Scheduling method of unmanned aerial vehicle defense detection linkage robot dog and related device

Abstract

The invention discloses a scheduling method of an unmanned aerial vehicle defense detection linkage robot dog and a related device, and relates to the technical field of unmanned defense vehicle detection, and the method comprises the steps: obtaining a detection task and the information of a schedulable robot dog; according to the detection task and the information of the schedulable robot dog, constructing a target function and a constraint condition; based on the constraint condition, solving the target function to obtain a robot dog to be selected; and confirming the robot dogs to be selected based on the information of the schedulable robot dogs to obtain the robot dogs used for executing the unmanned aerial vehicle defense detection task. Task requirements and robot dog resources can be accurately matched, and it is ensured that the detection task is efficiently executed. By optimizing the scheduling strategy, the system can still keep the maximum computing power schedulability after completing the detection task, and the long-term stability of the system is improved. The scheduling method provided by the invention solves the problems of unreasonable selection, resource waste and poor detection timeliness in the prior art.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) defense detection technology, and in particular to a scheduling method and related device for a UAV defense detection linkage robot dog. Background Technology

[0002] In recent years, with the rapid development of drone technology, its application in logistics, security, and inspection has become increasingly widespread. Traditional drone detection methods mainly rely on radar, radio signal analysis, infrared imaging, and optical recognition. However, these methods are easily interfered with in complex environments, making it difficult to provide high-precision, real-time drone identification. Furthermore, a single defense approach is insufficient to adapt to dynamically changing threat scenarios. Therefore, building a more flexible and efficient drone detection and defense system has become a significant technical challenge.

[0003] In recent years, the development of intelligent robot technology has provided new solutions for drone detection. Quadrupedal bionic robots (robot dogs) possess high mobility, adaptability to complex environments, and intelligent perception capabilities, enabling them to be flexibly deployed in different scenarios and work in conjunction with other detection devices. By combining technologies such as artificial intelligence, sensor fusion, and distributed computing, robot dogs can more accurately identify targets and collaboratively execute detection tasks. However, in the collaborative work between robot dogs and drones, how to rationally allocate tasks, optimize resource utilization, and improve detection efficiency remains an important issue in current research. Summary of the Invention

[0004] This invention provides a scheduling method and related device for drone defense and detection linkage robot dogs, which solves the problems of unreasonable technology selection, resource waste and poor detection timeliness in the prior art.

[0005] In view of this, the first aspect of the present invention provides a scheduling method for a drone defense and detection linkage robot dog, the method comprising:

[0006] Acquire information about detection tasks and schedulable robot dogs;

[0007] Based on the detection task and the information of the schedulable robot dog, construct the objective function and constraints;

[0008] Based on the constraints, the objective function is solved to obtain the candidate robot dogs;

[0009] Based on the information of the schedulable robot dog, the candidate robot dogs are confirmed to obtain a robot dog for performing drone defense and detection tasks.

[0010] Optionally, the method for generating the detection task includes: inputting the detection task through text description and generating text content.

[0011] Optionally, the method for obtaining the detection task includes: extracting the text content through text analysis technology to obtain the detection task; the detection task includes: the detection scope, the content specifications of the detection, the computing power requirements of the robot dog during detection, the detection time arrangement, and the detection environment.

[0012] Optionally, the method for constructing the objective function includes:

[0013] Based on the information of the schedulable robot dogs, the objective function is obtained by randomly selecting schedulable robot dogs to maximize the remaining schedulable computing power of the robot dogs after the matching of robot dogs in this detection task is completed.

[0014] Optionally, the expression for the objective function is:

[0015] ;

[0016] In the formula, For the set of all schedulable robot dogs, ; For robot dogs The current remaining computing power; For robot dogs The computing power consumed in performing this detection mission.

[0017] Optionally, the method for constructing the constraints includes:

[0018] When constructing a set of all schedulable robot dogs, constraints are applied to the elements in the set of all schedulable robot dogs based on the detection task to obtain constraint conditions.

[0019] Optionally, the constraints include:

[0020] Robot dog sensor specifications matching: or ;

[0021] Computing power requirements are met: ;

[0022] Travel speed matching time requirements: ;

[0023] Environmental adaptability matching: ;

[0024] In the formula, Represents a robot dog Possessing information acquisition capabilities; This indicates the specifications of this reconnaissance mission; Represents a robot dog Possessing information acquisition capabilities; Represents a robot dog and The combination of these features provides information acquisition capabilities; This indicates the computing resources required for the current detection mission; The latest time specified for the task; Represents a robot dog The minimum speed of travel; Represents a robot dog The breadth of information acquired; Represents a robot dog Able to adapt to different travel environments; This indicates the environmental requirements for this detection mission; This indicates the area to be detected.

