89 results about "Home robot" patented technology

The invention discloses a visual question and answer method based on environmental perception and a knowledge base, and aims to realize an accurate visual question and answer function through a reasoning technology of integrating field specific environmental information and knowledge base information. The method comprises the following steps: firstly, extracting image features by utilizing a ResNet model in visual feature extraction, extracting text features by utilizing a BERT model in text feature extraction, and comprehensively processing the features and context information acquired by an environment perception module through multi-modal fusion; and then, on the basis of the fused multi-modal features, through combination of a Wikdata knowledge base and Seq2Seq, an answer is output in a text form, and visual feedback can be provided. Through environment perception, the system can adjust answers in real time to ensure that the system highly adapts to the current scene, and is applied to the fields of intelligent assistants, aided driving, household robots and the like.

The invention discloses a map construction method of a body-equipped robot control system, a body-equipped robot and a medium. The method comprises the following steps: acquiring 3D point cloud data and a first environment image acquired when the body-equipped robot moves in a home environment; acquiring a second environment image acquired by a camera in the home environment; constructing a target three-dimensional home map according to the 3D point cloud data, the first environment image and the second environment image; and determining that the posture of the target object is changed according to a second posture of the target object in the target three-dimensional home map at the current moment and a third posture of the target object in the target three-dimensional home map at the previous moment. And dynamically recording the pose change of the target object from the third pose to the second pose in the target three-dimensional home map according to the time to obtain a target four-dimensional home map. According to the method, the four-dimensional home map is generated according to the pose changes of the object in the three-dimensional home map at different moments, and the intelligent control degree of the home robot is improved.

The invention provides a home robot action generation method based on the Re-Plan principle, and belongs to the technical field of robots. According to the invention, a dynamic gating fusion network is designed to improve the multi-mode sensing efficiency of the home service robot, and a joint space-time security optimization mechanism is introduced to improve the quality of multi-mode feature fusion; on the basis of a HomeAct-1. 2k data set in combination with a curriculum learning strategy, lightweight fine tuning of a Qwen-VL-Chat model is completed, an action generation framework based on the Re-Plan principle is designed on the basis of the model, and the task execution capacity of the home service robot in complex tasks is effectively improved.

The invention discloses a household robot AI algorithm model synchronization method, device and equipment and a storage medium, which are used for solving the problem that upgrading of an existing household robot AI algorithm model depends on manual operation and a centralized management strategy and is difficult to meet large-scale, high-efficiency and automatic upgrading requirements. The method comprises the following steps: acquiring position information of the domestic robot; receiving equipment information, an operation state and current home environment information sent by the home robot; judging the equipment state of the household robot according to the position information; matching a plurality of target AI algorithm models in a preset AI algorithm library according to the equipment state, the equipment information, the running state and the current home environment information; and synchronizing the target AI algorithm model to the household robot.

The invention relates to the field of visual analysis, in particular to a visual analysis method for a domestic robot. The method comprises the following steps: acquiring a real-time following image, and determining real-time behavior information and home environment information according to the real-time following image; acquiring following information, and determining abnormal following information according to the real-time behavior information, the following information and the home environment information; and adjusting the following information according to the abnormal following information and the real-time following image, determining real-time following information, and following the family members according to the real-time following information. According to the method, the real-time following information is determined by acquiring the following image in real time and accurately identifying and analyzing the behavior information and the environment condition of the family members. By comparing the real-time behavior information with the home environment, an abnormal following condition is detected, so that the following path and behavior are optimized. The adjusted following information ensures that the robot more intelligently adapts to the activities of the family members, the home automation experience is improved, and the safety of the family members is enhanced.

The utility model provides a kind of protection charging system of robot charging pile, it is related to robot charging technical field, system includes charging end, signal sampling end, power supply unit, monitoring unit, main control unit. By introducing monitoring unit detection robot ontology and the on-off between monitoring contact on charging pile, generating on signal or disconnect signal and send to main control unit, main control unit controls the power supply unit in charging pile and powers on output charging voltage and current according to on signal or disconnect signal and charges or disconnects power supply and stops charging, so that robot can automatically turn off power after leaving charging pile, avoid the charging electrode piece of charging pile long time conduction, even if human press charging contact on charging pile also cannot trigger power supply, can prevent electric shock, guarantee the safety of robot charging pile, especially suitable for domestic robot, can avoid domestic child mis-trigger or naughty active trigger and lead to electric shock.

