A low-cost embodied mobile companion robot

Abstract

The present invention relates to a low-cost embodied movable companion robot, which belongs to the technical field of video measurement, and comprises: a visual detection module, an interactive unit and a model construction module, wherein the visual detection module is used to detect physical entities within a detection range and generate a visual image of the physical entity; the interactive unit is connected to the visual detection module, and the interactive unit is used to process the visual image in the visual detection module; the model construction module is used to construct the execution behavior of the robot according to the visual image, and the model construction module is connected to the interactive unit; the visual image is judged by the model construction module to construct the execution behavior of the robot, so that the robot operates according to the execution behavior; the beneficial effects of the present invention are as follows: the execution behavior of the robot is constructed according to a clear visual image, the execution behavior of the robot is evaluated according to the visual image, and each action of the robot is executed separately.

Description

Technical Field

[0001] The present invention belongs to the technical field of video measurement, and in particular relates to a low-cost embodied movable companion robot. Background Art

[0002] Embodied Intelligence is a concept related to artificial intelligence and robotics, emphasizing the ability of AI systems to interact with physical entities in the real world. The core elements and characteristics of embodied intelligence are as follows:

[0003] Interaction with physical entities: Embodied intelligence interacts with other physical entities through the robot's sensors or actors to perceive or respond to the external world.

[0004] Perception and action: This form of intelligence relies not only on algorithms and data processing but also emphasizes the development of intelligence through the interaction between robots and physical entities. For example, when a delivery robot moves in a city, it needs to use its sensors and actuators to avoid obstacles and find the right path.

[0005] Natural and intuitive interaction: Embodied intelligence enables AI systems to interact with physical entities more naturally and intuitively. For example, a household robot can adjust its actions in real time based on environmental changes to better complete tasks.

[0006] In short, embodied intelligence is a technology that emphasizes the interaction between AI systems and physical entities. It enables AI systems to interact with physical entities more naturally and promotes the overall development of AI technology. Summary of the Invention

[0007] The technical problem to be solved by the present invention is how to interact with physical entities through an AI system. The present invention provides a low-cost embodied mobile companion robot, which constructs the robot's execution behavior based on clear visual images, evaluates the robot's execution behavior based on visual images, and executes each action of the robot separately.

[0008] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0009] A low-cost embodied mobile companion robot comprising:

[0010] A visual detection module, configured to detect a physical entity within a detection range and generate a visual image of the physical entity;

[0011] An interactive unit, the interactive unit is connected to the visual detection module, and the interactive unit is used to process the visual image in the visual detection module;

[0012] A model building module, which is used to build the robot's execution behavior according to the visual image. The model building module is connected to the interaction unit;

[0013] The model building module is used to build the robot's execution behavior based on the visual image, so that the robot can run according to the execution behavior.

[0014] Optionally, the visual detection module detects the physical entity within a detection distance range, wherein the visual detection module detects the physical entity within an adjustable detection distance range;

[0015] The visual detection module detects the physical entity within the detection area, wherein the visual detection module detects the physical entity within an adjustable range of the detection area;

[0016] The visual inspection module generates three-dimensional visual images of physical entities.

[0017] Optionally, the visual detection module detects physical entities within a distance range by using a differential distance adjustment method, and the differential distance adjustment method is as follows:

[0018] (1);

[0019] in, is the set detection distance, The fixed point position at one end of the set detection distance, The active point position at the other end of the set detection distance, After one end of the set detection distance is fixed, the position of the active point at the other end of the set detection distance can be adjusted;

[0020] To adjust the distance, To increase the adjustment distance, In order to reduce the adjustment distance, The distance for adjustment can be increased or decreased;

[0021] For data combination operation, after one end of the set detection distance is fixed, the adjustment distance is increased or decreased to adjust the active point position at the other end of the set detection distance;

[0022] or After fixing one end of the set detection distance, adjust the position of the active point at the other end of the set detection distance to increase or decrease the set detection distance to obtain the final distance.

[0023] Optionally, the visual inspection module uses a region adjustment method to detect the physical entity within the region range. The region adjustment method is the following formula (2):

[0024] (2);

[0025] in, is the area of ​​the first region, To adjust the area of ​​the first region, the area of ​​the first region can be increased or decreased. To calculate the size of the adjusted first region;

[0026] For the Area, To adjust the Operations on area, The area of ​​the region can be increased or decreased, To calculate the adjusted Area size;

[0027] For the Regional area, To adjust the Operations on area, The area of ​​the region can be increased or decreased, To calculate the adjusted Area size;

[0028] is the sum of the areas of each region, It is the sum of the areas of all adjustable regions.

