Robot motion control method, robot motion control device, medium, and apparatus

Abstract

The application provides a robot action control method, a robot action control device, a computer readable storage medium and an electronic device, relates to the technical field of robot control, and can determine the position of a target rescue object in a topographic map, generate robot actions corresponding to the next moment on the basis of the position and the robot actions corresponding to the current moment, thereby obtaining an action set, and the robot can reach the position requiring rescue by executing the actions in the action set, thereby completing the rescue task. In the application, the optimal target action set can be selected according to the incentive values corresponding to each action set, and the robots in the robot team can more efficiently complete the rescue task by executing the actions in the target action set, which is beneficial to improving the rescue efficiency.

Description

Technical Field

[0001] This application relates to the field of robot control technology, and more specifically, to a robot motion control method, a robot motion control device, a computer-readable storage medium, and an electronic device. Background Technology

[0002] For some emergency rescue missions, such as lunar rescue missions, it may be inconvenient to carry out the rescue work manually. In such cases, robots may be needed to perform the rescue mission. When using robots for rescue missions, the following problem usually needs to be addressed: how to control the robot to efficiently complete the rescue mission through optimal action selection.

[0003] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide a robot motion control method, a robot motion control device, a computer-readable storage medium, and an electronic device. This method can generate the robot motion corresponding to the next moment based on the robot's position and the current moment's motion, thus obtaining a motion set. The robot can reach the location requiring rescue by executing the motions in the motion set, thereby completing the rescue mission. In this application, the optimal target motion set can be selected based on the excitation value corresponding to each motion set. Robots in the robot team can complete the rescue mission more efficiently by executing the motions in the target motion set, which is beneficial for improving rescue efficiency.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to one aspect of this application, a robot motion control method is provided, the method comprising:

[0007] Determine the location of the target rescue object on the topographic map;

[0008] Based on the position and the robot action corresponding to the current time, generate the robot action corresponding to the next time, so as to obtain the action set corresponding to the robot action at each time.

[0009] Select the target action set based on the excitation value corresponding to each action set;

[0010] The robot team controls each robot to execute its corresponding action from the target action set according to the time sequence in order to reach the location of the target rescue object.

[0011] In one exemplary embodiment of this application, the method further includes:

[0012] The total time measurement function is calculated based on the total number of actions of each type of robot in the robot team and the time required to execute the actions, and the total time consumption incentive value is calculated based on the total time measurement function.

[0013] The relative distance excitation value is calculated based on the relative distance between the operating robot in the robot team and the target rescue object at the final moment.

[0014] The destination arrival incentive value is determined based on the location of the robot team.

[0015] Calculate the step-by-step excitation value based on the robot's actions at each moment;

[0016] Incentive values ​​for each action set are generated based on the total time consumption incentive value, relative distance incentive value, destination arrival incentive value, and step-by-step incentive value.

[0017] In one exemplary embodiment of this application, the different types of robots in the robot team correspond to different attributes, including perception ability, passability of different types of areas, range of motion, and speed of motion.

[0018] In one exemplary embodiment of this application, a robot action corresponding to the next time moment is generated based on the position and the robot action corresponding to the current time moment, so as to obtain a set of actions corresponding to the robot actions at each time moment, including:

[0019] By using reinforcement learning algorithms, and based on position, the robot action at the current moment, and the attributes of each type of robot, the robot action at the next moment is generated, so as to obtain the action set corresponding to the robot action at each moment.

[0020] In one exemplary embodiment of this application, determining the location of the target rescue object on a topographic map includes:

[0021] The topographic map is divided into a grid map according to the preset division rules;

[0022] Determine the location of the target rescue object on the grid map.

[0023] In one exemplary embodiment of this application, the target action set includes multiple sub-action sets corresponding to different times, and the sub-action sets include the actions to be executed for each robot.

[0024] In one exemplary embodiment of this application, the robot team includes a first preset number of central robots, a second preset number of transport robots, and a third preset number of operation robots, wherein the central robots are used to command the transport robots and operation robots, the transport robots are used to transport the operation robots, and the operation robots are used to perform specific operations.

