Intelligent companion robot

Abstract

The present invention provides an intelligent pet companion robot, comprising: a chassis and a body; a mobile device is installed on the chassis; a rotatable camera, a laser radar and a two-way communication speaker are arranged on the outside of the body, the camera is used to collect image data, and the laser radar is used to collect radar data; a processor and a wireless communication module are arranged inside the body; the wireless communication module is used to send image data and / or audio data to the client of the intelligent pet companion robot; the two-way communication speaker is used to implement intercom; the processor is used to generate a two-dimensional map according to the radar data, and use the Monte Carlo algorithm to determine the current position of the intelligent pet companion robot; use the A‑star algorithm to perform global path planning based on the two-dimensional map to generate a moving path; and control the mobile device to move the intelligent pet companion robot to the vicinity of the pet according to the moving path. The intelligent pet companion robot provided by the present invention can better realize the monitoring of pets when the owner is not at home.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of robotics technology, and in particular to an intelligent pet companion robot. Background Art

[0002] Keeping pets can not only alleviate people's loneliness and make them feel accompanied, but also give them a sense of accomplishment and happiness from taking care of pets. As residents' income continues to increase and the pace of life continues to accelerate, more and more people are keeping pets. Pets can accompany humans, but they also need human care. For office workers or pet owners who often have short business trips, it is difficult to take good care of pets. Therefore, pet companion robots that help owners take care of pets when they are away from home are gradually entering the market.

[0003] The pet companion robot disclosed in the Chinese patent application with publication number CN112775979A and invention name "Control method of pet companion robot, pet companion robot and chip" uses an infrared temperature detection sensor to scan a circular area with the pet companion robot as the center and the scanning distance of the infrared temperature detection sensor as the radius. The circular area is the preset area. The preset area is scanned in real time by the infrared temperature detection sensor, and the scanning result is obtained; when the scanning result meets the preset conditions: there is a movable object; when an object with a temperature within a preset range is detected, it is determined that a pet is detected in the preset area, and then the pet is fed. However, since the preset area scanned by the infrared temperature detection sensor is limited, if the pet is not in the preset area, it is difficult to achieve intelligent monitoring of the pet. Summary of the invention

[0004] The embodiment of the present invention provides an intelligent pet companion robot for better monitoring the pet when the owner is not at home.

[0005] The embodiment of the present invention provides an intelligent pet companion robot, comprising: a chassis and a body, wherein the chassis is used to carry the body;

[0006] The chassis is equipped with a moving device for moving the intelligent pet companion robot;

[0007] A rotatable camera, a laser radar and a two-way communication speaker are arranged outside the body. The camera is used to collect image data, the laser radar is used to collect radar data, and the two-way communication speaker includes a pickup and a microphone;

[0008] A processor and a wireless communication module are arranged inside the machine body, and the camera, laser radar, two-way communication speaker and the wireless communication module are all connected to the processor;

[0009] The wireless communication module is used to send the image data collected by the camera and / or the audio data collected by the microphone to the client of the intelligent pet companion robot;

[0010] The two-way communication speaker is used to realize intercom between users and pets;

[0011] The processor is used to:

[0012] The Gmapping algorithm is used to generate a two-dimensional map based on the received radar data, and the Monte Carlo algorithm is used to determine the current position of the intelligent companion robot;

[0013] When a pet is identified within camera range based on image data received from the sensor, the current location of the pet is determined;

[0014] The current position of the intelligent companion robot is taken as the starting point, and the current position of the pet is taken as the target end point. The A-star algorithm is used to perform global path planning based on the two-dimensional map to generate a moving path.

[0015] The mobile device is controlled to move the intelligent pet companion robot according to the moving path, so as to move the intelligent pet companion robot to the vicinity of the pet.

[0016] In one embodiment, the processor is further configured to:

[0017] When it is determined that the pet is not within the camera range according to the image data received from the sensor, in response to the received pet-finding instruction, the microphone is controlled to collect audio data of the pet;

[0018] A generalized cross-correlation-phase transform algorithm is used to determine the direction of arrival and the distance based on the audio data, and the current position of the pet is determined based on the determined direction of arrival and the distance.