This invention discloses a multifunctional home robot, comprising: a robot body; a central control system disposed on the robot body, the central control system being configured to perform multimodal data fusion and intelligent decision-making; a multimodal sensing unit electrically connected to the central control system for collecting user physiological data, behavioral data, and environmental data; and a life-assistance execution unit connected to the central control system for performing various operational tasks in the home environment according to instructions from the central control system. This multifunctional home robot solves the problem of single-function home service devices by introducing a dual-core architecture of a "life-assistance execution unit" and an "adaptive physiotherapy execution unit." The robot can not only perform household chores such as floor cleaning and tidying up, but also provide professional physiotherapy services. More importantly, the central control system enables the scenario-based linkage between the two.

An autonomously moving robot (100) for a household (105), wherein the robot (100) comprises: - a sensor (120) for scanning the household (105) in the vicinity of the robot (100); - a processing device (115) for determining an occupancy grid (135) based on the scanning; - wherein the occupancy grid (135) comprises a plurality of cells (140); - wherein a cell (140) represents a section of the household (105); - wherein for the cell (140) the logit of an occupancy by an object (110) is specified; - wherein the logit is the natural logarithm of a chance that the cell (140) is occupied by an object (110); - wherein the chance comprises a probability of occupancy divided by a probability of the cell (140) not being occupied;- wherein the processing device (115) is configured to control the movement of the robot (100) in the household (105) such that a section whose associated cell (140) has a logit exceeding a predetermined threshold is not entered; - further comprising a communication device for receiving another occupancy grid (135) from another robot (100) in the household (105); wherein the processing device (115) is configured to integrate the further occupancy grid (135) into the existing one by adding the logit values ​​of corresponding cells (140) respectively.;

The application provides an AI-based surgical instrument counting and homing robot, and relates to the technical field of robots, and comprises a placing table, a placing plate is slidably installed on the top of the placing table, a rotating assembly is arranged on the outer side of the placing table, four mechanical arm assemblies are installed on the rotating assembly in four directions, and a moving assembly is arranged at the bottom of the rotating assembly. The surgical instruments are installed and classified on the placing plate, the placing plate is placed on the top of the placing table, and through cooperation of the moving assembly and the rotating assembly, four sets of mechanical arm assemblies can be alternately corresponded to the placing table and connected with the identification assembly. Then, the identification assembly is driven to move along the top of the placing table, the surgical instruments are identified, and after reaching the position of the instruments to be taken out, the instruments are clamped and taken out by the mechanical arm assemblies. After use, the mechanical arm assemblies are sent back to the original path on the placing table, the instruments are positioned and homed, and disorder is avoided.

The present application relates to the field of robots, and discloses a smart home robot and its task execution method and storage medium, the method comprising: responding to task instructions to obtain multiple images collected by various cameras at the same time; for images with target objects, obtaining depth information of the target objects in the images to calculate the initial pose of the target objects in the associated camera coordinate system; obtaining multiple transformed poses of the target objects in the three-dimensional map according to the initial pose of the target objects and the pose of the associated cameras in the three-dimensional map; for each transformed pose, determining the corresponding pose weight according to the depth information and the initial pose; performing pose weighted average calculation according to each transformed pose and the associated pose weight to obtain the adjusted pose of the target object; and controlling the smart home robot to perform the target task according to the adjusted pose. The present application uses data from multiple external cameras to identify and locate objects, so that the robot can perform tasks more flexibly and accurately.