[0029] Optionally, the interactive unit is used to adjust the visual image in the visual detection module. The interactive unit can adjust the visual image in the visual detection module to be clear and transmit the visual image to the model building module.

[0030] Optionally, a model building module manipulates the robot's actions based on the visual image;

[0031] If the visual image is an obstacle, the model building module causes the robot to avoid the obstacle and the robot deviates from moving toward the obstacle;

[0032] If the visual image is a product, the model building module causes the robot to grip the product and the robot moves toward the product;

[0033] If the visual image shows that the product is in the wrong position, the model building module enables the robot to grip the product and place it in the correct position, and the robot moves the product.

[0034] Optionally, the model building module executes the robot's execution behavior using a visual image interchange method, and the visual image interchange method is the following formula (3):

[0035] (3);

[0036] in, For each visual image, To distinguish the operations of each visual image,

[0037] To distinguish and converge each visual image;

[0038] is the corresponding operation of each visual image, is the total number of visual images, Assigning each visual image to its corresponding execution operation;

[0039] Execute on each visual image;

[0040] To include various visual images, To distinguish the operations of each visual image, Perform corresponding operations for each visual image, For each visual image, execution is performed.

[0041] Optionally, the visual image interchange method is to interchange each visual image into different execution behaviors of the robot.

[0042] Optionally, the model building module is connected to the execution evaluation module, and the execution evaluation module is used to evaluate whether the robot deviates from the movement toward the obstacle, the robot moves toward the product, or the robot moves the product.

[0043] Optionally, the execution evaluation module is connected to multiple execution units, and each execution unit operates the robot independently.

[0044] Beneficial effects of the present invention:

[0045] The present invention detects a physical entity within a detection range, generates a visual image of the physical entity, adjusts the visual image to make the visual image clear, constructs an execution behavior of the robot based on the clear visual image, evaluates the execution behavior of the robot based on the visual image, and executes each action of the robot separately. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 Schematic diagram of the system structure of the present invention;

[0048] Figure 2 It is a workflow diagram of the present invention;

[0049] Figure 3 A schematic diagram of the principle of detecting a physical entity within the detection distance range of the present invention;

[0050] Figure 4 This is a schematic diagram of the principle of detecting physical entities within the detection area of ​​the present invention. DETAILED DESCRIPTION

[0051] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0052] Example 1:

[0053] like Figure 1 As shown, this embodiment provides a low-cost embodied mobile companion robot, comprising: a visual detection module, an interaction unit, a model building module, an execution evaluation unit, and a plurality of execution units;

[0054] The visual detection module is used to detect a physical entity within a detection range and generate a visual image of the physical entity, wherein the visual detection module generates a three-dimensional visual image of the physical entity, and the visual detection module can be executed according to a program set therein;

[0055] The interactive unit is connected to the visual detection module. The interactive unit is used to process the visual images in the visual detection module. The interactive unit can execute according to the program set inside it;

[0056] The model building module is used to build the robot's execution behavior according to the visual image. The model building module is connected to the interactive unit and can be executed according to the program set inside it;

[0057] The model building module is used to build the robot's execution behavior based on the visual image, so that the robot can run according to the execution behavior.

[0058] The model building module is connected to the execution evaluation module, which is used to evaluate whether the robot deviates from the movement toward the obstacle (i.e., the robot will not go straight toward the obstacle, the robot can avoid the obstacle), or the robot moves toward the product (i.e., the robot grabs the product), or the robot moves the product to a new position (i.e., the robot places the product on the next process).

[0059] The execution evaluation module connects multiple execution units, and each execution unit operates the robot separately. For example, the first execution unit makes the robot deviate from the movement towards the obstacle, and the second execution unit makes the robot The execution unit is to move the robot toward the product. The execution unit allows the robot to move the product to a certain location.

[0060] The interactive unit of this embodiment is used to adjust the visual image in the visual detection module. The interactive unit can adjust the visual image in the visual detection module to be clear and transmit the visual image to the model construction module.

[0061] In addition, the model building module manipulates the robot’s actions based on the visual images;

[0062] If the visual image is an obstacle, the model building module causes the robot to avoid the obstacle and the robot deviates from moving toward the obstacle;

[0063] If the visual image is a product, the model building module causes the robot to grip the product and the robot moves toward the product;

[0064] If the visual image shows that the product is in the wrong position, the model building module enables the robot to grip the product and place it in the correct position, and the robot moves the product.