[0019] In one embodiment, the processor is further configured to:

[0020] The microphone is controlled to play a pre-recorded voice signal of the pet owner or a voice signal of the pet owner in a real-time voice call to guide the pet to make a sound or approach the intelligent pet companion robot.

[0021] In one embodiment, the processor is further configured to:

[0022] When it is determined that the pet is not within the camera range based on the image data received from the sensor, a full coverage path planning algorithm is used to traverse all areas on the two-dimensional map except for obstacles;

[0023] During the traversal process, the image data collected by the camera is recognized and processed in real time;

[0024] If a pet is identified, the traversal is stopped, the current location of the pet is determined, and the current location and current time of the pet are marked in the two-dimensional map.

[0025] In one embodiment, the processor is further configured to:

[0026] Generate a probability distribution diagram of the pet's location in each time period based on the pet's locations and corresponding times marked during multiple traversals;

[0027] When a pet-finding instruction is received, each location in the time period corresponding to the current time is determined as the target destination in order of probability according to the probability distribution diagram, and navigation is performed.

[0028] In one embodiment, a display device is installed outside the body for displaying a pre-recorded video signal of the pet owner or a video signal of the pet owner in a real-time video call.

[0029] In one embodiment, a horizontally rotating universal head is provided on the top of the body, and the camera is connected to the universal head.

[0030] In one embodiment, the moving device includes four steering wheels and four driving wheels, and the bottoms of the driving wheels are arranged at the same height to achieve omnidirectional movement.

[0031] In one embodiment, the machine body is provided with a grain storage device for storing pet food; a grain storage self-locking button is provided on the top of the machine body for controlling the ejection and retraction of the grain storage device.

[0032] In one embodiment, a food bowl is provided at the bottom of the chassis, and the food bowl is extendably connected to the chassis; the food bowl and the food storage device can be connected; in response to a food release instruction, a predetermined amount of pet food is put into the food bowl from the food storage device, and the food bowl is extended.

[0033] The intelligent pet companion robot provided by the embodiment of the present invention includes: a chassis and a body, the chassis is used to carry the body; the chassis is installed with a moving device for realizing the movement of the intelligent pet companion robot; a rotatable camera, a laser radar and a two-way communication speaker are arranged on the outside of the body, the camera is used to collect image data, the laser radar is used to collect radar data, and the two-way communication speaker includes a pickup and a microphone; a processor and a wireless communication module are arranged inside the body, and the camera, the laser radar, the two-way communication speaker and the wireless communication module are all connected to the processor; the wireless communication module is used to send the image data collected by the camera and / or the audio data collected by the pickup to the client of the intelligent pet companion robot end; the two-way communication speaker is used to realize intercom between the user and the pet; the processor is used to: generate a two-dimensional map using the Gmapping algorithm according to the received radar data, and determine the current position of the intelligent companion pet robot using the Monte Carlo algorithm; when the pet is identified as being within the camera range according to the image data received from the sensor, determine the current position of the pet; take the current position of the intelligent companion pet robot as the starting point, take the current position of the pet as the target end point, use the A-star algorithm to perform global path planning based on the two-dimensional map, and generate a moving path; control the mobile device to move the intelligent companion pet robot according to the moving path, so as to move the intelligent companion pet robot to the vicinity of the pet. By using the wireless communication module to send the image data collected by the camera and / or the audio data collected by the microphone to the client of the intelligent companion pet robot, the user can realize real-time monitoring of the pet; by using the two-way communication speaker to realize intercom between the user and the pet, the emotional companionship can be better provided for the pet; by using the laser radar to generate a map and locate the pet, and using the A-star algorithm for global path planning, the intelligent companion pet robot can be accurately moved to the vicinity of the pet, so as to better provide companionship services to the pet. In summary, the intelligent pet companion robot provided by the embodiments of the present invention can better monitor the pet when the owner is not at home. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0035] Figure 1 This is a schematic diagram of the structure of an intelligent pet companion robot provided in one embodiment of the present invention.

[0036] The above drawings have shown clear embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0037] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0038] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0039] The serial numbers of the components in this document, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings).

[0040] Embodiment 1

[0041] Figure 1 This is a schematic diagram of the structure of an intelligent pet companion robot provided by an embodiment of the present invention. Figure 1 As shown, the intelligent companion pet robot provided in this embodiment may include: a chassis 1 and a body 2. The chassis 1 is used to carry the body 2.