[0025] A second aspect of the present invention provides a scheduling system for a drone defense and detection linkage robot dog, the system comprising:

[0026] The acquisition unit is used to acquire information about the detection task and the schedulable robot dog.

[0027] The construction unit is used to construct the objective function and constraints based on the detection task and the information of the schedulable robot dog;

[0028] The solving unit is used to solve the objective function based on the constraints to obtain the candidate robot dogs;

[0029] The analysis unit is used to confirm the candidate robot dogs based on the information of the schedulable robot dog, and obtain the robot dog used to perform the drone defense and detection task.

[0030] A third aspect of the present invention provides a scheduling device for a drone defense and detection linkage robot dog, the device comprising a processor and a memory:

[0031] The memory is used to store program code and transmit the program code to the processor;

[0032] The processor is used to execute the steps of the scheduling method for the drone defense and detection linkage robot dog as described in the first aspect above, according to the instructions in the program code.

[0033] A fourth aspect of the present invention provides a computer-readable storage medium for storing program code for executing the scheduling method of the drone defense and detection linkage robot dog described in the first aspect above.

[0034] As can be seen from the above technical solutions, the present invention has the following advantages:

[0035] This invention provides a scheduling method for a drone defense and detection linkage robot dog, comprising: acquiring information on the detection task and schedulable robot dogs; constructing an objective function and constraints based on the detection task and schedulable robot dog information; solving the objective function based on the constraints to obtain candidate robot dogs; and confirming the candidate robot dogs based on the schedulable robot dog information to obtain the robot dog used to perform the drone defense and detection task. This invention can accurately match task requirements and robot dog resources, ensuring efficient execution of the detection task. By optimizing the scheduling strategy, the system can maintain maximum computing power schedulability after completing the detection task, improving the long-term stability of the system. This method is applicable to complex environments and various drone threat scenarios, improving the accuracy and real-time performance of drone detection, reducing resource waste, and providing reliable technical support for intelligent security, border monitoring, and critical infrastructure protection. It thus solves the problems of unreasonable technology selection, resource waste, and poor detection timeliness in existing technologies. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 A flowchart illustrating a scheduling method for a drone defense and detection linkage robot dog provided in an embodiment of the present invention;

[0038] Figure 2 This is a schematic diagram of the structure of a scheduling system for a drone defense and detection linkage robot dog provided in an embodiment of the present invention. Detailed Implementation

[0039] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0040] Please see Figure 1 The present invention provides a method for scheduling a drone defense and detection linkage robot dog, comprising:

[0041] Step 101: Obtain information on the detection task and the schedulable robot dog.

[0042] In one embodiment, the method for generating a detection task includes: inputting the detection task through a text description and generating text content.

[0043] It should be noted that in practical applications, inputting detection tasks via text descriptions allows the system to flexibly parse different task requirements, making it suitable for various application scenarios. Compared to traditional fixed parameter input methods, text input supports Natural Language Processing (NLP), making it easier for users to define tasks and improving the system's versatility and scalability.

[0044] In one embodiment, the method for obtaining the detection task includes: extracting text content through text analysis technology to obtain the detection task; the detection task includes: the detection scope, the content specifications of the detection, the computing power requirements of the robot dog during detection, the detection time schedule, and the detection environment.

[0045] It should be noted that in practical applications, text analysis technology is used to extract detection tasks (such as detection range, content specifications, computing power requirements, environmental factors, etc.) to ensure that task requirements are accurately mapped to the robot dog's capabilities. This allows the system to dynamically construct appropriate scheduling schemes based on task requirements and the robot dog's resource availability, thereby optimizing task execution efficiency.

[0046] Furthermore, by acquiring information on all schedulable robot dogs (including sensor specifications, computing power, feasible environment, speed, and other parameters), the system can conduct a comprehensive evaluation during task matching, ensuring that the selected robot dog is capable of performing the current detection task. This also maximizes the schedulability of the system's overall computing power, avoiding resource waste or task failure. Since different robot dogs possess varying sensing and mobility capabilities, obtaining detailed robot dog information ensures that the system can accurately select suitable individuals to perform tasks in diverse environments (such as cities, forests, mountains, and oceans). Combining detection time scheduling with speed constraints ensures that the robot dog completes full-area coverage within the task timeframe, improving the reliability of the detection task.