[0065] Example 2:

[0066] Based on Example 1, Figure 3 As shown, this embodiment provides a working method of a low-cost embodied mobile companion robot:

[0067] Step 1: Detect the physical entity within the detection range and generate a visual image of the physical entity;

[0068] Step 2: Adjust the visual image to make it clear;

[0069] Step 3: Construct the robot's execution behavior based on the visual image;

[0070] Step 4: Evaluate the robot's execution behavior based on the visual image;

[0071] Step 5: Execute each action of the robot, wherein each action of the robot is executed separately.

[0072] Example 3:

[0073] Based on Example 1, the visual detection module detects the physical entity within a detection distance range, wherein the visual detection module detects the physical entity within an adjustable detection distance range;

[0074] like Figure 3 As shown, the visual detection module uses a differential distance adjustment method to detect physical entities within a distance range. The differential distance adjustment method is as follows:

[0075] (1);

[0076] in, The detection distance is set to Figure 3 The distance from point a to point b (the initial distance from point a to point b), The fixed point position at one end of the set detection distance is point b. The active point position at the other end of the set detection distance is point a. After one end of the set detection distance is fixed, the position of the active point at the other end of the set detection distance can be adjusted, that is, point b is fixed, and the position of point a relative to point b can be changed, so that the distance from point a to point b can be adjusted;

[0077] To adjust the distance, To increase the adjustment distance, In order to reduce the adjustment distance, The distance for adjustment can be increased or decreased;

[0078] For data combination operation, after one end of the set detection distance is fixed, the adjustment distance is increased or decreased to adjust the active point position at the other end of the set detection distance;

[0079] or After one end of the set detection distance is fixed, that is, point b is fixed, adjust the position of the active point at the other end of the set detection distance, that is, point b, to adjust the set detection distance. Increase or decrease to get the final distance.

[0080] Formula (1) is mainly to initially fix point b and keep the position of point a unchanged. The position of point a relative to point b is unchanged. The detection distance is set to When point b is fixed and the position of point a changes, the position of point a relative to point b changes, and the distance is adjusted The increase or decrease of , the final distance Can be increased or decreased.

[0081] Example 4:

[0082] Based on Example 1 to Example 3, the visual detection module detects the physical entity within the detection area, wherein the visual detection module detects the physical entity within the adjustable range of the detection area, such as Figure 4 As shown in FIG, the visual inspection module uses the regional adjustment method to detect the physical entity in the regional range. The regional adjustment method is the following formula (2):

[0083] (2);

[0084] in, is the area of ​​the first region, To adjust the area of ​​the first region, the area of ​​the first region can be increased or decreased. To calculate the size of the adjusted first region;

[0085] For the Area, To adjust the Operations on area, The area of ​​the region can be increased or decreased, To calculate the adjusted Area size;

[0086] For the Area, To adjust the Operations on area, The area of ​​the region can be increased or decreased, To calculate the adjusted Area size; the total area of ​​the area is indivual.

[0087] is the sum of the areas of each region, It is the sum of the areas of all adjustable regions.

[0088] Formula (2) is that the area of ​​the first region can be increased or decreased, and the area of ​​the second region can be increased or decreased. Area Can be increased or decreased, similarly, Area Can be increased or decreased, so the area of ​​the first area to the The area of ​​each region can be increased or decreased.

[0089] Area 1 to The area of ​​each area can be increased or decreased at the same time, or the area of ​​the first area to the second area can be increased or decreased at the same time. The area of ​​each region is increased or decreased individually.

[0090] Therefore, the sum of the areas of each adjustable region It can be increased or decreased.

[0091] Example 4:

[0092] Based on Example 1, the model building module executes the robot's execution behavior using a visual image interchange method, and the visual image interchange method is the following formula (3):

[0093] (3);

[0094] in, For each visual image, In order to distinguish the operations of each visual image, the interactive unit can adjust the visual image in the visual detection module to be clear and transmit the visual image to the model building module, so each visual image can be distinguished. To distinguish and converge each visual image;

[0095] is the corresponding operation of each visual image, is the total number of visual images, Each visual image corresponds to its own execution operation, that is, Correspondingly, the robot is deviated from the movement towards the obstacle. There is , Corresponding to the previous The execution unit is what allows the robot to move toward the product. Corresponding to the previous The execution unit allows the robot to move the product to a certain location.

[0096] Execute on each visual image;

[0097] To include various visual images, , To distinguish the operations of each visual image, that is, to analyze what each visual image is, Perform corresponding operations for each visual image, For each visual image, execution is performed.

[0098] Formula (3) prepares for the execution of the evaluation module and each execution unit.

[0099] The visual image interchange method of this embodiment is to interchange each visual image into different execution behaviors of the robot.