[0042] The chassis is equipped with a mobile device 101 for realizing the movement of the intelligent companion pet robot. In an optional embodiment, the mobile device may include 4 steering wheels and 4 driving wheels, and the bottom of the driving wheels are arranged at the same height to realize omnidirectional movement. Each steering wheel has a steering degree of freedom and a driving degree of freedom, wherein the steering degree of freedom of the steering wheel is actively controlled, and the driving degree of freedom of the steering wheel is followed; each driving wheel also has a steering degree of freedom and a driving degree of freedom, wherein the driving degree of freedom of the driving wheel is actively controlled, and the steering degree of freedom of the driving wheel is followed, and the driving wheel and the steering wheel can be arranged symmetrically about the central axis of the chassis. Such a mobile device can well assist the intelligent companion pet robot to complete movements such as straight, sideways, oblique, and in-situ turning, and is simple to control.

[0043] The body is provided with a rotatable camera 201, a laser radar 202 and a two-way communication speaker 203. The camera is used to collect image data, the laser radar is used to collect radar data, and the two-way communication speaker includes a pickup and a microphone. In an optional implementation, a horizontally rotating universal head can be provided on the top of the body, and the camera is connected to the universal head so that the camera can achieve 360° rotation.

[0044] A processor 204 and a wireless communication module 205 are provided inside the body, and the camera, laser radar, two-way communication speaker and wireless communication module are all connected to the processor. The wireless communication module is used to send the image data collected by the camera and / or the audio data collected by the microphone to the client of the intelligent pet companion robot, so that the user can watch the image of the pet or hear the voice of the pet in real time through the client, and can better monitor the pet. Through the wireless communication module, the user can make a voice call through the client of the intelligent pet companion robot, and the user and the pet can talk through the two-way communication speaker. Not only can the user hear the pet's voice in real time, the pet can also hear the owner's voice, which can better provide spiritual companionship for the pet.

[0045] The processor is used to: generate a two-dimensional map using the Gmapping algorithm based on the received radar data, and determine the current position of the intelligent pet companion robot using the Monte Carlo algorithm; determine the current position of the pet when a pet is identified within the camera range based on the image data received from the sensor; use the current position of the intelligent pet companion robot as the starting point and the current position of the pet as the target end point, perform global path planning based on the two-dimensional map using the A-star algorithm, and generate a moving path; control the mobile device to move the intelligent pet companion robot along the moving path, so as to move the intelligent pet companion robot to the vicinity of the pet.

[0046] Pets usually move around in various indoor spaces and have a large range of activities. Therefore, in order to accurately locate the pet, in this embodiment, the radar data collected by the laser radar is first used to construct an indoor two-dimensional map of the pet's activity space. When constructing the map, the Gmapping algorithm is used to obtain an accurate indoor map. The Monte Carlo algorithm is then used to determine the current position of the intelligent pet companion robot. Global path planning is performed based on the two-dimensional map, accurate obstacle avoidance, and the global optimal movement path is found. Move the intelligent pet companion robot to the vicinity of the pet according to the determined movement path to achieve close monitoring of the pet or voice interaction, etc. It should be noted that the Gmapping algorithm, Monte Carlo algorithm and A-star algorithm in this embodiment all adopt algorithms in the prior art, which will not be repeated here.

[0047] The intelligent pet companion robot provided in this embodiment can realize real-time monitoring of pets by users by using a wireless communication module to send image data collected by the camera and / or audio data collected by the microphone to the client of the intelligent pet companion robot; by using a two-way communication speaker to realize intercom between users and pets, emotional companionship can be better provided for pets; by using a laser radar to generate a map and locate the pet, and using the A-star algorithm for global path planning, the intelligent pet companion robot can be accurately moved to the vicinity of the pet to better provide companionship services to the pet. In summary, the intelligent pet companion robot provided in this embodiment can better realize the monitoring of pets when the owner is not at home.

[0048] Embodiment 2

[0049] The processor can determine whether the pet is within the camera range of the smart pet companion robot based on image recognition according to the image data collected by the camera. When the pet is not within the camera range of the smart pet companion robot for a preset period of time, for example, the pet is not within the camera range of the smart pet companion robot for 30 minutes, a pet search instruction will be generated. Alternatively, the user can also send a pet search instruction to the smart pet companion robot through the client of the smart pet companion robot.

