking, capable of performing at least one of the following processes: mood inference and context analysis. The aim is to present a framework for cognitive decision-making and behavior production. 30 Explanation of the Figures To better understand the invention, descriptions of the figures included in the specification are given below. is given: • Figure 1: Front and rear perspective view of the robot's screen-equipped head module. 35 It shows. 3 • Figure 2: Integrated view of the robot's movable arm module and gripper tip. It shows a blown-up appearance. • Figure 3: Front and rear views of the robot's upper body housing structure. It shows. • Figure 4: Front, top, side, and perspective views of the robot's tracked mobile base. 5 It shows. • Figure 5: Shows a general view of the robot from the side, front, back, and top. • Figure 6: The robot's ROS-based software architecture and its top-level control, bottom-level control, sensors, and It shows the functional relationship between servo motor nodes. • Figure 7: Robot hardware architecture and robot microcomputer, microcontrollers, 10 connections between sensors, drivers, motors, display, microphone, camera and speaker It shows. Explanation of References in Figures (1) Head module with screen / head outer body (2) Side head guard or side cover section (3) Side circular sensor, loudspeaker or connecting ring (4) Front face screen / touch face display area 20 (5) Head guidance and neck connection mechanism (6) Rear connection or service opening (7) Upper arm module (8) Arm joint attachment area (9) Forearm module 25 (10) Wrist turning ring (11) Gripper type gripper unit (12) Gripper drive coupling element (13) Pincer fingers (14) Grip surface or contact pad 30 (15) Intermediate joint (16) Cylindrical drive and joint elements (17) Forearm inner mounting socket (18) Gripping parallel linkage mechanism 4 (19) Replaceable clamp contact pad (20) Upper body front guard (21) Shoulder connection slot (22) Side body panel (23) Rear housing of the upper body 5 (24) Lower body connecting foot or connecting projection (25) Tracked mobile base main chassis (26) Palette module (27) Drive / carrier wheel area (28) Upper carrier platform or body seating area 10 (29) Front lighting or front indicator panel (30) Sensor nodes (31) Servo motor nodes (32) Sub-control nodes (33) Brain-inspired cognitive model / upper control nodes 15 (34) Robot microcomputer / main processing unit (35) Camera (36) Microphone (37) 5-inch LCD touchscreen (38) Speaker 20 (39) Servo motors (40) DC motors (41) Servo drive (42) DC motor driver (43) Sensor units 25 (44) Microcontrollers Description of the Invention 1. General System Structure This invention is a multimodal cognitive social robot assistant system for educational and gaming purposes, which interacts with the user. an integrated robot designed for educational, gamified, and social interaction The system includes a platform; a head module with screen (1), movable arm modules (7, 9), and a clamp type 5. gripping tip or gripper unit (11), upper body front guard (20), upper body rear guard (23), tracked mobile base main chassis (25), track modules (26), sensor nodes (30), servo motor nodes (31), lower control nodes (32), brain-inspired cognitive model or upper control nodes (33), The robot will work together with the microcomputer (34), sensor units (43) and microcontrollers (44). It is structured. 10 The system evaluates multimodal data received from the user and the environment to determine the user's location. It can determine attention level, interaction context, educational progress, and play performance. Depending on the defined context, the training content may include a game task, facial expression, verbal response, head orientation, arm movement, At least one of the grasping motion and tracked mobility behaviors is selected and implemented. Thus, the robot only Not as a static educational tool, but as a tool that perceives, decides, responds, and adapts to the user. 15 It functions as a social robot assistant. 2. Mechanical Structure and External Body Design The head module with screen (1), shown in Figure 1, enables the robot to communicate visually with the user. It is the basic interaction unit. Head module (1), side head housing or side cover section (2), side circular module (3), front face display or touch face display area (4), head orientation and neck 20 It may include a coupling mechanism (5) and a rear coupling or service opening (6). The front face display (4) of the robot eyes, mouth, facial expressions, mood, attention focus, speech pattern, or anticipation of a response It is configured to display facial avatar animations showing head and neck orientation. The connection mechanism (5) connects the head module to the user, sound source or interaction context. It enables it to orient itself. 