21 results about "Domestic robot" patented technology

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 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.

The invention discloses an automatic grabbing method based on a 3D hand-eye system and a five-finger dexterous hand. The automatic grabbing method comprises the following steps that S100, automatic hand-eye calibration is conducted on the 3D hand-eye system; s200, collecting a video stream by a camera of the RGB camera, detecting a to-be-grabbed object, and calculating a central point coordinate; s300, performing visual angle full conversion on a depth image output by the IR structured light depth camera, and calculating a space coordinate and an estimated size under an object camera coordinate system in combination with an RGB detection center point coordinate; s400, the space coordinate position under the camera coordinate system is firstly converted to be under the five-finger dexterous hand grabbing coordinate system and then converted to be under the mechanical arm base coordinate system; and S500, the detected object is grabbed through the five-finger dexterous hand. The method can be widely applied to multiple fields of intelligent warehousing, automatic production lines, household robots, unmanned distribution and the like, the operation efficiency is greatly improved, and the labor cost is reduced.

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.

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.

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.

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.

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.

This utility model relates to the field of home robot technology and discloses a home robot that facilitates the placement of items. It includes a device housing, with an air pump fixedly connected to the rear end of the housing. A four-way pipe is fixedly connected to the drive end of the air pump, and output air pipes are fixedly connected to the output ends of the four-way pipe. A fixed shell is connected to the input end of the output air pipes via an adjustment assembly. A sliding shell is slidably connected to the inner wall of the fixed shell. A bellows is fixedly connected to the bottom rear end of the housing, and a circulating fan is installed on the inner wall of the bellows. An exhaust trough is connected to the top of the bellows via a drying assembly. A controller is installed at the front end of the housing. In this utility model, the drive slides 2 and 1 achieve precise multi-axial movement, significantly improving the efficiency of item storage and retrieval, enabling intelligent operation, and ensuring that hot air evenly covers the storage space, quickly reducing the moisture content of clothing and inhibiting mold growth.

The invention discloses a miniaturized three-frequency antenna for a home service robot. The antenna comprises a dielectric substrate, and a metal ground plane, a coplanar waveguide feeder line and a metal radiation unit which are arranged on the same surface of the dielectric substrate, wherein the edge, close to the metal radiation unit, of the metal ground plane is of a stepped structure. The metal radiation unit is integrally formed by a butterfly radiation structure and a split-ring resonator structure through a connection structure. The butterfly-shaped radiation structure is used for exciting broadband 2.4 GHz low-frequency resonance, and the split-ring resonator structure excites 3.5 GHz and 5.8 GHz high-frequency resonance through coupled feed. The unique gap between the stepped ground plane and the butterfly radiation structure synergistically realizes good impedance matching of three frequency bands. The antenna is compact in structure and has broadband performance in the 2.4 GHz frequency band, the radiation pattern of each frequency band has good omni-directivity, and the multi-frequency-band wireless communication requirement of a home robot in a complex indoor environment is met.

The invention provides a method and system for operating a target object by a home robot, and belongs to the technical field of artificial intelligence, and the method comprises the steps: in response to an operation instruction, recognizing the target object from a home environment according to a pre-generated template of the target object, and executing an operation corresponding to the operation instruction on the target object; wherein the step of generating the template of the target object comprises the steps of entering a teaching mode, and obtaining interaction data sent to the home robot by a user and image data of the user; determining the name of the target object according to the interaction data, and determining the image feature vector of the target object according to the user posture in the image data; and generating a template of the target object according to the name and the image feature vector of the target object. The user only needs to send the interaction data to the home robot, and the home robot can automatically generate the template of the target object according to the interaction data and the image data of the user, so that the target object can be identified from the home environment and operated, the operation is simple, and the use threshold is low.

1. Name of the design product: Household robot. 2. Use of the design product: The design product is used for household intelligent robot. 3. Design points of the design product: In shape. 4. Pictures or photos best indicating the design points: Perspective view.