[0025] According to one aspect of this application, a robot motion control device is provided, comprising:

[0026] Location determination unit, used to determine the location of the target rescue object on the topographic map;

[0027] The action set generation unit is used to generate the robot action corresponding to the next time step based on the position and the robot action corresponding to the current time step, so as to obtain the action set corresponding to the robot action at each time step;

[0028] The action set selection unit is used to select the target action set based on the excitation value corresponding to each action set.

[0029] The robot control unit is used to control each robot in the robot team to perform its corresponding action in the target action set according to the time sequence in order to reach the location of the target rescue object.

[0030] In one exemplary embodiment of this application, the apparatus further includes:

[0031] The parameter calculation unit is used to calculate the total time measurement function based on the total number of actions of each type of robot in the robot team and the time required to execute the actions, and to calculate the total time consumption incentive value based on the total time measurement function; to calculate the relative distance incentive value based on the relative distance between the operating robot in the robot team and the target rescue object at the final moment; to determine the destination arrival incentive value based on the corresponding position of the robot team; to calculate the step-by-step incentive value based on the robot actions at each moment; and to generate the incentive value corresponding to each action set based on the total time consumption incentive value, relative distance incentive value, destination arrival incentive value, and step-by-step incentive value.

[0032] In one exemplary embodiment of this application, the different types of robots in the robot team correspond to different attributes, including perception ability, passability of different types of areas, range of motion, and speed of motion.

[0033] In one exemplary embodiment of this application, the action set generation unit generates the robot action corresponding to the next time step based on the position and the robot action corresponding to the current time step, so as to obtain the action set corresponding to the robot action at each time step, including:

[0034] By using reinforcement learning algorithms, and based on position, the robot action at the current moment, and the attributes of each type of robot, the robot action at the next moment is generated, so as to obtain the action set corresponding to the robot action at each moment.

[0035] In one exemplary embodiment of this application, the location determination unit determines the location of the target rescue object on the topographic map, including:

[0036] The topographic map is divided into a grid map according to the preset division rules;

[0037] Determine the location of the target rescue object on the grid map.

[0038] In one exemplary embodiment of this application, the target action set includes multiple sub-action sets corresponding to different times, and the sub-action sets include the actions to be executed for each robot.

[0039] In one exemplary embodiment of this application, the robot team includes a first preset number of central robots, a second preset number of transport robots, and a third preset number of operation robots, wherein the central robots are used to command the transport robots and operation robots, the transport robots are used to transport the operation robots, and the operation robots are used to perform specific operations.

[0040] According to one aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method of any one of the above.

[0041] According to one aspect of this application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of any one of the above via executing the executable instructions.

[0042] The exemplary embodiments of this application may have some or all of the following beneficial effects:

[0043] In a robot motion control method provided in an example embodiment of this application, the location of the target rescue object on a terrain map can be determined; the robot motion corresponding to the next time moment can be generated based on the location and the robot motion corresponding to the current time moment to obtain a motion set corresponding to the robot motion at each time moment; a target motion set can be selected according to the excitation value corresponding to each motion set; and each robot in the robot team can be controlled to execute the corresponding motion in the target motion set in a time sequence to reach the location of the target rescue object. This allows the generation of the robot motion corresponding to the next time moment based on the location and the robot motion corresponding to the current time moment, thus obtaining a motion set. The robots can reach the location requiring rescue by executing the motions in the motion set, thereby completing the rescue task. In this application, the optimal target motion set can be selected based on the excitation value corresponding to each motion set, and the robots in the robot team can complete the rescue task more efficiently by executing the motions in the target motion set, which is beneficial to improving rescue efficiency.

[0044] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0046] Figure 1 A flowchart illustrating a robot motion control method according to an embodiment of this application is shown schematically.

[0047] Figure 2 A flowchart illustrating a robot motion control method according to another embodiment of this application is shown schematically;

[0048] Figure 3 This illustration schematically depicts an application scenario according to an embodiment of the present application;

[0049] Figure 4 A schematic block diagram of a robot motion control device according to one embodiment of the present application is shown.

[0050] Figure 5 The schematic diagram illustrates the structure of a computer system suitable for implementing the electronic devices of the present application. Detailed Implementation

[0051] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of the embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this application.

[0052] Furthermore, the accompanying drawings are merely illustrative of this application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0053] Please see Figure 1 , Figure 1 A flowchart illustrating a robot motion control method according to an embodiment of this application is shown schematically. Figure 1 As shown, the robot motion control method may include steps S110 to S140.