25 The movable arm structure shown in Figure 2; upper arm module (7), arm joint attachment region (8), forearm module (9), wrist turning ring (10), clamp type gripping end or gripper unit (11), gripper drive connecting element (12), clamp fingers (13), gripping surface or contact pad (14), intermediate connecting joint (15), cylindrical drive and joint elements (16), front arm inner linkage socket (17), gripping parallel linkage The lever structure may include a mechanism (18) and a replaceable gripper contact pad (19). This lever structure includes a salute, 30 pointing, showing educational material, orienting towards a play object, holding an object, attracting user attention It is controlled for the purpose of directing or generating social gestures. The upper body structure shown in Figure 3 includes: upper body front guard (20), shoulder attachment slot (21), side body panel (22), upper body rear housing (23) and lower body mounting foot or mounting projection (24) It may include: Upper fuselage front housing (20) and upper fuselage rear housing (23), head module (1), movable 35 It forms a load-bearing and protective outer structure between the shoulder modules (7, 9) and the tracked mobile base (25). Connection sockets (21) enable the movable arm modules to be connected to the body, while the lower body connection foot or connecting projection (24), mechanical integration of the upper body with the tracked mobile base It allows. 6 The tracked mobile base shown in Figure 4; tracked mobile base main chassis (25), track module (26), drive / carrier wheel area (27), upper carrier platform or body seating area (28) and front lighting or may include the front instrument panel (29). Main chassis (25), subcarrier carrying the right and left track modules (26). It forms the structure. The drive / carrier wheel area (27) is the drive or guide that enables the movement of the track. It can accommodate its wheels. The upper carrier platform (28) supports the robot's upper body on a tracked mobile base. It is the area where it is located. Front lighting or front instrument panel (29), direction, status or interaction. It can be used for notification purposes. Figure 5 shows a general view of the robot from the side, front, back, and top. This general view... In view: head module (1), front face display (4), upper arm module (7), forearm module (9), gripper tip (11), upper body front guard (20), upper body rear guard (23), tracked mobile base main chassis (25), track 10 module (26), drive / carrier wheel area (27) and front lighting or front indicator panel (29) together It is located there. The structure in question is compact and low-profile, suitable for children's homes, classrooms, and indoor use. It provides a robot layout with a center of gravity. 3. Multimodal Sensing and Interaction Units The robot’s multimode sensing unit consists of a camera (35), microphone (36), sensor units (43) and associated 15 It collects data from the user and the environment through sensor nodes (30). Sensor units (43), IMU, distance sensor, touch sensor, force sensor, motor feedback sensor, battery status It may include at least one of the sensors or environmental sensing sensors. In a preferential application, the system may include at least one of the following: at least two cameras, at least a four-channel microphone array, at least one speaker, at least six proximity sensors, and at least... It can be configured to work with at least six touch sensors. 20 The camera (35) provides data for user, face, object, motion or environment detection. The microphone (36) provides audio. The command is used for speech or ambient sound detection. Speaker (38), voice response, warning, game sound or outputs speech synthesis. 5-inch LCD touchscreen (37), displays both face avatar animations. It can also provide a user interface. Thus, the robot can utilize visual, auditory, tactile, and motor skills. By using them together, they enable multimodal human-robot interaction. 25 4. Software Architecture and Control Layers The ROS-based software architecture shown in Figure 6 consists of sensor nodes (30), servo motor nodes (31), between lower control nodes (32) and brain-inspired cognitive model or upper control nodes (33) It includes a functional relationship. This architecture layers the processes of perception, decision-making, and motion generation. It executes them. Thus, high-level cognitive decisions and low-level motor control processes are separated from each other by 30 They are separate; however, they are coordinated simultaneously through the flow of data and commands. 4.1. Perception Layer The sensing layer is via sensor nodes (30), camera (35), microphone (36) and sensor units (43) By processing the incoming data, the robot determines its environment and the user's status. Image processing is performed at this layer. Voice command recognition, face detection, object detection, user tracking, touch detection, distance measurement 35 and slope / acceleration assessment can be performed. The data obtained are sent to the lower control nodes (32) and the upper It is sent to control nodes (33) and used for decision making and behavior generation. 