[0050] When the pet is not within the camera range of the intelligent pet companion robot, in order to achieve rapid and accurate positioning of the pet, the intelligent pet companion robot provided in this embodiment can further achieve positioning through audio data on the basis of the above embodiments. Specifically, the processor in the intelligent pet companion robot provided in this embodiment is also used to: when it is determined that the pet is not within the camera range according to the image data received from the sensor, in response to the received pet search instruction, control the microphone to collect the audio data of the pet; determine the direction of arrival (DOA) and distance according to the audio data using the generalized cross correlation-phase transform algorithm (Generalized Cross Correlation-Phase Transform, GCC-PHAT), and determine the current position of the pet according to the determined direction of arrival and distance. The pet's sound is collected by the microphone, and the current position of the pet is determined according to the direction and distance of the sound.

[0051] When the pet does not make any sound, for example, when the pet is sleeping, the pet's sound cannot be obtained through the microphone. At this time, the processor can also be used to control the microphone to play the pre-recorded voice signal of the pet owner or the voice signal of the pet owner in the real-time voice call to guide the pet to make a sound or approach the intelligent companion robot, complete the audio data collection, and finally realize the positioning of the pet.

[0052] The intelligent pet companion robot provided in this embodiment, based on the above embodiment, further collects the audio data of the pet by controlling the microphone, then determines the wave direction and distance based on the audio data, and finally determines the current position of the pet based on the determined wave direction and distance. When the pet is out of the camera range of the intelligent pet companion robot, the pet can be quickly and accurately positioned.

[0053] Embodiment 3

[0054] When the pet is not within the camera range of the intelligent companion pet robot, in addition to being able to locate the pet based on the sound, or after the sound source location fails, the pet can also be located by traversing the already obtained indoor two-dimensional map. Specifically, the processor in the intelligent companion pet robot provided in this embodiment is also used to: when it is determined that the pet is not within the camera range based on the image data received from the sensor, the complete coverage path planning algorithm (Complete Coverage Path Planning, CCPP) is used to traverse all areas on the two-dimensional map except obstacles; during the traversal process, the image data collected by the camera is recognized and processed in real time; if the pet is recognized, the traversal is stopped, the current position of the pet is determined, and the current position and current time of the pet are marked in the two-dimensional map.

[0055] It is understandable that the daily activity time and activity location of the pet have certain regularity. After multiple traversal positioning, the processor can also be used to: generate a probability distribution map of the pet's location in each time period according to the pet's location and the corresponding time marked during the multiple traversal processes; when receiving a pet search instruction, determine each location in the time period corresponding to the current time as the target end point according to the probability distribution map, and perform navigation. For example, 24 hours a day can be divided into 12 time periods. In the probability distribution map, the location where the pet appears in each time period in the previous traversal and the number of times each location appears can be recorded. The probability of a pet appearing in a location with a high number of appearances is higher. For example, when receiving a pet search instruction, if the location where the pet may appear in the time period corresponding to the current time is determined to be A (10 times), B (68 times), C (50 times) and D (34 times) according to the probability distribution map, then first determine position B as the target end point and perform navigation. If the pet is identified at B, then end. If the pet is not identified at B, then determine position C as the target end point, continue navigation, and so on.

[0056] The intelligent pet companion robot provided in this embodiment can accurately determine the location of the pet by traversing the two-dimensional map when the pet is not within the camera range of the intelligent pet companion robot. Based on multiple traversals, a time-location probability distribution map of the pet is constructed, and the location with a high probability is preferentially set as the target destination, which can accelerate the pet positioning process and save positioning time.

[0057] Embodiment 4

[0058] On the basis of any of the above embodiments, the intelligent companion pet robot provided in this embodiment can not only realize real-time monitoring of pets, but also realize intelligent feeding of pets. The body of the intelligent companion pet robot provided in this embodiment is provided with a grain storage device for storing pet food; a grain storage self-locking button is provided on the top of the body for controlling the ejection and retraction of the grain storage device. A food bowl is provided at the bottom of the chassis, and the food bowl can be extended to connect with the chassis; the food bowl and the grain storage device can be connected; in response to the grain release instruction, a predetermined amount of pet food is put into the food bowl from the grain storage device, and the food bowl is extended. The amount of pet food that can be stored in the grain storage device in this embodiment is much larger than the amount of the food bowl, and it can be realized that food is added once and fed multiple times. For example, the storage device and the food bowl can be connected through a pipe with a valve, and food is put into the food bowl when feeding. The grain release instruction can be generated according to a preset frequency, for example, feeding once every 6 hours; or it can be sent by the user to the intelligent companion pet robot through the client.

