Anti-falling control method and device of quadruped robot in tunnel scene

Abstract

The application provides a fall-prevention control method and device for a quadruped robot in a tunnel scene. The method is based on point cloud depth data obtained by a laser radar, and then a first motion strategy model trained by inputting a DQN algorithm and a second motion strategy model containing a SLAM positioning and navigation module are used to obtain a marching strategy of the quadruped robot. The problem that the quadruped robot cannot work after falling due to a tunnel and a high platform in the prior art in the power cable tunnel scene is solved.

Description

Technical Field

[0001] The present invention relates to the field of robot control, and in particular to a method for preventing a quadruped robot from falling in a tunnel scenario, an anti-fall control device for a quadruped robot in a tunnel scenario, a computer-readable storage medium, a processor, and an electronic device. Background Art

[0002] Power equipment is a vital pillar of modern society, and maintenance technology that ensures the safe operation of power equipment is a key technology in my country's power industry. New robotics technologies have enormous application potential and demand in complex and hazardous operating scenarios within the power industry. As my country's power system becomes increasingly complex, the requirements for maintenance technology, safety assurance, and intelligence for power equipment are gradually increasing, and the application of new robotics technologies in this field will become more extensive and in-depth. However, this field often faces harsh operating environments and multiple potential hazards. Equipment maintenance and inspection work requires highly specialized personnel in high-risk environments, presenting a series of technical and operational challenges such as personal safety hazards and low efficiency. These challenges increase the urgency and importance of the research and development of key technologies for new robotic maintenance of power equipment. Therefore, key technologies such as new robotic operation, maintenance, and inspection of power equipment will be a key focus for my country's power industry.

[0003] Power cables and tunnels are the primary means of transmitting and securing electricity for the capital's power grid. Due to historical factors, some tunnels are aging and in disrepair. Furthermore, the harsh underground environment makes inspections difficult and risky, and traditional inspection methods require significant human and material resources.

[0004] Quadruped robots, with their superior obstacle-crossing and adaptive capabilities, have significantly lower requirements for ground conditions than wheeled robots, and hold great promise for application in cable tunnels. However, in narrow power cable tunnels, particularly in tunnels with existing tunnels, if a quadruped robot falls, it can become unable to operate autonomously, necessitating manual intervention, which is time-consuming and labor-intensive, significantly impacting the stability and efficiency of the robot's autonomous inspections. Therefore, minimizing the probability of a quadruped robot falling from a high platform into a tunnel and improving its operational reliability under uncertain conditions are key to improving inspection efficiency in cable tunnels. Summary of the Invention

[0005] The main purpose of this application is to provide an anti-fall control method for a quadruped robot in a tunnel scenario, an anti-fall control device for a quadruped robot in a tunnel scenario, a computer-readable storage medium and a quadruped robot, so as to at least solve the problem in the prior art that in a power cable tunnel scenario, the quadruped robot cannot work after falling due to tunnels and platforms.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a fall prevention control method for a quadruped robot in a tunnel scene is provided, including: acquiring point cloud data centered on the quadruped robot through a laser radar to obtain point cloud depth data; inputting the point cloud depth data into a first motion strategy model to obtain a first moving strategy, the first moving strategy at least including the angular velocity and linear velocity of the quadruped robot, the first motion strategy model is a model trained based on the DQN algorithm to generate a moving mode based on the surrounding environment of the quadruped robot; inputting the point cloud depth data into a second motion strategy model to obtain a second moving strategy, the second moving strategy at least including the angular velocity and linear velocity of the quadruped robot, the second motion strategy model includes a SLAM positioning module and a navigation module; performing a weighted average operation based on the first moving strategy and the second moving strategy to obtain a target control strategy, and controlling the movement of the quadruped robot according to the target control strategy.