[0054] Step S110: Determine the location of the target rescue object on the topographic map.

[0055] Step S120: Generate the robot action corresponding to the next time step based on the position and the robot action corresponding to the current time step, so as to obtain the action set corresponding to the robot action at each time step.

[0056] Step S130: Select the target action set according to the excitation value corresponding to each action set.

[0057] Step S140: Control each robot in the robot team to execute its corresponding action in the target action set according to the time sequence in order to reach the location of the target rescue object.

[0058] Implementation Figure 1 The method shown can generate the robot action corresponding to the next moment based on the position and the robot action corresponding to the current moment, thereby obtaining an action set. The robot can reach the location that needs rescue by executing the actions in the action set, thereby completing the rescue task. In this application, the optimal target action set can be selected according to the excitation value corresponding to each action set. The robots in the robot team can complete the rescue task more efficiently by executing the actions in the target action set, which is conducive to improving rescue efficiency.

[0059] The steps described above in this example implementation will now be explained in more detail.

[0060] In step S110, the location of the target rescue object on the topographic map is determined.

[0061] Specifically, the target rescue object can be a person, an object, etc., and this application embodiment is not limited to this. Furthermore, the topographic map can be a real-time image taken from a top-down perspective or an image taken from other perspectives; this application embodiment is not limited to this either. The topographic map can be taken by a detector or by other devices. Moreover, the position of the target rescue object on the topographic map can be represented with arbitrary precision, such as a coordinate position or a region.

[0062] In step S120, the robot action corresponding to the next time step is generated based on the position and the robot action corresponding to the current time step, so as to obtain the action set corresponding to the robot action at each time step.

[0063] Specifically, the robot action at the current moment (e.g., moving 1m to the left) and the robot action at the next moment can be the same or different. At the same moment, the actions of different robots in the robot team can also be different.

[0064] In step S130, the target action set is selected according to the excitation value corresponding to each action set.

[0065] Specifically, the incentive value corresponding to each action set is used to quantify the benefit effect of the corresponding action set, and the target action set can be the action set with the largest incentive value.

[0066] In step S140, each robot in the control robot team executes its corresponding action in the target action set according to the time sequence in order to reach the location of the target rescue object.

[0067] Specifically, the target action set contains the sub-action set corresponding to each moment, and each sub-action set contains the action corresponding to each robot at that moment.

[0068] As an optional embodiment, the method further includes: calculating a total time measurement function based on the total number of actions of each type of robot in the robot team and the time required to execute the actions, and calculating a total time consumption incentive value based on the total time measurement function; calculating a relative distance incentive value based on the relative distance between the operating robot in the robot team and the target rescue object at the final moment; determining a destination arrival incentive value based on the corresponding position of the robot team; calculating a step-by-step incentive value based on the robot actions at each moment; and generating incentive values ​​corresponding to each action set based on the total time consumption incentive value, relative distance incentive value, destination arrival incentive value, and step-by-step incentive value. This effectively calculates incentive values ​​that characterize the benefits of action sets, allowing the selection of the optimal action set. The robot team executing the optimal action set can thus more efficiently complete the rescue mission.

[0069] Optionally, the specific implementation of the total time measurement function based on the total number of actions of each type of robot in the robot team and the time required to execute the actions can be as follows: Determine the total number S of actions of the transport robots in the robot team. trans The total number of actions S performed by robot 1 in the robot team operator1 The total number of actions S performed by robot 2 in the robot team operator2 Determine the time h required for the transport robot to perform its actions. trans Based on expression T overall =S trans *h trans +(S operator1 +S operator2 )*h trans Calculate the total time measurement function T overall Among them, h trans It can be equal to the reciprocal of the transport robot's speed.

[0070] Furthermore, a specific implementation method for calculating the total time consumption incentive value based on the total time measurement function can be as follows: a preset positive real number λ and the total time measurement function T are used... overall Substitute into expression R e =λ / T overall To calculate the total time consumption incentive value R e ; where the positive real number λ is related to the area of ​​the topographic map. Specifically, it can be set to a positive correlation or a negative correlation, which is not limited in the embodiments of this application.