[0059] Embodiment 5

[0060] Existing pet companion robots focus more on how to feed pets intelligently. For example, in the Chinese patent application with publication number CN112775979A and invention name "Control method of pet companion robot, pet companion robot and chip", the infrared temperature detection sensor can scan a circular area with the pet companion robot as the center and the scanning distance of the infrared temperature detection sensor as the radius. The circular area is the preset area, so that the pet companion robot can scan the preset area through the infrared temperature detection sensor and obtain the temperature data of each object in the preset area. And the temperature data of each object is used as the scanning result. The preset area is scanned in real time by the infrared temperature detection sensor, and the scanning result is obtained; when the scanning result meets the preset conditions: there is a movable object; when an object with a temperature within a preset range is detected, it is determined that a pet is detected in the preset area, and the step of starting the camera device is executed. The preset area is photographed by the camera device, and the shooting data is obtained; the shooting data is image processed, and the pet type corresponding to the pet is determined according to the image processing result. Then, the feed type and feed delivery amount are determined according to the pet type, and finally the feed is delivered according to the feed type and feed delivery amount. Accurate feeding is mainly achieved by determining the type of pet. Moreover, the preset area scanned by the infrared temperature detection sensor is limited. If the pet is not in the preset area, it is difficult to achieve the effect of intelligent feeding. The Chinese patent application with publication number CN113080094A and invention name "Pet companion method, device and computer equipment" is as follows: confirm the target amount of exercise of the pet; form a corresponding exercise plan according to the target amount of exercise, and the pet companion robot interacts with the pet according to the exercise plan; the pet wearable device records the actual amount of exercise of the pet; form a feeding plan according to the actual amount of exercise, and the pet feeding device puts food according to the feeding plan. The pet companion robot forms a corresponding exercise plan according to the target amount of exercise, including: determining the activity scene diagram of the pet; planning the activity path and activity mode of the pet robot that matches the target amount of exercise of the pet according to the activity scene diagram, or the user sets the activity path of the pet robot in the activity scene. The pet companion robot attracts the pet in the set manner, and performs corresponding exercises according to the activity path according to the interaction of the pet until the amount of exercise of the pet meets the target amount of exercise. The pet companion robot has cameras and sensors that can identify the pet and the surrounding environment. At the same time, the pet companion robot can sense the interaction of the pet, such as the pet's touch, the pet's approach, etc. The pet companion robot has a binocular camera and can avoid obstacles based on the binocular camera, so that it can ensure that it can operate normally during the interaction with the pet without being hindered by obstacles. Scientific feeding is mainly based on the actual amount of exercise of the pet.

[0061] Pets not only need to be cared for by humans, but also need human companionship. In addition to feeding, pets also have emotional needs, but the existing pet companion robots obviously have not realized this and are still at the stage of feeding machines.

[0062] The intelligent pet companion robot provided in this embodiment is further provided with a display device installed on the outside of the body, which is used to display a pre-recorded video signal of the pet owner or a video signal of the pet owner in a real-time video call. The microphone is controlled to play a pre-recorded voice signal of the pet owner or a voice signal of the pet owner in a real-time voice call. For example, a pre-recorded video of the pet owner can be played through the display device at a preset time point (such as the time when the owner usually gets off work), and / or the microphone plays a pre-recorded voice of the pet owner, so that the pet can feel the company of the owner through sound and / or video even if the owner is not at home. With the help of the wireless communication module, the user can make a real-time voice or real-time video call with the intelligent pet companion robot through the client, play the voice signal of the pet owner in the real-time voice call through the microphone, and / or play the video of the pet owner in the real-time video call through the display device, so as to better realize the remote interaction between the owner and the pet and provide better emotional companionship for the pet.