7 4.2. Sub-Level Control and Motion Generation Layer Lower control nodes (32) make low-level decisions using data from the perception layer, It performs safe motion generation, motor command generation, and status monitoring processes. servo motor Head guidance mechanism (5), upper arm module (7) via nodes (31), servo motors (39), The forearm module (9), wrist rotation ring (10) and gripper end (11) control the movements. DC 5 The movement commands for the motors (40) are the approach of the tracked mobile base (25, 26, 27) to the user, movements of moving away, following, taking direction, or changing position within the playing field It enables it to be accomplished. 4.3. Higher Control and Cognitive Decision-Making Layer Brain-inspired cognitive models or higher control nodes (33) adapt the user’s interaction context to educational 10 progress, game performance, attention span, preference information, emotional response indicators, and It evaluates the previous interaction history. Based on this evaluation, the behavior generation module provides training. content, game task, asking questions, giving hints, repeating tasks, increasing difficulty level or reduction, giving encouraging feedback, changing facial expressions, generating verbal responses, arm gestures, or You can perform at least one of the mobile behavior selection actions. 15 5. Hardware Architecture and Driver Infrastructure The hardware architecture shown in Figure 7 includes the robot microcomputer or main processing unit (34), camera (35), microphone (36), 5-inch LCD touchscreen (37), speaker (38), servo motors (39), DC motors (40), These may include servo drives (41), DC motor drives (42), sensor units (43) and microcontrollers (44). Robot microcomputer (34), image processing, sound processing, user interface, cognitive decision making and 20 Microcontrollers (44) carry out behavioral production processes. Microcontrollers (44) receive from the robot microcomputer (34). It converts commands into real-time low-level input / output operations. Servo drive (41) drives servo motors (39) to guide arm modules, gripper end and head. It enables the movement of the mechanism. The DC motor driver (42) drives the DC motors (40) of the tracked subsystem. It performs its movement. Sensor units (43) provide safety, contact, distance, incline, motor feedback and 25 This structure transmits information such as battery status to microcontrollers (44) or robot microcomputer (34). Thanks to this, sensing, motor control, and safety operations are coordinated at the hardware level. 6. Education, Games, and Personalized Interaction Process The robot provides the user with educational tasks, mini-games, stories, and question-and-answer sessions for gamified learning purposes. at least 30 activities involving object recognition, following instructions, problem-solving, or interactive learning. It can offer one. User's age group, education level, task achievement, game performance, attention Content and behavior selection is based on the situation, preference information, and previous interaction history. It is adaptable. For example, a hint can be given when the user is struggling, and an encouraging facial expression can be used when they succeed. And audio feedback can be generated, or the game difficulty can be gradually changed. The robot's memory unit contains: username, preference information, training history, game history, previous task results, 35 interaction logs, personalized content history, short-term interaction memory, long-term user profile memory, educational memory, play memory, social interaction memory, or emotional response memory are the most important of these. It can include at least one memory structure. Thanks to this memory structure, the robot can have a friend-like social interaction with the user. It can establish connections, refer to previous interactions, and generate personalized responses. 8 7. Motion Adaptation, Security, and Real-Time Updates The robot's motion control is powered by environmental sensing data and AI-assisted decision-making mechanisms. It can be continuously updated. User location, obstacle distance, and touch are all derived from the sensor layer. The robot's movement strategy is determined by evaluating data such as information, slope / acceleration value, and motor feedback. It is updated. In this context, the robot can follow the user, approach the user, move away from the user, 5 obstacle avoidance, safe stopping or steering maneuvers within safe speed limits. can accomplish it. Safety features include speed limiting, collision avoidance, obstacle detection, safe stopping, and low-speed braking. Orientation control, force-limited arm movement, contact detection, tilt detection, fall detection, and safety. It may include at least one of the following distance maintenance procedures: IMU, distance sensor, touch sensor, force 10 Using data obtained from sensors and motor feedback, the robot's sudden contact, imbalance, and other issues can be identified. It