[0071] Furthermore, the specific implementation method for calculating the relative distance excitation value based on the relative distance between the operating robot and the target rescue object at the final moment in the robot team can be as follows: determine the relative distance d between the operating robot and the target rescue object based on the position of the operating robot in the robot team. i , i = 1, 2, ..., n, where n is a positive integer, d i Used to represent the relative distance between the i-th operating robot and the target rescue object; based on the expression The destination arrival incentive value R can be calculated. d γ is a positive real number. The final moment can be determined when the task is completed, the robot enters an unsuitable movement area, or the total time exceeds a set threshold.

[0072] Furthermore, the specific implementation of determining the destination arrival incentive value based on the location of the robot team can be as follows: determine whether a designated robot (e.g., the operating robot) in the robot team has reached the destination (i.e., the location of the target rescue object) based on the location of the robot team; if so, set the destination arrival incentive value R. fIf the value is set to 100, then the destination arrival incentive value R is set accordingly. f The value is determined to be 0.

[0073] Furthermore, the specific implementation method for calculating the step-by-step excitation value based on the robot's actions at each moment can be: through the expression R q =αmaxQ(S) t a) Determine the step-by-step excitation value R q Where α is a positive real number, S t Let 'a' be the quantized robot state at the current moment, 'a' be the quantized robot action at the current moment, and 'Q' represent the preset function.

[0074] As an optional implementation, different types of robots in the robot team correspond to different attributes, including perception capabilities, navigability in various types of areas, range of motion, and speed. This allows for an improvement in the overall rescue capability of the robot team based on the attributes of different robots, thereby enhancing rescue efficiency.

[0075] Specifically, perception capabilities can be quantified. For example, the perception capability of a transport robot can be represented as 50%, and the perception capability of an operating robot can be represented as 100%. Each type of area can include at least: easily passable areas and difficult-to-pass areas. In easily passable areas, the transport robot can carry the operating robot, while in difficult-to-pass areas, the operating robot can pass alone. For example, in easily passable areas, the passability of both the transport robot and the operating robot is 100%, while in difficult-to-pass areas, the passability of the transport robot is 0%, and the passability of the operating robot is 100%. Furthermore, for example, the range of motion and speed of the transport robot can be represented as 100%, and the range of motion and speed of the operating robot can be represented as 10%.

[0076] As an optional implementation, the robot action for the next moment is generated based on the robot's position and the robot action at the current moment, to obtain a set of actions corresponding to the robot actions at each moment. This includes: generating the robot action for the next moment using a reinforcement learning algorithm, based on the position, the robot action at the current moment, and the attributes of each type of robot, to obtain a set of actions corresponding to the robot actions at each moment. This can improve the feasibility of the obtained action set, thereby helping to improve the rescue efficiency of the robot team.

[0077] Specifically, reinforcement learning algorithms (Deep Q-Learning) can perform operations on robot action selection. At each moment of the rescue process, reinforcement learning algorithms (Deep Q-Learning) can select the optimal action for each robot participating in the rescue, so that the entire robot team can reach the rescue location more quickly.

[0078] As an optional embodiment, determining the location of the target rescue object on the topographic map includes: dividing the topographic map into a grid map according to a preset division rule; and determining the location of the target rescue object on the grid map. This can help improve the efficiency of acquiring action sets.

[0079] Specifically, the preset division rules can be represented in any form such as text or strings, and this application embodiment does not limit them. The preset division rules are used to limit the size of the grid, such as 10m*10m. Determining the position of the target rescue object in the grid map includes: determining the target grid to which the target rescue object belongs in the grid map, as the position of the target rescue object.

[0080] As an optional embodiment, the target action set includes multiple sub-action sets corresponding to different times, each sub-action set containing the action to be performed by each robot. This facilitates cooperation between robots in a robot team during rescue operations, increasing the probability of a successful rescue.

[0081] As an optional embodiment, the robot team includes a first preset number of central robots, a second preset number of transport robots, and a third preset number of operating robots. The central robots are used to command the transport robots and operating robots, the transport robots are used to transport the operating robots, and the operating robots are used to perform specific operations. This increases the diversity of robot types within the robot team, thereby improving the success rate of robot rescue operations.