[0063] Embodiment 6

[0064] The present application is further explained below through a specific example. When there is no pet within the camera range of the intelligent companion pet robot, sensors such as laser radar are used to determine the location of the pet indoors, and autonomously avoid obstacles and navigate to the vicinity of the pet, so as to better realize the monitoring of the pet when the owner is not at home. The intelligent companion pet robot provided in this embodiment includes a body, a rotatable camera and a chassis. The body is provided with a laser radar, a grain storage port and a self-locking button of the grain storage port. The body is provided with a sensor, a controller, a core board, and a two-way communication speaker at the bottom of the body. The chassis has 4 steering wheels; the controller has a wireless communication component, and a food bowl is provided at the bottom of the chassis. The sensor is used to receive data obtained by the sensor and send the data to the core board when the core board needs it. The core board is used to receive information sent by the client, process data, execute algorithms, store information, and output instructions to the controller. The controller has a wireless communication component for receiving instructions from the core board and controlling the various components of the intelligent companion pet robot to perform corresponding operations. A horizontally rotating universal head is provided on the top of the body of the intelligent companion pet robot, and the camera is connected to the universal head to achieve 360° steering. The chassis has 4 drive wheels, and the bottoms of the drive wheels are arranged at the same height.

[0065] There is a two-way communication speaker at the front of the body. The two-way communication speaker includes a pickup and a microphone. The two-way communication speaker is connected to the wireless communication component, and the user can interact with the pet remotely through the client. A laser radar is installed on the outside of the body. The core board builds the Robot Operating System (ROS). The laser radar transmits the acquired data to the sensor. The core board uses the Gmapping algorithm to build a two-dimensional map based on the data received from the sensor, determines the position of the robot through the Monte Carlo algorithm, and applies the A-star algorithm to do global path planning for the known target end point.

[0066] When there is a pet within the camera range of the smart pet companion robot, the core board obtains the data collected by the camera through the sensor, and uses image recognition technology to determine the pet's location. If the core board receives instructions such as releasing food or voice interaction sent by the client, the core board will establish that location as the target end point and use the A-star algorithm to autonomously avoid obstacles and navigate to the vicinity of the pet. The smart pet companion robot can then feed the pet, interact with the pet by voice, or view the pet at close range through the camera.

[0067] When the pet is not within the camera range of the smart companion robot, if the core board receives the pet-finding command from the client, the smart companion robot can locate the sound source based on the pet sound obtained by the microphone. If the microphone does not obtain the pet sound, the core board of the smart companion robot will send a command to the controller, and the controller will control the microphone to play the owner's recording or real-time speaking voice to guide the pet to make a sound or approach the robot. If the pet is not within the camera range of the robot and the pet makes a sound, the microphone will obtain the pet sound and send it to the core board through the sensor. The core board uses the generalized cross correlation-phase transform (Generalized Cross Correlation-Phase Transform, GCC-PHAT) algorithm to perform DOA estimation and distance estimation, thereby determining the target terminal position, and using the A-star algorithm to autonomously avoid obstacles and navigate to the vicinity of the pet, so that the smart companion robot can feed or interact with the pet by voice or perform close-up camera viewing operations.

[0068] If the sound source positioning fails, the core board will use the full coverage path planning algorithm to traverse all areas on the map except obstacles. During the traversal process, the core board continuously processes the data obtained by the camera. If a pet is recognized (that is, the pet appears within the camera range during the traversal process), the core board stops traversal and marks the location and current time of the pet on the map. After the intelligent companion pet robot traverses and searches for many times, the core board will form a probability distribution map of the pet's location at a certain moment. When the intelligent companion pet receives a command to find a pet from the robot's core board, the core board will first prioritize several possible locations of the pet as the end point according to the probability distribution map, and use the A-star algorithm to autonomously avoid obstacles and navigate to the vicinity of the pet. If the pet is not recognized within the camera range, the traversal method is used to find the pet.

[0069] The intelligent companion pet robot is equipped with a food storage port at the rear and a self-locking button on the top. Press the button to lock the food storage port, and operate it again to retract the food storage port. The chassis of the intelligent companion pet robot is equipped with a food bowl, which is connected to the body with a self-locking switch. The food bowl can be entered and exited through remote signal reception. The core board receives the signal received by the sensor and sends instructions to the controller, which controls the entry and exit of the food bowl.