[0007] Optionally, before inputting the point cloud depth data into the first motion strategy model, the method further includes: obtaining the tunnel width, the pit width and the distance between the quadruped robot and the tunnel wall on one side of the pit to obtain a first target distance, a second target distance and a third target distance, obtaining the initial position of the quadruped robot to obtain a first position, obtaining the terminal position of the quadruped robot to obtain a second position; determining the first target distance, the second target distance, the third target distance, the first position and the second position as the initial state of the model; determining the angular velocity and the linear velocity of the quadruped robot as behaviors, and randomly taking values ​​for the angular velocity and the linear velocity to obtain multiple first target behaviors; determining multiple update states based on the initial state and each of the first target behaviors, and performing random updates on each of the update states based on preset rules. The new state is scored to obtain a state reward; the initial state, the first target behavior, the state reward, the updated state, and whether the first position and the second position overlap are determined as an experience group and stored in an experience pool; the neural network is trained based on samples in the experience pool, and the Q value is calculated based on the target Q network, the maximum Q value corresponding to the updated state is determined as the target Q value, the neural network is updated based on the target Q value, and the target Q network is updated based on the neural network at intervals of a first preset number; the updated state is determined as the initial state, and the first target behavior and the updated state and the experience group corresponding to the updated state are regenerated based on the iterated initial state, and the neural network is trained according to the iterated updated state and the experience group until the number of iterations reaches a second preset number, thereby obtaining the first motion strategy model.

[0008] Optionally, before scoring each of the updated states based on preset rules and obtaining a state reward, the method further includes: calculating the product of the first target distance and a first preset coefficient to obtain a fourth target distance, and calculating the product of the second target distance and a second preset coefficient to obtain a fifth target distance; determining the first preset rule as follows: when the third target distance in the updated state is less than or equal to the fifth target distance, determining the first preset score as the state reward; determining the second preset rule as follows: when the third target distance in the updated state is greater than the fifth target distance and less than the fourth target distance, determining the second preset score as the state reward; determining the third preset rule as follows: when the third target distance in the updated state is greater than or equal to the fourth target distance, determining the second preset score as the state reward; determining the third preset rule as follows: when the third target distance in the updated state is greater than or equal to the fourth target distance determining a fourth preset rule as, when the distance between the first position and the second position decreases in the updated state, determining the fourth preset score as the state reward; determining a fifth preset rule as, when the distance between the first position and the second position increases in the updated state, determining the fifth preset score as the state reward; determining a sixth preset rule as, when the quadruped robot collides in the updated state, determining the first preset score as the state reward, the first preset score is less than the fifth preset score, the fifth preset score is less than the third preset score, the third preset score is less than the fourth preset score, and the fourth preset score is less than the second preset score.

[0009] Optionally, the point cloud depth data is input into a first motion strategy model to obtain a first moving strategy, including: updating the first target distance, the second target distance and the third target distance based on the point cloud depth data; determining the first position and the second position based on the point cloud depth data; determining the first target distance, the second target distance, the third target distance, the first position and the second position as the current state; randomly generating the moving angular velocity and the moving linear velocity of the quadruped robot based on the current state to obtain multiple alternative moving strategies; determining the corresponding predicted state based on the current state and each of the alternative moving strategies, and determining the state reward corresponding to the predicted state to obtain an alternative strategy score; determining the alternative moving strategy corresponding to the maximum value of the alternative strategy score as the first moving strategy.

[0010] Optionally, the point cloud depth data is input into a second motion strategy model to obtain a second movement strategy, including: inputting the point cloud depth data into the SLAM positioning module to obtain the current posture of the quadruped robot and a target map constructed based on the point cloud depth data; inputting the current posture and the target map into the navigation module to predict the movement angular velocity and the movement linear velocity of the quadruped robot within a preset time length to obtain the second movement strategy.

[0011] Optionally, the point cloud depth data is input into the SLAM positioning module to obtain the current posture of the quadruped robot and a target map constructed based on the point cloud depth data, including: performing feature extraction on the point cloud depth data based on the SLAM algorithm, determining the points therein that match the preset objects, and obtaining key feature points; determining the key feature points obtained when the point cloud depth data was last extracted as comparison feature points, and determining the travel trajectory of the quadruped robot based on the key feature points and the comparison feature points; performing map reconstruction based on the key feature points and the travel trajectory to obtain the target map; determining the current position and travel direction of the quadruped robot based on the target map and the key feature points to obtain the current posture.

[0012] Optionally, after controlling the movement of the quadruped robot according to the target control strategy, the method further includes: re-collecting the point cloud depth data at every preset time interval, and updating the target control strategy through the first motion strategy model and the second motion strategy model based on the point cloud depth data; and controlling the movement of the quadruped robot according to the updated target control strategy.