[0082] Specifically, the first preset quantity, the second preset quantity, and the third preset quantity can correspond to the same value or different values, and this application embodiment does not limit this. Furthermore, the central robot, the transport robot, and the operating robot can correspond to different resolutions. For example, the resolution corresponding to the central robot can be zero, the resolution corresponding to the transport robot can be on the order of tens of centimeters, and the resolution corresponding to the operating robot can be on the order of millimeters. Additionally, for example, the central robot's range of motion and average speed are both zero; the transport robot's range of motion is the entire potential rescue map area, and its average speed is 1 m / s; the operating robot's range of motion is 1 / 10 of the potential rescue map area, and its average speed is 5 cm / s. Furthermore, the specific operation performed by the operating robot can be understood as a refined operation, which can be set based on user needs.

[0083] Please see Figure 2 , Figure 2 A flowchart illustrating another embodiment of a robot motion control method according to this application is shown schematically. Figure 2 As shown, the robot motion control method may include steps S210 to S290.

[0084] Step S210: Determine the location of the target rescue object on the topographic map.

[0085] Step S220: Generate the robot action corresponding to the next time step based on the position and the robot action corresponding to the current time step, so as to obtain the action set corresponding to the robot action at each time step.

[0086] Step S230: Calculate the total time measurement function based on the total number of actions of each type of robot in the robot team and the time required to execute the actions, and calculate the total time consumption incentive value based on the total time measurement function.

[0087] Step S240: Calculate the relative distance excitation value based on the relative distance between the operating robot in the robot team and the target rescue object at the final moment.

[0088] Step S250: Determine the destination arrival incentive value based on the location of the robot team.

[0089] Step S260: Calculate the step-by-step excitation value based on the robot's actions at each moment.

[0090] Step S270: Generate the incentive values ​​corresponding to each action set based on the total time consumption incentive value, relative distance incentive value, destination arrival incentive value, and step-by-step incentive value.

[0091] Step S280: Select the target action set according to the excitation value corresponding to each action set.

[0092] Step S290: Control each robot in the robot team to execute its corresponding action in the target action set according to the time sequence in order to reach the location of the target rescue object.

[0093] It should be noted that steps S210 to S290 are related to... Figure 1 For the specific implementation details of steps S210 to S290, please refer to the examples shown. Figure 1 The steps and their embodiments shown are not repeated here.

[0094] It is evident that implementation Figure 2 The method shown can generate the robot action corresponding to the next moment based on the position and the robot action corresponding to the current moment, thereby obtaining an action set. The robot can reach the location that needs rescue by executing the actions in the action set, thereby completing the rescue task. In this application, the optimal target action set can be selected according to the excitation value corresponding to each action set. The robots in the robot team can complete the rescue task more efficiently by executing the actions in the target action set, which is conducive to improving rescue efficiency.

[0095] Please see Figure 3, Figure 3 The illustration shows a schematic diagram of an application scenario according to an embodiment of this application. Figure 3 The topographic map shown can be a real-time image taken by a lunar probe. According to a preset division rule, the topographic map can be divided into a 10m*10m grid. In this grid, area 360 can be a difficult-to-pass area, and other areas outside area 360 can be easy-to-pass areas. The topographic map can specifically include: a constructed central robot 310, a constructed transport robot 320, a constructed operation robot 330, a constructed operation robot 340, and an object to be rescued 350.

[0096] Specifically, the location of the object 350 to be rescued on the terrain map can be determined. Based on the location and the robot action corresponding to the current moment, the robot action corresponding to the next moment is generated to obtain the action set corresponding to the robot actions at each moment. A total time measurement function is calculated based on the total number of actions of each type of robot in the robot team and the time required to execute the actions, and a total time consumption incentive value is calculated based on the total time measurement function. A relative distance incentive value is calculated based on the relative distance between the operating robot in the robot team and the object 350 to be rescued at the final moment. A destination arrival incentive value is determined based on the location corresponding to the robot team. Step-by-step incentive values ​​are calculated based on the robot actions at each moment. Incentive values ​​corresponding to each action set are generated based on the total time consumption incentive value, relative distance incentive value, destination arrival incentive value, and step-by-step incentive values. A target action set is selected based on the incentive values ​​corresponding to each action set. Then, the central robot 310 can control the transport robot 320, the operating robot 330, and the operating robot 340 to execute their respective corresponding actions in the target action set in sequence to reach the location of the object 350 to be rescued, so as to carry out the rescue of the object 350.