[0047] Step 102: Based on the detection task and the information of the schedulable robot dog, construct the objective function and constraints.

[0048] In one embodiment, the method for constructing the objective function includes:

[0049] Based on the information of schedulable robot dogs, the objective function is obtained by randomly selecting schedulable robot dogs to maximize the remaining schedulable computing power of the robot dogs after the matching of robot dogs in this detection task is completed.

[0050] Specifically, let's assume... For the set of all schedulable robot dogs, ; For robot dogs Total computing power; For robot dogs The current remaining computing power; For robot dogs The computing power consumed in performing this detection mission; , This refers to the set of robot dogs selected to perform detection tasks.

[0051] The expression for the constructed objective function is:

[0052] ;

[0053] It's important to note that the goal is to maximize the overall computing power remaining in the system after the detection task is completed, while randomly selecting schedulable robot dogs to perform the task. This means: ensuring task completion while reserving as much unused computing power as possible so the system can handle subsequent detection tasks; avoiding excessive concentration of computing power on a few robot dogs, ensuring balanced resource allocation, and improving the continuous execution capability of tasks. Through this optimization strategy, the system ensures that after task execution, the overall remaining computing power of the system is maximized while randomly selecting robot dogs, thus preventing subsequent tasks from failing due to excessive computing power consumption by individual robot dogs.

[0054] It is understandable that UAV detection missions may be long-term and continuous. If the system excessively consumes computing power in each mission, subsequent missions may fail. Therefore, this invention addresses this issue by: rationally selecting robot dogs to share the computing power consumption; prioritizing the preservation of critical computing resources when computing power availability decreases; and dynamically optimizing task allocation to ensure stable system operation over extended periods. By randomly selecting schedulable robot dogs, overloading or prolonged idleness of some robots is avoided, thereby optimizing the overall system's computing resource load balancing. This method prevents computing resources from being exhausted by a single robot dog, extending the overall system's lifespan; and ensures that detection missions do not fail due to robot dog malfunctions or low computing power.

[0055] In one embodiment, the method for constructing constraints includes:

[0056] When constructing the set of all schedulable robot dogs, constraints are applied to the elements in the set of all schedulable robot dogs based on the detection task to obtain the constraint conditions.

[0057] The constraints include:

[0058] Robot dog sensor specifications matching: or ;

[0059] Computing power requirements are met: ;

[0060] Travel speed matching time requirements: ;

[0061] Environmental adaptability matching: ;

[0062] In the formula, Represents a robot dog Possessing information acquisition capabilities; This indicates the specifications of this reconnaissance mission; Represents a robot dog Possessing information acquisition capabilities; Represents a robot dog and The combination of these features provides information acquisition capabilities; This indicates the computing resources required for the current detection mission; The latest time specified for the task; Represents a robot dog The minimum speed of travel; Represents a robot dog The breadth of information acquisition is calculated based on the maximum width of data collection. Represents a robot dog Able to adapt to different travel environments; This indicates the environmental requirements for this detection mission; This indicates the area to be detected.

[0063] in, The calculation method is as follows:

[0064] set up, The area is transformed based on a circular model, so that the actual detection area of ​​the robot dog is larger than the actual area to be detected, thus ensuring the integrity of the detected content:

[0065] ;

[0066] Where s represents the actual area of ​​the region to be detected; This represents the proportionality coefficient, which is adaptively selected based on the degree of irregularity in the region. Its value is equal to:

[0067] Using a standard rectangle or circle with the same area as the region to be detected, align the centroids and calculate based on the degree of area variation:

[0068] ;

[0069] In the formula, This indicates the minimum area of ​​the non-overlapping portion of a standard rectangle or circle with the same area after the center of gravity is aligned.

[0070] It's important to note that the constraints serve to filter the schedulable robot dog set M during construction, ensuring that the selected robots meet all the requirements of the current detection task. The constraints directly impact the task's success rate, the system's computational resource utilization efficiency, and the long-term availability of the robots. They ensure that the selected robots possess the necessary information acquisition capabilities to complete the task, such as infrared imaging, radio spectrum analysis, and radar detection. Multiple robots can work together to complete the detection task; for example, one robot dog can have visual recognition capabilities while another handles radio spectrum detection, allowing them to collaborate. During task execution, the robots need to process sensor data, run target recognition algorithms, and may engage in remote communication, thus requiring sufficient computing power. This constraint ensures that the task will not fail due to insufficient computing power. Real-time computing power monitoring prevents the selection of robots with low computing power but high workloads. Task allocation is dynamically adjusted; if a single robot dog's computing power is insufficient, multiple robots can be assigned to collaborate on the task. The robots must be able to complete the detection of the entire area within a specified time; otherwise, target loss or incomplete data acquisition may occur. Too low a speed may cause the task to time out, while too high a speed may affect the recognition accuracy. Therefore, the detection task must be completed within a suitable speed range.