The present invention relates to a home robot system for providing customized services and, more specifically, to a home robot system for providing customized services that offers a variety of functions to assist a user's life, such as air purification, fire prevention, and intrusion protection, and provides an experience to the user in which the robot extracts the center point of the user's face from an image captured by a camera, adjusts the position thereof such that the center point of the captured image aligns with the center point of the user's face, and thereby allows the robot to autonomously move to a position facing the user, thus enabling a home automation system with enhanced emotional interaction with the user.

This application provides a method for generating household robot actions based on ChatGPT interaction and ontology knowledge. It uses ChatGPT's natural language processing capabilities to infer the task target state. Through the provided hybrid reasoning and verification mechanism, the household robot can still quickly complete accurate target instance reasoning in complex household scenarios, solving the problem of target instance inability to identify or fuzzy identification in traditional methods; and can independently construct a small and high-precision ontology knowledge base to guide task planning and execution based on the task to be performed. It improves the efficiency of household robots in utilizing prior knowledge and the intelligence level of the robot itself. This application also provides a household robot action generation system based on ChatGPT interaction and ontology knowledge.

The home robot of this embodiment includes: a mobile unit for driving; a camera for capturing images; and a control unit for controlling the mobile unit and the camera. The control unit can control the user information for image capture to be registered, and set image capture conditions based on the individual and scene respectively. The mobile unit moves within a specified area and determines whether the image capture conditions based on the individual and scene are met. If the image capture conditions based on the individual and scene are met, the camera captures an image.

The invention relates to the technical field of cleaning accessories, and provides a pipeline switching and reversing mechanism and a domestic robot system.The pipeline switching and reversing mechanism comprises a pipeline assembly and a switching assembly, and the pipeline assembly comprises a first liquid inlet pipe, a second liquid inlet pipe, a first liquid discharging pipe and a second liquid discharging pipe; the switching assembly is provided with a first pressure applying part and a second pressure applying part, and the first pressure applying part is used for periodically extruding the first liquid inlet pipe and the first liquid outlet pipe so as to realize periodic alternate connection and disconnection of the first liquid inlet pipe and the first liquid outlet pipe; and the second pressure applying part is used for periodically extruding the second liquid inlet pipe and the second liquid outlet pipe so as to realize periodic alternate connection and disconnection of the second liquid inlet pipe and the second liquid outlet pipe. According to the pipeline switching reversing structure provided by the invention, the overall switching logic is simpler, the on-off of each pipe body of the pipeline assembly is realized by adopting an extrusion mode, and compared with the on-off of a traditional electromagnetic valve, the probability of valve body liquid leakage caused by high temperature and impurities is lower.

The invention is suitable for the technical field of household cleaning, and provides a self-cleaning technology evaluation method and system based on a household robot, and the method comprises the steps: obtaining household equipment information, and obtaining three-dimensional modeling information; analyzing according to the micro biosensing information, comparing an analysis result with a safety threshold value, and carrying out differential calculation on an initial value and a final value; updating three-dimensional modeling information according to the periodically scanned data, performing trend analysis on pollution generation frequency of each region according to a cleaning historical record, and performing re-analysis on the processed target region; the emotional tendency is judged according to the semantic protector, the facial emotional state and the limb behavior are analyzed according to the expression behavior, and the execution deviation in the task process is accurately recognized according to the recognizable label, so that the problem that an existing household robot cannot comprehensively analyze the clean area during self-cleaning, and the cleaning efficiency is poor is solved. The problems that different areas of a family cannot be divided into different areas, and different levels of processing cannot be carried out on the cleaning frequencies of the different areas are solved.

The present application relates to system for control of position of a robotic land vehicle for evacuation operation. More particularly, the present invention relates to a navigation and indoor positioning system for an accident response home bot using received signal strength indicator to locate and evacuate a distressed person during accident. The navigation and indoor positioning system for an accident response home bot utilizes a trilateration system to locate the person where an accident response home bot will fetch and escort the person to a safe location.

1. Name of the designed product: Household robot. 2. Use of the designed product: The designed product is used for managing household affairs. 3. Design points of the designed product: In shape. 4. Picture or photo best indicating the design points: Perspective view.