[0097] Please see Figure 4 , Figure 4 This schematically illustrates a structural block diagram of a robot motion control device according to one embodiment of the present application. The robot motion control device 400 and... Figure 1 The methods shown correspond to, for example Figure 4 As shown, the robot motion control device 400 includes:

[0098] Location determination unit 401 is used to determine the location of the target rescue object on the topographic map;

[0099] The action set generation unit 402 is used to generate the robot action corresponding to the next time step based on the position and the robot action corresponding to the current time step, so as to obtain the action set corresponding to the robot action at each time step.

[0100] The action set selection unit 403 is used to select a target action set based on the excitation value corresponding to each action set.

[0101] The robot control unit 404 is used to control each robot in the robot team to perform its corresponding action in the target action set according to the time sequence in order to reach the location of the target rescue object.

[0102] It is evident that implementation Figure 4 The device shown can generate robot actions for the next time step based on the robot's position and the robot's actions at the current time step, thereby obtaining a set of actions. The robot can reach the location that needs rescue by executing the actions in the set of actions, thereby completing the rescue mission. In this application, the optimal target set of actions can be selected based on the excitation value corresponding to each set of actions. The robots in the robot team can complete the rescue mission more efficiently by executing the actions in the target set of actions, which is conducive to improving rescue efficiency.

[0103] In one exemplary embodiment of this application, the apparatus further includes:

[0104] The parameter calculation unit is used to calculate the total time measurement function based on the total number of actions of each type of robot in the robot team and the time required to execute the actions, and to calculate the total time consumption incentive value based on the total time measurement function; to calculate the relative distance incentive value based on the relative distance between the operating robot in the robot team and the target rescue object at the final moment; to determine the destination arrival incentive value based on the corresponding position of the robot team; to calculate the step-by-step incentive value based on the robot actions at each moment; and to generate the incentive value corresponding to each action set based on the total time consumption incentive value, relative distance incentive value, destination arrival incentive value, and step-by-step incentive value.

[0105] As can be seen, by implementing this optional embodiment, the incentive value that can characterize the benefit of the action set can be effectively calculated. The optimal action set can be selected through the incentive value. The robot team can complete the rescue mission more efficiently by executing the optimal action set.

[0106] In one exemplary embodiment of this application, the different types of robots in the robot team correspond to different attributes, including perception ability, passability of different types of areas, range of motion, and speed of motion.

[0107] It is evident that implementing this optional embodiment can enhance the overall rescue capabilities of the robot team based on the attributes of different robots, thereby improving rescue efficiency.

[0108] In one exemplary embodiment of this application, the action set generation unit 402 generates the robot action corresponding to the next time step based on the position and the robot action corresponding to the current time step, so as to obtain the action set corresponding to the robot action at each time step, including:

[0109] By using reinforcement learning algorithms, and based on position, the robot action at the current moment, and the attributes of each type of robot, the robot action at the next moment is generated, so as to obtain the action set corresponding to the robot action at each moment.

[0110] It is evident that implementing this optional embodiment can improve the feasibility of the acquired action set, thereby enhancing the rescue efficiency of the robot team.

[0111] In one exemplary embodiment of this application, the location determination unit 401 determines the location of the target rescue object on the topographic map, including:

[0112] The topographic map is divided into a grid map according to the preset division rules;

[0113] Determine the location of the target rescue object on the grid map.

[0114] It is evident that implementing this optional embodiment can help improve the efficiency of obtaining action sets.

[0115] In one exemplary embodiment of this application, the target action set includes multiple sub-action sets corresponding to different times, and the sub-action sets include the actions to be executed for each robot.

[0116] It is evident that implementing this optional embodiment can facilitate cooperation between robots in a robot team during rescue operations, thereby increasing the probability of a successful rescue.

[0117] In one exemplary embodiment of this application, the robot team includes a first preset number of central robots, a second preset number of transport robots, and a third preset number of operation robots, wherein the central robots are used to command the transport robots and operation robots, the transport robots are used to transport the operation robots, and the operation robots are used to perform specific operations.