[0100] The model building module is connected to the execution evaluation module, and the execution evaluation module is used to evaluate whether the robot deviates from moving towards the obstacle, the robot moves towards the product, or the robot moves the product.

[0101] Throughout this specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Therefore, appearances of the phrases "one embodiment," "an embodiment," "an example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combinations and / or subcombinations. Furthermore, it will be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes only and are not necessarily drawn to scale. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0102] Those skilled in the art will understand that all or part of the steps in implementing the above facts and methods can be completed by instructing relevant hardware through a program, and the program involved or the program can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: the corresponding method steps are then brought out, and the storage medium can be ROM / RAM, a disk, an optical disk, etc.

[0103] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope of the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A low-cost embodied mobile companion robot, characterized in that: include: A visual detection module, configured to detect a physical entity within a detection range and generate a visual image of the physical entity; The visual detection module detects physical entities within a distance range by using a differential distance adjustment method, and the differential distance adjustment method is the following formula (1): (1)； in, is the set detection distance, The fixed point position at one end of the set detection distance, The active point position at the other end of the set detection distance, After one end of the set detection distance is fixed, the position of the active point at the other end of the set detection distance can be adjusted; To adjust the distance, To increase the adjustment distance, In order to reduce the adjustment distance, The distance for adjustment can be increased or decreased; For data combination operation, after one end of the set detection distance is fixed, the adjustment distance is increased or decreased to adjust the active point position at the other end of the set detection distance; or After fixing one end of the set detection distance, adjust the position of the active point at the other end of the set detection distance to increase or decrease the set detection distance to obtain the final distance; Alternatively, the visual detection module uses a region adjustment method to detect the physical entity within the region range, and the region adjustment method is the following formula (2): (2)； in, is the area of ​​the first region, To adjust the area of ​​the first region, the area of ​​the first region can be increased or decreased. To calculate the size of the adjusted first region; For the Area, To adjust the Operations on area, The area of ​​the region can be increased or decreased, To calculate the adjusted Area size; For the Area, To adjust the Operations on area, The area of ​​the region can be increased or decreased, To calculate the adjusted Area size; is the sum of the areas of each region, is the sum of the areas of all adjustable regions; An interactive unit, connected to the visual detection module, and configured to process visual images in the visual detection module; A model building module, the model building module is used to build the robot's execution behavior according to the visual image, and the model building module is connected to the interaction unit; The model building module executes the robot's execution behavior using a visual image exchange method, and the visual image exchange method is the following formula (3): (3)； in, For each visual image, To distinguish the operations of each visual image, To distinguish and converge each visual image; is the corresponding operation of each visual image, is the total number of visual images, Assigning each visual image to its corresponding execution operation; Execute on each visual image; To include various visual images, To distinguish the operations of each visual image, Perform corresponding operations for each visual image, To perform execution on each visual image; The model building module is used to build the robot's execution behavior based on the visual image, so that the robot can run according to the execution behavior.

2. A low-cost embodied mobile companion robot according to claim 1, characterized in that: The visual detection module detects the physical entity within a detection distance range, wherein the visual detection module detects the physical entity within an adjustable detection distance range; The visual detection module detects the physical entity within the detection area, wherein the visual detection module detects the physical entity within an adjustable range of the detection area; The visual inspection module generates three-dimensional visual images of physical entities.

3. A low-cost embodied mobile companion robot according to claim 1, characterized in that: The interactive unit is used to adjust the visual image in the visual detection module. The interactive unit can adjust the visual image in the visual detection module to be clear and transmit the visual image to the model construction module.

4. A low-cost embodied mobile companion robot according to claim 1, characterized in that: The model building module operates the robot's movements based on the visual image; If the visual image is an obstacle, the model building module causes the robot to avoid the obstacle and the robot deviates from moving toward the obstacle; If the visual image is a product, the model building module causes the robot to grip the product and the robot moves toward the product; If the visual image shows that the product is in the wrong position, the model building module enables the robot to grip the product and place it in the correct position, and the robot moves the product.

5. A low-cost embodied mobile companion robot according to claim 1, characterized in that: The visual image interchange method is to interchange each visual image into different execution behaviors of the robot.

6. A low-cost embodied mobile companion robot according to claim 1, characterized in that: The model building module is connected to the execution evaluation module, and the execution evaluation module is used to evaluate whether the robot deviates from the movement toward the obstacle, the robot moves toward the product, or the robot moves the product.

7. A low-cost embodied mobile companion robot according to claim 6, characterized in that: The execution evaluation module is connected to a plurality of execution units, and each of the execution units operates the robot independently.

Images