is designed to produce a safe response in situations involving inclines, proximity to obstacles, or limitations of movement. In a preferential application, the robot uses online model updating, reinforcement learning, and Bayesian inference. with at least one of the self-supervised learning or continuing learning approaches the user It can adapt to habits and environmental conditions. These update processes, education and play 15 personalization of behavior, improvement of movement route, appropriate distance for the user It can be used to determine or adapt the difficulty of the task. Learning and updating. Operations, security limits, and content, usage time, and communication limits determined by the authorized user. or is carried out within the limitations of the space available. 8. Operating Modes, Communication and Modularity 20 Depending on the educational, gaming, or social interaction scenarios, the robot can switch between teacher mode, friend mode, and other modes. Features such as guide mode, game companion mode, personal assistant mode, or free chat mode It can operate in at least one of the following modes. Operating modes are parent, teacher, or authorized user. Security, content, usage time, game mode, education level, communication limits, or determined by It can be configured according to movement space constraints. Content is transmitted via wireless communication unit 25 Updates, user profile synchronization, remote monitoring, parent panel connection, teacher panel connection, access to cloud-based artificial intelligence service, or data transfer processes. At least one of them can be accomplished. Thanks to the modular structure of the invention, the camera (35), microphone (36), speaker (38), battery, tracked base (25), arm module (7, 9), gripper tip (11), shielded head module (1), sensor units (43), microcontrollers 30 (44), at least components such as servo driver (41), DC motor driver (42) or robot microcomputer (34) One can be modified, improved, or adapted to different educational, gaming, and social interaction scenarios. adaptable. Application Method in Industry The invention, educational technologies, gamified learning, interactive teaching for children 35 systems, social robotics, personal assistant robots, home and classroom robotics applications, guidance systems, human-robot interaction research, and AI-powered autonomous assistants It can be implemented in systems. The robot provides education for children, students, and individual users. content delivery, game task execution, user tracking, audio and visual response generation, social 9 performing gestures, orienting oneself towards an object, or engaging in interactive learning activities. It can be used for these purposes. Thanks to the modular structure of the invention, the camera (35), microphone (36), speaker (38), battery, tracked base (25), arm module (7, 9), gripper tip (11), head module with screen (1), sensor units (43), microcontrollers (44), servo drive (41), DC motor drive (42) or robot microcomputer 5 At least one of the components such as (34) can be changed, improved or used differently It can be adapted according to different scenarios. Therefore, the invention is suitable for mass production, maintenance and repair, and different applications. Industrially applicable, adaptable to educational / game content and user profiles. It offers a social robot assistant solution.
Claims
REQUESTS 1. The invention is a multimodal cognitive social robot assistant system for educational and play purposes, featuring interaction with the user (5 hours). an educational, gamified, and socially interactive robot body, the robot's At least one tracked mobile base that enables movement indoors, providing the user with visual facial expressions. At least one head module with a screen configured to display, interact with the user through gestures, orientation, or objects. At least one movable arm and / or gripping end configured to enable interaction, from the user and At least one multimodal sensing unit configured to collect data from the environment, and voice communication with the user. and / or at least one interaction unit structured for visual communication, user profile and At least one memory unit that stores the interaction history, based on data received from the sensing unit. At least one cognitive decision-making module that defines the user's interaction context, and the defined interaction. Depending on the context, educational content can include game tasks, facial expressions, verbal responses, arm movements, and mobile behaviors. It must contain at least one behavior generation module that selects at least one of them. 15 2. According to Claim 1, it is a cognitive social robot assistant system, characterized by having at least a multimodal sensing unit. a camera, microphone, proximity sensor, touch sensor, force sensor, inertial measurement unit, motor It consists of a feedback sensor, a battery status sensor, or an environmental sensing sensor.