[0118] As can be seen, implementing this optional embodiment can increase the diversity of robot types in the robot team, thereby increasing the success rate of robot rescue.

[0119] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0120] Since the functional modules of the robot motion control device in the example embodiments of this application correspond to the steps of the example embodiments of the robot motion control method described above, for details not disclosed in the device embodiments of this application, please refer to the embodiments of the robot motion control method described above in this application.

[0121] Please see Figure 5 , Figure 5 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0122] It should be noted that, Figure 5 The computer system 500 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0123] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for system operation. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0124] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0125] Specifically, according to embodiments of this application, the processes described in the above-described flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the various functions defined in the methods and apparatus of this application.

[0126] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0127] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0129] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0130] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the foregoing claims.

Claims

1. A robot motion control method, characterized in that, include: Determine the location of the target rescue object on the topographic map; Based on the position and the robot action corresponding to the current time, generate the robot action corresponding to the next time, so as to obtain the action set corresponding to the robot action at each time. Select the target action set based on the incentive value corresponding to each action set; The robot team controls each robot to execute its corresponding action in the target action set according to a time sequence in order to reach the location of the target rescue object; wherein, the robot team includes a first preset number of central robots, a second preset number of transport robots, and a third preset number of operation robots, wherein the central robots are used to command the transport robots and the operation robots, the transport robots are used to transport the operation robots, and the operation robots are used to perform specific operations; The method further includes: A total time measurement function is calculated based on the total number of actions of each type of robot in the robot team and the time required to execute the actions, and the total time consumption incentive value is calculated based on the total time measurement function. The relative distance excitation value is calculated based on the relative distance between the operating robot in the robot team and the target rescue object at the final moment; The destination arrival incentive value is determined based on the location of the robot team. Calculate the step-by-step excitation value based on the robot's actions at each moment; The incentive values ​​corresponding to each action set are generated based on the total time consumption incentive value, the relative distance incentive value, the destination arrival incentive value, and the step-by-step incentive value.

2. The method according to claim 1, characterized in that, in: The robot team consists of different types of robots with different attributes, including perception ability, passability in various types of areas, range of motion, and speed of motion.

3. The method according to claim 2, characterized in that, Based on the position and the robot action corresponding to the current time, generate the robot action corresponding to the next time moment to obtain the action set corresponding to the robot action at each time moment, including: By using reinforcement learning algorithms, and based on the position, the robot action corresponding to the current moment, and the attributes of each type of robot, the robot action corresponding to the next moment is generated, so as to obtain the action set corresponding to the robot action at each moment.

4. The method according to claim 1, characterized in that, Determine the location of the target rescue object on the topographic map, including: The topographic map is divided into a grid map according to a preset division rule; Determine the location of the target rescue object on the grid map.

5. The method according to claim 1, characterized in that, in: The target action set includes multiple sub-action sets corresponding to different times, and each sub-action set includes the action to be executed for each robot.

6. A robot motion control device, characterized in that, include: Location determination unit, used to determine the location of the target rescue object on the topographic map; An action set generation unit is used to generate a robot action corresponding to the next time step based on the position and the robot action corresponding to the current time step, so as to obtain an action set corresponding to the robot action at each time step. The action set selection unit is used to select the target action set based on the excitation value corresponding to each action set. A robot control unit is used to control each robot in the robot team to execute its corresponding action in the target action set according to the time sequence, so as to reach the location of the target rescue object; wherein, the robot team includes a first preset number of central robots, a second preset number of transport robots, and a third preset number of operation robots, wherein the central robots are used to command the transport robots and the operation robots, the transport robots are used to transport the operation robots, and the operation robots are used to perform specific operations; The parameter calculation unit is used to calculate the total time measurement function based on the total number of actions of each type of robot in the robot team and the time required to execute the actions, and to calculate the total time consumption incentive value based on the total time measurement function; to calculate the relative distance incentive value based on the relative distance between the operating robot in the robot team and the target rescue object at the final moment; to determine the destination arrival incentive value based on the corresponding position of the robot team; to calculate the step-by-step incentive value based on the robot actions at each moment; and to generate the incentive value corresponding to each action set based on the total time consumption incentive value, relative distance incentive value, destination arrival incentive value, and step-by-step incentive value.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-6.

8. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1-6 by executing the executable instructions.

Images