[0013] According to another aspect of the present application, an anti-fall control device for a quadruped robot in a tunnel scene is provided, the device comprising: a first acquisition unit, for acquiring point cloud data centered on the quadruped robot through a laser radar to obtain point cloud depth data; a first input unit, for inputting the point cloud depth data into a first motion strategy model to obtain a first moving strategy, the first moving strategy at least including the moving angular velocity and the moving linear velocity of the quadruped robot, the first motion strategy model being a model trained based on a DQN algorithm and generating a moving mode based on the surrounding environment of the quadruped robot; a second input unit, for inputting the point cloud depth data into a second motion strategy model to obtain a second moving strategy, the second moving strategy at least including the moving angular velocity and the moving linear velocity of the quadruped robot, the second motion strategy model including a SLAM positioning module and a navigation module; a first calculation unit, for performing a weighted average operation based on the first moving strategy and the second moving strategy to obtain a target control strategy, and controlling the movement of the quadruped robot according to the target control strategy.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0015] According to another aspect of the present application, a quadruped robot is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0016] Applying the technical solution of this application, first, a laser radar is used to obtain point cloud data centered on the quadruped robot to obtain point cloud depth data; then, the point cloud depth data is input into a first motion strategy model to obtain a first moving strategy, wherein the first moving strategy at least includes the angular velocity and linear velocity of the quadruped robot, and the first motion strategy model is a model trained based on the DQN algorithm to generate a moving mode based on the surrounding environment of the quadruped robot; then, the point cloud depth data is input into a second motion strategy model to obtain a second moving strategy, wherein the second moving strategy at least includes the angular velocity and linear velocity of the quadruped robot, and the second motion strategy model includes a SLAM positioning module and a navigation module; finally, a weighted average operation is performed based on the first and second moving strategies to obtain a target control strategy, and the movement of the quadruped robot is controlled according to the target control strategy. This application is based on the point cloud depth data obtained by the laser radar, and then obtains the moving strategy of the quadruped robot by inputting a first motion strategy model trained using the DQN algorithm and a second motion strategy model including a SLAM positioning and navigation module. The present invention solves the problem in the prior art that in power cable tunnel scenarios, a quadruped robot cannot work after falling due to pits and high platforms. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The following is a hardware structure block diagram of a mobile terminal for anti-fall control of a quadruped robot in a tunnel scenario according to an embodiment of the present application;

[0018] Figure 2 A schematic flow chart of a method for preventing a quadruped robot from falling in a tunnel scenario according to an embodiment of the present application is shown;

[0019] Figure 3 A flowchart of a method for preventing a quadruped robot from falling in a tunnel scenario according to an embodiment of the present application is shown;

[0020] Figure 4A structural block diagram of an anti-fall control device for a quadruped robot in a tunnel scenario provided according to an embodiment of the present application is shown.

[0021] The above drawings include the following reference numerals:

[0022] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] As introduced in the background technology, in the prior art, in some tunnel scenarios, the presence of tunnel factors will cause the quadruped robot to be unable to work autonomously once it falls, and can only be manually intervened, which is time-consuming and labor-intensive. In order to solve the problem in the prior art that in power cable tunnel scenarios, the quadruped robot cannot work after falling due to tunnels and platforms, the embodiments of the present application provide an anti-fall control method for a quadruped robot in a tunnel scenario, an anti-fall control device for a quadruped robot in a tunnel scenario, a computer-readable storage medium and a quadruped robot.

[0027] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method for preventing a quadruped robot from falling in a tunnel scenario according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0029] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the device information display method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned networks include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] In this embodiment, a method for preventing a quadruped robot from falling in a tunnel scenario is provided, which runs on a mobile terminal, a computer terminal, or a similar computing device. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 2 This is a flowchart of a method for preventing a quadruped robot from falling in a tunnel scenario according to an embodiment of the present application.

[0032] like Figure 2 As shown, the method includes the following steps:

[0033] Step S201, acquiring point cloud data centered on the quadruped robot through a laser radar to obtain point cloud depth data;

[0034] Specifically, a lidar is installed on the body of the quadruped robot to measure the distance to surrounding obstacles. Point cloud data is obtained through the lidar. After preprocessing, depth data on both sides of the robot is obtained. The point cloud depth data is published through the ROS node. Relevant nodes can obtain the above point cloud depth data by subscribing to the ROS node. The point cloud data centered on the quadruped robot is obtained through the lidar, and then the depth data of the surrounding environment is obtained.

[0035] Step S202: Input the point cloud depth data into a first motion strategy model to obtain a first movement strategy. The first movement strategy at least includes the angular velocity and linear velocity of the quadruped robot. The first motion strategy model is a model trained based on the DQN algorithm that generates a movement pattern based on the quadruped robot's surrounding environment.