3. According to Claim 1, it is a cognitive social robot assistant system, and its feature is; a cognitive decision-making module. User's age group, education level, task achievement, game performance, attention span, preference 20 by evaluating at least one of its information, emotional response indicators, or previous interaction history, the robot It is the adaptation of one's behavior.
4. According to Claim 1, it is a cognitive social robot assistant system, and its feature is the behavior generation module. Asking questions, giving hints, or assigning tasks based on the user's educational progress or game performance. repetition, increasing difficulty level, decreasing difficulty level, providing encouraging feedback, or 25 It is the performance of at least one of the processes involved in generating reward behavior.
5. According to claim 1, it is a cognitive social robot assistant system, and its feature is that the robot uses gamified learning. The aim is to provide the user with educational tasks, mini-games, stories, question-and-answer sessions, object recognition, and instruction following. It must offer at least one problem-solving or interactive learning activity.
6. According to Claim 1, it is a cognitive social robot assistant system, the feature of which is; a head module with a screen that acts as the robot's eyes, 30 mouth, facial expressions, mood, attention focus, speech pattern, or anticipation of a response It displays animations.
7. It is a cognitive social robot assistant system according to Claim 1, and its feature is shown in the head module with a screen. The interaction context determined by the cognitive decision-making module of facial expression, user response, Task performance, game performance, user familiarity, or the robot's internal state are all factors that need to be considered. 35 8. According to Claim 1, it is a cognitive social robot assistant system, characterized by its movable arm and / or grasping tip. pointing to the user, greeting, moving towards an object, holding a game object, educational material. This involves controlling actions for the purpose of displaying, generating social gestures, or directing user attention. 11 9. According to Claim 1, it is a cognitive social robot assistant system, and its feature is that the tracked mobile base of the robot approaching the user, moving away from the user, following the user, heading towards a designated location, game at least one of the following actions: changing position within the area or adopting orientation according to the user. its purpose is to enable it to be accomplished.
10. According to Claim 1, it is a cognitive social robot assistant system, the feature of which is; a tracked mobile base for children, home, 5 Suitable for classroom or indoor use, features include speed limiting, collision avoidance, and obstacle detection. at least one of the following functions: safe stop, low-speed directional control, or safe follow. It includes.
11. According to Claim 1, it is a cognitive social robot assistant system, and its feature is that its memory unit contains the user's name. Preferences, educational background, game history, previous task results, interaction records, personalized content 10 history, user habits learned by the robot, short-term interaction memory, long-term user profile memory, educational memory, game memory, social interaction memory, or emotional response memory It is the inclusion of at least one of its memories.
12. According to Claim 1, it is a cognitive social robot assistant system whose feature is that the robot befriends the user. Personality profile, form of address, speaking style, preferences to enable similar social interaction 15 from functions such as remembering, referring to previous interactions, or generating user-specific responses It includes only a few of them.
13. According to Claim 1, it is a cognitive social robot assistant system, and its feature is the cognitive decision-making module. local AI model, cloud-based AI model, or both local and cloud-based AI. It works with a multi-layered artificial intelligence architecture where the models work together. 20 14. According to Claim 1, it is a cognitive social robot assistant system whose features include: robot natural language processing, voice... command recognition, speech synthesis, image processing, face detection, object detection, user tracking, It must perform at least one of the following processes: mood inference or context analysis.