[0070] Specific implementation method: Press the self-locking button of the grain storage port, the grain storage port pops up, put in an appropriate amount of pet food, and press the button again to retract the grain storage port. When the user is at work or any place with a signal, use a mobile client such as a mobile phone or tablet to open the corresponding software to automatically connect to the device, and the wireless communication element starts to send and receive signals. The user remotely controls the smart pet companion robot through the mobile client to release food at a fixed time or quantity or click the feeding button to release food. When releasing food, the core board controls the food bowl to self-lock or retract according to the relevant instructions of the client; the user needs to manually carry the smart pet companion robot at home when using it for the first time, and the core board uses the data obtained by the laser radar to build an indoor map. Users can check the dynamics of pets through the mobile client. When there is no pet within the camera range, users can send a pet-finding command to the core board. The core board first obtains the pet's voice based on the microphone, applies the GCC-PHAT algorithm to perform DOA estimation and distance estimation, thereby determining the target terminal position, and applies the A-star algorithm to autonomously avoid obstacles and navigate to the vicinity of the pet. During this period, the core board can control the microphone, which is a component of the two-way voice communication speaker, to play the owner's recording or real-time speaking voice to guide the pet to make a sound when the microphone does not obtain the pet's voice. If the sound source fails to be located, the core board will use the full coverage path planning algorithm to traverse all areas on the map except obstacles. During the traversal process, the core board continuously processes the data obtained by the camera. If a pet is recognized (that is, the pet appears within the camera range during the traversal process), the core board stops traversing and marks the location and current time of the pet's appearance on the map. After the intelligent companion pet robot has traversed and searched for many times, the core board will form a probability distribution map of the pet's location at a certain moment. When the intelligent companion pet receives a command to find a pet from the core board of the robot, the core board will first prioritize several possible locations of the pet according to the probability distribution map, and use the A-star algorithm to autonomously avoid obstacles and navigate to the vicinity of the pet. If the pet is not recognized within the range of the camera, the traversal method will be used to find the pet. Users can also talk to the pet through the two-way communication speaker, and can record and play at a fixed time to call the pet to eat, etc.

[0071] The intelligent companion pet robot provided in this embodiment is provided with a 360° camera on the top of the body to obtain the video data of the pet, and can transmit the video data to the client such as the mobile phone APP through the wireless communication component and the core board, so that the pet owner can view the dynamics of the pet in real time even if he is not at home. The two-way communication speaker is connected to the wireless communication component to realize the intercom between the user and the pet, and the user can record and set the playback time on the client such as the mobile phone APP to summon the pet to eat, etc. A laser radar is also installed. After the core board receives the surrounding environment information obtained by the laser radar, the mapping function can be completed. When the user does not find the pet when viewing the video on the client, the pet can be viewed by sending a pet search command through the client such as the mobile phone APP. After the core board receives the command, the sound source positioning can be used, and the machine learning can be used to prioritize the location where the pet is more likely to appear, and the traversal search method can be used to determine the target end point (i.e. the pet position), and then the A-star algorithm is used to autonomously avoid obstacles and navigate to the vicinity of the pet. A grain storage port and a grain storage port self-locking button are provided. After pressing the button, the grain storage port is self-locked, and the grain storage port is retracted again, which is convenient for the pet owner to load the pet food. There is a food bowl with controllable entry and exit. When the mobile phone APP or other client sends the corresponding command to the sensor, the core board will control the food bowl through the controller to make it self-lock or retract. This allows the smart companion pet robot to move flexibly while achieving a good effect of remote feeding the pet.

[0072] Indoor positioning and navigation solutions can also use Bluetooth positioning technology, that is, by installing iBeacon beacons indoors, the positioning can be accurately calculated through the received signal strength indicator (RSSI) values ​​of three points according to the positioning algorithm requirements. Through the built-in positioning algorithm and the interaction with the map engine database, the current specific location of the Bluetooth receiving device is calculated for real-time navigation. Ultra-Wide Band (UWB) indoor positioning technology can also be used.

[0073] The present invention is equipped with a laser radar. After the core board receives the surrounding environment information obtained by the laser radar, it can complete the mapping function. When the user fails to find the pet when viewing the video on the client, the user can send a pet search command through a mobile phone APP or other client to view the pet. After receiving the command, the core board can use sound source positioning, machine learning to prioritize the location where the pet is more likely to appear, and traversal search to determine the target end point (i.e. the pet's location), and then use the A-star algorithm to autonomously avoid obstacles and navigate to the vicinity of the pet.