[0036] Specifically, a first motion strategy model, which generates a movement pattern based on the quadruped robot's surroundings, is trained using the DQN algorithm. Inputting point cloud depth data yields a first movement strategy, including angular and linear velocity. This strategy rapidly generates movement patterns based on the real-time environment, improving the quadruped robot's responsiveness in dynamic environments.

[0037] Step S203: input the point cloud depth data into a second motion strategy model to obtain a second movement strategy, wherein the second movement strategy at least includes the movement angular velocity and the movement linear velocity of the quadruped robot, and the second motion strategy model includes a SLAM positioning module and a navigation module;

[0038] Specifically, the second motion strategy model includes a SLAM positioning module and a navigation module. Taking the same point cloud depth data as input, it generates a second motion strategy, including angular velocity and linear velocity. This strategy offers higher precision in positioning and navigation, ensuring the quadruped robot's path planning capabilities in complex environments.

[0039] Step S204 , performing a weighted average operation based on the first moving strategy and the second moving strategy to obtain a target control strategy, and controlling the movement of the quadruped robot according to the target control strategy.

[0040] Specifically, the first and second driving strategies are combined through a weighted average method to generate a target control strategy. This approach optimizes the complementary advantages and disadvantages of the strategies, enhancing the synergy between the quadruped robot's environmental perception, path planning, and motion control, and further enhancing its autonomy and adaptability in complex environments. Based on the target control strategy, the quadruped robot's motion is precisely controlled.

[0041] Thus, the embodiment of the present application provides an anti-fall control method for a quadruped robot in a tunnel scenario. First, point cloud data centered on the quadruped robot is acquired through a laser radar to obtain point cloud depth data. Then, the point cloud depth data is input into a first motion strategy model to obtain a first moving strategy. The first moving strategy at least includes the angular velocity and linear velocity of the quadruped robot. The first motion strategy model is a model trained based on the DQN algorithm and generates a moving mode based on the surrounding environment of the quadruped robot. Then, the point cloud depth data is input into a second motion strategy model to obtain a second moving strategy. The second moving strategy at least includes the angular velocity and linear velocity of the quadruped robot. The second motion strategy model includes a SLAM positioning module and a navigation module. Finally, a weighted average operation is performed based on the first and second moving strategies to obtain a target control strategy, and the quadruped robot movement is controlled according to the target control strategy. This application is based on the point cloud depth data acquired by the laser radar, and then by inputting the first motion strategy model trained using the DQN algorithm and the second motion strategy model including the SLAM positioning and navigation modules, respectively, to obtain a moving strategy for the quadruped robot. The present invention solves the problem in the prior art that in power cable tunnel scenarios, a quadruped robot cannot work after falling due to pits and high platforms.

[0042] As a possible implementation, before inputting the point cloud depth data into the first motion strategy model, the method further includes the following steps:

[0043] Step S301, obtaining the tunnel width, the pit width, and the distance between the quadruped robot and the tunnel wall on one side of the pit, obtaining a first target distance, a second target distance, and a third target distance, obtaining an initial position of the quadruped robot to obtain a first position, obtaining an end position of the quadruped robot to obtain a second position;

[0044] Specifically, this process involves data collection and processing from sensors, obtaining information about the surrounding environment through devices such as lidar, and providing a basis for subsequent data analysis and model training.

[0045] Step S302, determining the first target distance, the second target distance, the third target distance, the first position, and the second position as the initial state of the model;

[0046] Specifically, the initial state is set as the operating benchmark for the robot in a specific environment, laying the foundation for subsequent motion strategy generation.

[0047] Step S303, determining the angular velocity and linear velocity of the quadruped robot as behaviors, and randomly taking values ​​of the angular velocity and linear velocity to obtain a plurality of first target behaviors;

[0048] Specifically, this step generates multiple possible movement strategies through random sampling, providing data support for the model to explore different movement schemes.

[0049] Step S304: determining multiple updated states based on the initial state and each first target behavior, scoring each updated state based on a preset rule, and obtaining a state reward;

[0050] Specifically, by defining scoring rules, the effect of each behavior can be quantitatively evaluated so as to optimize the model in subsequent training.

[0051] Step S305: Determine the initial state, the first target behavior, the state reward, the updated state, and whether the first position and the second position overlap as an experience group and store it in the experience pool;

[0052] Specifically, the experience groups saved in the experience pool will provide a rich data basis for subsequent neural network training and promote knowledge accumulation in the learning process.