The invention discloses a household robot article searching method and system based on a multi-source pre-built map, and the method comprises the following steps: S1, controlling a household robot to move in a household scene through employing an autonomous synchronous positioning and mapping technology, obtaining environment data obtained by a multi-source sensor carried by the household robot, and storing the environment data in a database; constructing an environment map fusing the ground occupation information and the overlook visual information, wherein the environment map is used as a multi-source pre-established map for subsequent article search; s2, calculating three types of scores of each landmark in the home scene; calculating the comprehensive score of each landmark according to the three types of scores of each landmark, and selecting the first K landmarks with the highest comprehensive score to construct an associated landmark set; and S3, in combination with the multi-source pre-established map and the associated landmark set, constructing a high-low layer collaborative target exploration mechanism, and realizing layer-by-layer reasoning from region planning to action execution. According to the method, the semantic reasoning result is accurately sent to the ground, the actual navigation behavior is driven, and the accuracy of target positioning and the efficiency of path planning are improved.

The invention relates to a method for determining a movement path (130) along which a mobile device (100), in particular a robot, preferably a domestic robot or vacuum cleaner robot, is to move in a surrounding area (120), having the steps of: providing obstacle information which comprises information about the position of an obstacle (140, 1422, 144, 146) that can be overcome by the mobile device, said obstacle information having been determined on the basis of sensor information (202) which has been captured by means of at least one sensor (106) of the mobile device; checking whether additional information relating to the process of overcoming obstacles is available; if additional information is available: determining the movement path on the basis of the additional information; and providing the movement path or information relating to the movement path, in particular in order to navigate the mobile device.

Implementations of a fully configurable, modularized home robot are described that implement trained neural network classifiers to solve problems of providing home health care and monitoring of the elderly and / or infirm, providing entertainment for the family, providing environmental and safety monitoring coupled with mechanisms to clean the air and remedy indoor climates such as humidity and temperature, and provide a mechanism for caring for pets left at home when the owner is away based upon sensory input.

The invention discloses an unknown environment-oriented household robot article searching method and system, and belongs to the technical field of robots. The method comprises the following steps: constructing a multi-dimensional map comprising a semantic map, a historical track map and a visual correlation map; evaluating and determining an optimal leading-edge exploration point based on a perception-prior-behavior multi-dimensional scoring mechanism; carrying out local path planning by using a fast marching method, and generating a navigation action to realize autonomous navigation; and judging the existence of the target object through a dual verification mechanism combining semantics and vision. According to the system, by fusing a multi-dimensional map and a multi-dimensional scoring strategy, the efficiency, the success rate and the intelligent level of article search of the robot in an unknown home environment are remarkably improved.

The application provides a household robot voice calling navigation method, comprising: collecting voice calling information of an instruction person; analyzing the voice calling information to predict a preliminary position of the instruction person; navigating to the preliminary position of the instruction person; predicting the instruction person through event recognition; and navigating to an actual position of the instruction person. The household robot voice calling navigation method can accurately identify the instruction person from multiple family members and navigate to the actual position of the instruction person even if there is loss in the voice calling information collection, thereby improving the success rate and accuracy of the household robot voice calling navigation.

1. The name of the design product: home robot. 2. The use of the design product: for smart home security and smart voice communication. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The application relates to the field of somatic household robot communication and control, in particular to a wireless data processing method and device for a somatic household robot and a robot. In view of the problems that in existing robot communication, full-amount transmission of bus data leads to heavy burden of a wireless link, key data is difficult to be delivered in time, real-time performance and resource utilization are insufficient, a processing scheme is provided, in which intelligent forwarders collect communication total data on the robot side, and switch between full-amount forwarding and semantic filtering according to the state of the collected data; when semantic filtering, preset key data is extracted and sent to a target functional module. The scheme can reduce the occupation of wireless bandwidth by invalid or low-value data, improve the timeliness and reliability of key control and state information transmission, and enhance the communication flexibility and overall control efficiency in a dynamic deployment scene.

The invention relates to the technical field of robot chassis, in particular to a wheel type chassis of a small domestic robot, which comprises a chassis, and three U-shaped frames are mounted on the upper surface of the chassis; symmetrically arranged connecting shafts are fixed between the U-shaped frame and the chassis; the outer side wall of the connecting shaft is sleeved with a spring. The diameter of the chassis is only 450 mm, the chassis adapts to the narrow space of a family, the three U-shaped frames are distributed in a regular triangle mode and matched with a high-strength material, the maximum bearing capacity of the chassis reaches 240 kg, various household robot operation modules can be carried, the use scene is expanded, springs and shaft sleeves on the outer sides of connecting shafts form a composite vibration reduction structure, and the omnidirectional wheels can flexibly move along the Z axis; vibration caused by household ground protrusions and joints is effectively absorbed, the vibration is prevented from being transmitted to the robot body, and the operation stability of equipment is improved.