[0071] Step 103: Based on the constraints, solve the objective function to obtain the candidate robot dogs.

[0072] It should be noted that the objective function is solved as follows: the information acquisition capability requirement is transformed into constraints on the type and performance of the robot dog's sensors; the computing capability requirement is transformed into constraints on the robot dog's computing power and load; and the speed requirement is transformed into constraints on the robot dog's movement speed range. Then, optimization algorithms such as linear programming and genetic algorithms are used to solve the objective function. For linear programming, the objective function and constraints are transformed into standard linear programming form, and the optimal solution is found using methods such as the simplex method. The robot dog corresponding to this solution is the candidate robot dog. If a genetic algorithm is used, a group of robot dogs is randomly initialized as the initial population. The fitness of each individual is calculated according to the objective function. The population is iteratively updated through selection, crossover, and mutation operations until the termination condition is met. The robot dog corresponding to the individual with the highest fitness is the candidate robot dog. During the solution process, the synergy between robot dogs must also be considered. If the task requires multiple robot dogs to cooperate, it must be ensured that the candidate robot dogs can cooperate effectively and their capabilities can complement each other. At the same time, the solution results need to be evaluated and verified to check whether the candidate robot dog truly meets the requirements of the task. If it does not meet the requirements, the objective function or solution method needs to be adjusted and the solution needs to be performed again.

[0073] Step 104: Based on the information of the schedulable robot dog, confirm the robot dog to be selected, and obtain the robot dog to perform the drone defense and detection task.

[0074] Understandably, schedulable robot dogs refer to a group of robot dogs that are currently available and can be assigned to perform tasks. The confirmation process requires comprehensive consideration of multiple factors. Firstly, the hardware status of the candidate robot dogs must be checked, including whether the sensors are functioning properly, the power system is stable, and the communication equipment can transmit and receive signals normally. If a robot dog malfunctions in a critical hardware component, even if it is selected in the objective function solution, it cannot be included in the task execution team, as hardware failure may cause various problems during task execution, affecting the successful completion of the task. Secondly, the software system of the candidate robot dogs must be checked for normal operation. For example, whether the target recognition algorithm runs accurately and whether the real-time computing power monitoring program works effectively. Software system anomalies may cause the robot dog to make incorrect judgments or operations during task execution, thus affecting the overall detection task's effectiveness. Furthermore, the task history and current task load of the candidate robot dogs must be considered. If a robot dog has recently been frequently performing tasks and is already under high load, even if it meets the requirements of the objective function, it may not be suitable to be assigned new tasks to avoid malfunctions due to overwork. For candidate robot dogs with low task loads and a good historical performance, priority can be given to confirmation. After completing the above checks and evaluations, candidate robot dogs that meet all the conditions will be officially confirmed from the schedulable robot dogs to form a robot dog team to perform detection tasks. This ensures that the selected robot dogs can efficiently and stably complete the drone defense detection linkage task, improving the reliability of the entire system and the success rate of task execution.

[0075] This invention provides a scheduling method for a drone defense and detection linkage robot dog, comprising: acquiring information on the detection task and schedulable robot dogs; constructing an objective function and constraints based on the detection task and schedulable robot dog information; solving the objective function based on the constraints to obtain candidate robot dogs; and confirming the candidate robot dogs based on the schedulable robot dog information to obtain the robot dog used to perform the drone defense and detection task. This invention can accurately match task requirements and robot dog resources, ensuring efficient execution of the detection task. By optimizing the scheduling strategy, the system can maintain maximum computing power schedulability after completing the detection task, improving the long-term stability of the system. This method is applicable to complex environments and various drone threat scenarios, improving the accuracy and real-time performance of drone detection, reducing resource waste, and providing reliable technical support for intelligent security, border monitoring, and critical infrastructure protection. It thus solves the problems of unreasonable technology selection, resource waste, and poor detection timeliness in existing technologies.

[0076] The above is a scheduling method for a drone defense and detection linkage robot dog provided in the embodiments of the present invention. The following is a scheduling system for a drone defense and detection linkage robot dog provided in the embodiments of the present invention.