15. According to Claim 1, it is a cognitive social robot assistant system whose features include: robot voice response, on-screen facial expressions, Head orientation, arm movements, and tracked foot movements: at least two of these simultaneously or sequentially for 25 seconds. It is the process of generating a multimodal social response by coordinating in this way.
16. According to Claim 1, it is a cognitive social robot assistant system, and its feature is; robot-user interaction. Force-limited arm movement, contact detection, tilt detection, fall detection are used to ensure safety during the exercise. detection, collision risk detection, obstacle detection, emergency stop or safe distance maintenance It must include at least one of its functions. 30 17. It is a cognitive social robot assistant system according to Claim 1, and its feature is; a cognitive decision-making module. user loss of attention, failed task repetition, negative response, low level of interaction, or help. If it identifies a need, it will adjust the game's difficulty, training content, speaking style, facial expressions, It changes the level of assistance or the robot's movement.
18. According to Claim 1, it is a cognitive social robot assistant system, the feature of which is; the robot's training, play or social 35 Depending on the interaction scenarios, there are teacher mode, friend mode, guide mode, and game partner mode. in at least one of the operating modes such as assistant mode, personal assistant mode or free chat mode It is a study. 12 According to Claim 19, it is a cognitive social robot assistant system, characterized by its modular structure. Thanks to its features, it has a camera, microphone, speaker, battery, tracked base, arm module, gripper tip, and screen. At least one of the head module, sensor module or processor module can be modified, upgraded or Its adaptability to different usage scenarios is a key advantage.
20. According to Claim 1, it is a cognitive social robot assistant system, and its feature is; the robot's wireless communication 5 Content updates via the unit, user profile synchronization, remote monitoring, parental control panel. connection, teacher panel connection, cloud-based AI service access or usage data It is the performance of at least one of the transfer operations.
21. According to Claim 1, it is a cognitive social robot assistant system, the feature of which is that the robot acts as a parent, teacher or Security, content, usage time, game mode, education level, determined by the authorized user, 10 It must operate according to at least one of the following: communication limitations or movement restrictions.
22. According to Claim 1, it is a cognitive social robot assistant system whose feature is that the robot interacts safely with children. Compact body form with no sharp edges for interaction, low center of gravity, closed track. its structure consists of movable mechanisms or softened external surface structures with limited external access. It must include at least one of them. 15 23. According to Claim 1, it is a cognitive social robot assistant system, characterized by its tracked mobile robot body. a compact upper body positioned on the base, and a screened head attached to that upper body. integrated system consisting of a module and movable arm modules positioned on either side of the upper body It involves a mechanical system.
24. According to Claim 1, it is a cognitive social robot assistant system, the feature of which is that the robot body is tracked mobile 20 sliding forward on a spring-shaped or curved slide mechanism located on the upper part of the base The robot's body can be tilted forward in a controlled manner relative to the tracked mobile base.
25. According to claim 24, it is a cognitive social robot assistant system, and its feature is a curved or arc-shaped slide. its mechanism will keep the center of gravity of the robot body within the contact area of the tracked mobile base. The design is such that it reduces the risk of the robot tipping over during the forward leaning movement. 25 26. According to Claim 1, it is a cognitive social robot assistant system, characterized by its movable arm modules. one of them must have at least five degrees of freedom and be intended for object gripping at the end. It includes a structured clamp-type gripper.
27. It is a cognitive social robot assistant system according to Claim 1, and its feature is that the head module with screen moves to the right and left. a rotating head steering mechanism, a touchscreen approximately 5 inches in size, and the aforementioned 30 It includes a display unit that shows face avatar animations on the touchscreen. According to Claim 28, 1, it is a cognitive social robot assistant system with the feature of multimodal sensing and interaction. The unit must have at least two cameras, at least a four-channel microphone array, at least one speaker, and at least six ranges. It includes a sensor and at least six touch sensors. 35