We provide the system. [Solution] An information processing system that enables conversation with a specific character, A means for receiving character selection from a user device and transmitting it to an information processing device, A means of obtaining the latest information from external sources, adjusting the information based on individual characteristics, and associating it with characters, A means for analyzing a message received from a user, generating a character-appropriate response based on its content, and outputting the generated response as audio, A means of providing responses through home robots and supporting the user's daily life, A system that includes this.

The utility model discloses a walking device which comprises a motor bin and two driving wheel sets, the two driving wheel sets are arranged on the left side and the right side of the motor bin respectively, each driving wheel set comprises a first driving wheel and a second driving wheel, the two first driving wheels are arranged diagonally, and the two second driving wheels are arranged diagonally; wherein a motor is arranged in the motor bin, an output shaft of the motor extends out of the motor bin and is detachably connected with the first driving wheel and the second driving wheel, and the diameter of the output shaft connected with the first driving wheel is smaller than that of the output shaft connected with the second driving wheel. Correspondingly, the utility model further discloses a movable household robot which comprises a shell and the walking device, and the walking device is detachably arranged at the bottom end of the shell. The walking device is simple in structure, low in cost, high in detachability and convenient to clean subsequently.

This application belongs to the field of home robot technology, and proposes a home robot control method, a home robot, a control system, and a storage medium. This method solves the problem of low reliability in handling emergencies and susceptibility to mishandling in traditional home robots due to the lack of intelligent control methods. The method includes acquiring environmental information of the home robot's surrounding environment; identifying the environmental information and determining the target control operation based on the identification result; if the target control operation is a first-type control operation, the home robot automatically executes the target control operation; if the target control operation is a second-type control operation, the home robot sends an execution request for the target control operation to a cooperating remote control device, and executes the target control operation after receiving a response message from the remote control device instructing the execution of the target control operation.

This invention discloses a home intelligent guardian robot and its intelligent detection and obstacle avoidance method, relating to the field of intelligent home robot technology. The robot includes two sets of symmetrically arranged support arms. The inner sides of the two sets of support arms are rotatably connected to both ends of a connecting rod, and the middle of the connecting rod is rotatably connected to the outer wall of the main unit. Mecanum wheels are fixedly mounted at the bottom end of each set of support arms. An auxiliary functional unit is fixedly arranged on the outer side of the main unit, and an AI intelligent gimbal is fixedly mounted on the outer wall of the main unit or the auxiliary functional unit. This invention features an ingenious robot design, deeply integrating mechanical structure, protection, functional expansion, and intelligent perception to adapt to the home environment. Its intelligent detection and obstacle avoidance method allows the robot to autonomously perceive, identify, and make operational decisions, enhancing home security response capabilities, ensuring smooth movement, improving intelligence, safety, and convenience, and meeting daily family needs.

The invention describes a device (101) for a domestic robot (100), which is designed to interact with a domestic appliance (110). The device (101) is set up to determine position information in relation to N different reference points of the domestic appliance (110), where N ≥ 1, in particular where N ≥ 2, wherein the position information indicates the spatial position of the N different reference points relative to the domestic appliance (110). Furthermore, the device(101) is set up to determine, on the basis of sensor data from one or more sensors (102, 105) of the domestic robot (100), measurement information in relation to the N different reference points of the domestic appliance (110), wherein the measurement information indicates the spatial position of the N different reference points relative to the reference coordinate system of the domestic robot (100). The device (101) is also set up to determine position information in relation to the spatial position of the domestic appliance (110) within the reference coordinate system on the basis of the position information and on the basis of the measurement information.

1. Name of the product of this design: Multifunctional home robot (X-Companion). 2. Purpose of the product of this design: A robot used for intelligent home care, with functions such as emotional interaction, medication reminders, night lighting, intelligent voice interaction, and the ability to expand these functions modularly. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: Stereoscopic drawing 1.