[0074] The various embodiments in the present disclosure are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0075] The protection scope of the present disclosure is not limited to the above-mentioned embodiments. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the scope and spirit of the present disclosure. If these changes and modifications fall within the scope of the claims of the present disclosure and their equivalents, the intention of the present disclosure also includes these changes and modifications.

Claims

1. An intelligent companion robot, It is characterized in that include: A chassis and a body, wherein the chassis is used to support the body; The chassis is equipped with a moving device for realizing the movement of the intelligent pet companion robot; The body is provided with a rotatable camera, a laser radar and a two-way communication speaker on the outside, the camera is used to collect image data, the laser radar is used to collect radar data, and the two-way communication speaker includes a pickup and a microphone; A processor and a wireless communication module are arranged inside the body, and the camera, the laser radar, the two-way communication speaker and the wireless communication module are all connected to the processor; The wireless communication module is used to send the image data collected by the camera and / or the audio data collected by the microphone to the client of the intelligent pet companion robot; The two-way communication speaker is used to implement intercom between the user and the pet; The processor is used to: Generate a two-dimensional map using the Gmapping algorithm based on the received radar data, and determine the current position of the intelligent companion pet robot using the Monte Carlo algorithm; When a pet is identified within the camera range based on the image data received from the sensor, determining the current location of the pet; Taking the current position of the intelligent pet companion robot as the starting point and the current position of the pet as the target end point, the A-star algorithm is used to perform global path planning based on the two-dimensional map to generate a moving path; Controlling the moving device to move the intelligent pet companion robot according to the moving path, so as to move the intelligent pet companion robot to the vicinity of the pet; The processor is further configured to: When it is determined that the pet is not within the range of the camera according to the image data received from the sensor, a full coverage path planning algorithm is used to traverse all areas on the two-dimensional map except for obstacles; During the traversal process, real-time recognition and processing are performed on the image data collected by the camera; If a pet is identified, the traversal is stopped, the current position of the pet is determined, and the current position and current time of the pet are marked in the two-dimensional map; Generate a probability distribution diagram of the pet's location in each time period based on the pet's locations and corresponding times marked during multiple traversals; as well as When a pet search instruction is received, each location in the time period corresponding to the current time is determined as the target destination in order of probability according to the probability distribution map, and navigation is performed to achieve accurate pet search without installing additional devices on the pet. Wherein, a display device is installed on the outside of the body, which is used to display a pre-recorded video signal of the pet owner at a preset time point and / or to display a video signal of the pet owner in a real-time video call, so as to improve the interaction between the pet and the owner; The processor is further configured to: When it is determined that the pet is not within the range of the camera according to the image data received from the sensor, in response to the received pet-finding instruction, the microphone is controlled to collect audio data of the pet; Determine the direction of arrival and distance using a generalized cross-correlation-phase transform algorithm based on the audio data, and determine the current position of the pet based on the determined direction of arrival and distance; The processor is further configured to: The microphone is controlled to play a pre-recorded voice signal of the pet owner or a voice signal of the pet owner in a real-time voice call to guide the pet to make a sound or approach the intelligent pet companion robot.

2. The intelligent companion pet robot according to claim 1, It is characterized in that A horizontally rotating universal head is arranged on the top of the machine body, and the camera is connected to the universal head.

3. The intelligent pet companion robot according to claim 1, It is characterized in that The moving device comprises four steering wheels and four driving wheels, and the bottoms of the driving wheels are arranged at the same height to achieve omnidirectional movement.

4. The intelligent pet companion robot according to claim 1, It is characterized in that The machine body is provided with a grain storage device for storing pet food; the top of the machine body is provided with a grain storage self-locking button for controlling the ejection and retraction of the grain storage device.

5. The intelligent pet companion robot according to claim 4, It is characterized in that A food bowl is provided at the bottom of the chassis, and the food bowl is extendably connected to the chassis; the food bowl and the food storage device are communicatively arranged; in response to a food release instruction, a predetermined amount of pet food is put into the food bowl from the food storage device, and the food bowl is extended.

Images