[0053] Step S306: training a neural network based on samples in the experience pool, calculating a Q value based on a target Q network, determining the maximum Q value corresponding to the updated state as the target Q value, updating the neural network based on the target Q value, and updating the target Q network based on the neural network at intervals of a first preset number of times;

[0054] Specifically, this process involves the Q-learning mechanism in deep reinforcement learning, which improves the decision-making ability of the model by continuously updating network parameters.

[0055] In step S307, the updated state is determined as the initial state, and the first target behavior and the updated state and the experience group corresponding to the updated state are regenerated based on the iterated initial state, and the neural network is trained according to the iterated updated state and the experience group until the number of iterations reaches a second preset number, thereby obtaining a first motion strategy model.

[0056] Specifically, through state updates and behavior adjustments in the iterative process, the output of the model is continuously optimized, so that the generated first motion strategy can better adapt to the actual needs in complex environments.

[0057] Through the above steps, the final first motion strategy model not only takes environmental factors into account, but also can dynamically adjust the movement strategy to adapt to different obstacles and spatial constraints, thereby improving the flexibility and stability of the quadruped robot in different walking environments.

[0058] As a possible implementation, before scoring each updated status based on preset rules and obtaining status rewards, the method further includes the following steps:

[0059] Step S401, calculating the product of the first target distance and the first preset coefficient to obtain the fourth target distance, and calculating the product of the second target distance and the second preset coefficient to obtain the fifth target distance;

[0060] Specifically, by setting different preset coefficients, the target distance can be weighted, introducing adaptability to different scenarios. For example, if the environment is complex, the first preset coefficient can be set to a smaller value, allowing the fourth target distance to have a larger safety margin. This dynamic adjustment of the target distance can better reflect the actual environmental obstacles encountered, ensuring the robot's path planning is flexible and responsive.

[0061] Step S402, determining the first preset rule is that, when the third target distance in the update state is less than or equal to the fifth target distance, the first preset score is determined as the state reward;

[0062] Specifically, this means that when the distance between the robot and the obstacle is less than the safe distance, the lowest score is given, encouraging the robot to maintain the safe range and avoid potential collisions. This rule ensures that the robot will try to maintain a safe distance when approaching obstacles, thereby improving operational safety.

[0063] Step S403, determining the second preset rule as follows: if the third target distance is greater than the fifth target distance and less than the fourth target distance in the updated state, determining the second preset score as the state reward;

[0064] Specifically, a reward is given when the robot navigates within a relatively safe boundary. At this point, while still within a safe range despite being far from obstacles, this rule encourages the robot to maintain a stable speed and direction, enhancing path planning flexibility. This scoring mechanism also enhances the robot's ability to self-adjust its behavior, making it more adaptable in complex environments.

[0065] Step S404, determining the third preset rule is that if the third target distance in the updated state is greater than or equal to the fourth target distance, the third preset score is determined as the state reward;

[0066] Specifically, this rule aims to encourage robots to stay away from potentially dangerous areas. Effective distance management between existing obstacles and targets allows robots to earn more rewards by moving to safer areas, ensuring that robots avoid sharp turns and other unsafe behaviors, thereby enhancing their stability.

[0067] Step S405, determining the fourth preset rule is that when the distance between the first position and the second position decreases in the updated state, the fourth preset score is determined as the state reward;

[0068] Specifically, this rule ensures that sufficient rewards are given as the robot approaches the target location, encouraging it to move toward the target. Reducing distance not only improves travel efficiency but also promotes optimal path selection, reducing travel time and energy consumption, and accelerating task completion.

[0069] Step S406, determining the fifth preset rule as follows: when the distance between the first position and the second position increases in the updated state, determining the fifth preset score as a state reward;

[0070] Specifically, this rule prevents the robot from straying from the target point, reducing the risk of unexpected situations. If the distance continues to increase, this indicates that the robot's path selection is inappropriate, which will negatively impact the overall mission. Therefore, this reward system is designed to warn the robot to adjust its direction in a timely manner.

[0071] Step S407, determining the sixth preset rule: when the quadruped robot collides in the update state, determining the first preset score as the state reward, the first preset score is less than the fifth preset score, the fifth preset score is less than the third preset score, the third preset score is less than the fourth preset score, and the fourth preset score is less than the second preset score.