[0077] Please see Figure 2 The present invention provides a scheduling system for a drone defense and detection linkage robot dog, comprising:

[0078] The acquisition unit 201 is used to acquire information about the detection task and the schedulable robot dog.

[0079] Construction unit 202 is used to construct objective function and constraints based on the detection task and information of the schedulable robot dog.

[0080] Solver 203 is used to solve the objective function based on the constraints to obtain the candidate robot dogs.

[0081] Analysis unit 204 is used to confirm the candidate robot dog based on the information of the schedulable robot dog, and obtain the robot dog to perform the drone defense and detection task.

[0082] Furthermore, this embodiment of the invention also provides a scheduling device for a drone defense and detection linkage robot dog, the device including a processor and a memory:

[0083] The memory is used to store program code and transmit the program code to the processor;

[0084] The processor is used to execute the steps of the scheduling method for the drone defense and detection linkage robot dog as described in the above method embodiments, according to the instructions in the program code.

[0085] Furthermore, this embodiment of the invention also provides a computer-readable storage medium for storing program code, which is used to execute the scheduling method for the drone defense and detection linkage robot dog described in the above method embodiment.

[0086] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0087] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0088] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0089] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0090] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0091] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A scheduling method for a drone defense and detection linkage robot dog, characterized in that, include: Acquire information about detection tasks and schedulable robot dogs; Based on the detection task and the information of the schedulable robot dog, construct the objective function and constraints; Based on the constraints, the objective function is solved to obtain the candidate robot dogs; Based on the information of the schedulable robot dog, the candidate robot dogs are confirmed to obtain a robot dog for performing drone defense and detection tasks.

2. The scheduling method for the drone defense and detection linkage robot dog according to claim 1, characterized in that, The method for generating the detection task includes: inputting the detection task through text description and generating text content.

3. The scheduling method for the drone defense and detection linkage robot dog according to claim 2, characterized in that, The method for obtaining the detection task includes: extracting the text content through text analysis technology to obtain the detection task; the detection task includes: the detection scope, the detection content specifications, the computing power requirements of the robot dog during detection, the detection time arrangement, and the detection environment.

4. The scheduling method for the drone defense and detection linkage robot dog according to claim 1, characterized in that, The method for constructing the objective function includes: Based on the information of the schedulable robot dogs, the objective function is obtained by randomly selecting schedulable robot dogs to maximize the remaining schedulable computing power of the robot dogs after the matching of robot dogs in this detection task is completed.

5. The scheduling method for the drone defense and detection linkage robot dog according to claim 4, characterized in that, The expression for the objective function is: ； In the formula, For the set of all schedulable robot dogs, ; For robot dogs The current remaining computing power; For robot dogs The computing power consumed in performing this detection mission.

6. The scheduling method for the drone defense and detection linkage robot dog according to claim 5, characterized in that, The method for constructing the constraints includes: When constructing a set of all schedulable robot dogs, constraints are applied to the elements in the set of all schedulable robot dogs based on the detection task to obtain constraint conditions.

7. The scheduling method for the drone defense and detection linkage robot dog according to claim 6, characterized in that, The constraints include: Robot dog sensor specifications matching: or ; Computing power requirements are met: ; Travel speed matching time requirements: ; Environmental adaptability matching: ; In the formula, Represents a robot dog Possessing information acquisition capabilities; This indicates the specifications of this reconnaissance mission; Represents a robot dog Possessing information acquisition capabilities; Represents a robot dog and The combination of these features provides information acquisition capabilities; This indicates the computing resources required for the current detection mission; The latest time specified for the task; Represents a robot dog The minimum speed of travel; Represents a robot dog The breadth of information acquired; Represents a robot dog Able to adapt to different travel environments; This indicates the environmental requirements for this detection mission; This indicates the area to be detected.

8. A scheduling system for a drone defense and detection linkage robot dog, characterized in that, include: The acquisition unit is used to acquire information about the detection task and the schedulable robot dog. The construction unit is used to construct the objective function and constraints based on the detection task and the information of the schedulable robot dog; The solving unit is used to solve the objective function based on the constraints to obtain the candidate robot dogs; The analysis unit is used to confirm the candidate robot dogs based on the information of the schedulable robot dog, and obtain the robot dog used to perform the drone defense and detection task.

9. A scheduling device for a drone defense and detection linkage robot dog, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the scheduling method of the drone defense and detection linkage robot dog according to any one of the claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code, which is used to execute the scheduling method of the drone defense and detection linkage robot dog according to any one of claims 1-7.

Images