The invention discloses a household cleaning robot, and belongs to the technical field of household robots, the household cleaning robot comprises a collecting box, the collecting box comprises a main body, a side opening is formed in the vertical side wall of the main body, a bottom opening is formed in the bottom surface of the main body, and a filter element is arranged on the side, opposite to the side opening, of the main body. Through the arrangement of the collecting box, the sweeper, the converter, the mopping cleaner and the shell, when the bottom surface, the carpet and the junction of the ground and the carpet are cleaned, the converter can change the source position of airflow entering the collecting box, and areas with different negative pressure degrees are generated at different positions below the shell; the edge of the carpet can be intensively sucked and swept by utilizing larger negative pressure suction force, the edge of the carpet is lifted, and dead corners at the junction of the carpet and the ground are thoroughly cleaned by matching with the turntable capable of swinging to cross the center line of the shell.

The invention relates to a domestic dishwasher (1) having a washing container (2) for receiving washing items, an open-loop and closed-loop control device (15) for carrying out a washing program (27) for cleaning the washing items, and a domestic robot (16), the open-loop and closed-loop control device (15) being designed to interrupt the washing program during the execution of the washing program (27), in this way, the domestic robot (16) can interfere with the flushing container (2).

A method for determining a motion path on a surface in an environment, along which motion path a mobile appliance, in particular a robot, preferably a domestic robot or a robot vacuum cleaner, is intended to move. The method includes obtaining environment information and determining a region of the surface intended to be covered by the motion of the mobile appliance; determining, while taking into account the environment information, whether within the region there is at least one uneven area in the surface that can be negotiated by the mobile appliance; and determining the motion path while taking into account the at least one uneven area, if there is one. A mobile appliance is also described.

A simulation system for household robot tasks and data collection, comprising: a data collection module, a Unity module, a Python module, a communication module, a VR module and a resource file module. The present invention can support a variety of object attributes, an interactive simulation system for household robot tasks, and the system can support data acquisition for deep learning training, thereby reducing the cost of data annotation.

The invention discloses a home robot intelligent behavior recognition and control method based on deep learning, and relates to the technical field of home robots. Comprising the following steps: data acquisition: acquiring marked and unmarked video information; feature extraction: dividing a sample sequence, and performing feature extraction on the sample sequence to obtain a sequence feature vector; vector fusion: fusing the second sequence feature vectors to obtain a fusion vector; similarity calculation: respectively solving an average feature vector for a plurality of first sequence feature vectors corresponding to different behavior features, respectively calculating similarities with the fusion vector, and judging the behavior features according to the similarities; and behavior control: starting a preset control program according to the recognition of the behavior characteristics. In the feature extraction process, feature extraction can be carried out on feature changes between subsequent continuous frame pictures, the accuracy of representing continuous behavior features by sequence feature vectors is improved, and therefore the accuracy of behavior recognition is improved.

The invention provides a modular household robot, and belongs to the technical field of robots, the modular household robot comprises a cleaning mechanism, a main body mechanism, a moving mechanism and an auxiliary mechanism, when the modular household robot is used, a pushing block is driven by a driving assembly II to move towards the outside of a mounting cavity II, and a through hole of a connecting plate is aligned with an opening of the mounting cavity II; a second driving assembly drives a pushing block to penetrate through a through hole of a connecting plate to jack up a bonding strip, meanwhile, due to the fact that one end of the bonding strip is fixedly connected with a fixing strip, and the bonding strip can be pushed towards the outer side of the device in cooperation with a rotating cleaning mop, the bonding strip makes contact with the cleaning mop, and due to the characteristics of acrylic acid glue, the cleaning mop can be cleaned conveniently. The bonding layer on the bonding strip can effectively adsorb fine sundries such as hair, dust particles and the like which are difficult to clean in the cleaning process of the cleaning mop, when the cleaning mop rotates, the cleaning mop is in continuous friction contact with the bonding strip, the hair attached to the surface of the cleaning mop can be bonded by the bonding layer, and therefore the cleaning effect of the cleaning mop is further improved.