[0072] Specifically, by setting the penalty for collisions to the lowest possible score, this emphasizes the importance of warning during path planning. This rule not only helps the robot recognize the severity of a collision but also prompts it to reflect on and adjust its driving strategy to avoid similar situations in the future. This creates a positive feedback mechanism, allowing the robot to gradually learn and optimize its behavioral strategies, enabling it to interact more intelligently with its environment.

[0073] Through these steps, pre-set rules can effectively manage the robot's safety and efficiency in complex environments, enabling it to make autonomous decisions in dynamically changing environments, reducing collision risks and improving movement efficiency. Furthermore, this detailed evaluation system provides reliable feedback for subsequent action optimization, profoundly benefiting the training of deep learning models.

[0074] As a possible implementation, inputting the point cloud depth data into the first motion strategy model to obtain the first moving strategy includes the following steps:

[0075] Step S501, updating the first target distance, the second target distance, and the third target distance based on the point cloud depth data;

[0076] Specifically, the robot uses the depth data from the point cloud scan to update the distance parameters in front of it, to its left and right (i.e., the first, second, and third target distances) in real time. By updating these distance parameters, the robot can quickly respond to dynamic changes in its surroundings. For example, when it detects an approaching obstacle, it can adjust its distance in a timely manner to prevent collisions and ensure safe movement.

[0077] Step S502, determining a first position and a second position based on the point cloud depth data;

[0078] Specifically, point cloud data combined with SLAM technology accurately determines the robot's current position (first position) and target position (second position). This step provides accurate information about the robot's current posture and target point. This information is used to guide the robot's path planning, enabling it to select the optimal path based on its current state and target position, thereby improving navigation accuracy and efficiency.

[0079] Step S503, determining the first target distance, the second target distance, the third target distance, the first position, and the second position as the current state;

[0080] Specifically, all key environmental information and robot states are combined into a single, integrated state description. This step provides a comprehensive, up-to-date picture of the current state, encompassing both environmental perception and pose information. The model relies on this detailed information for policy generation and decision-making, ensuring that the path planning strategy is both responsive and robust.

[0081] Step S504, randomly generating the angular velocity and linear velocity of the quadruped robot based on the current state to obtain multiple alternative moving strategies;

[0082] Specifically, based on the current state information, multiple sets of candidate angular and linear velocities are randomly generated. These alternative strategies ensure diverse and exploratory paths, preventing the robot from becoming trapped in local optima and improving the adaptability and robustness of the entire system. Different speed combinations ensure that the robot can try multiple possible movement methods in a changing environment, ultimately finding the optimal strategy.

[0083] Step S505: Determine the corresponding predicted state based on the current state and each alternative driving strategy, and determine the state reward corresponding to the predicted state to obtain the alternative strategy score;

[0084] Specifically, the model predicts future states based on the current state and each set of candidate strategies, and then scores these states. This scoring is based on pre-set state-reward rules, comprehensively evaluating factors such as robot safety, path efficiency, and target proximity. This process, by simulating various possible future states, helps the robot weigh the pros and cons of each candidate strategy, improving the rationality and effectiveness of strategy selection.

[0085] Step S506 : Determine the alternative traveling strategy corresponding to the maximum alternative strategy score as the first traveling strategy.

[0086] Specifically, the strategy with the highest score among all candidate strategies is selected as the primary strategy. This decision-making process ensures that the robot selects the safest and most efficient strategy. By selecting the best from the best, it significantly improves the success rate of path planning and travel efficiency. This strategy optimization process enables the robot to find the optimal path in complex and changing environments when performing tasks.

[0087] Through the detailed steps described above, the first motion strategy model not only responds quickly to real-time point cloud data but also generates an efficient and safe movement strategy based on accurate environmental perception. This approach provides powerful technical support for the quadruped robot's autonomous navigation in complex environments, ensuring its excellent adaptability and reliability in various tasks.

[0088] As a possible implementation method, the point cloud depth data is input into the second motion strategy model to obtain the second movement strategy, including the following steps:

[0089] Step S601: input the point cloud depth data into the SLAM positioning module to obtain the current posture of the quadruped robot and the target map constructed based on the point cloud depth data;

[0090] Specifically, SLAM (Simultaneous Localization and Mapping) technology processes real-time point cloud depth data to determine the robot's current precise pose (including position and orientation) and environmental map. This step ensures that the robot can accurately perceive its current environment and its own precise position. SLAM not only constructs a detailed map of the surrounding environment but also improves the accuracy of pose estimation and the reliability of the map through loop closure detection and pose graph optimization, providing a solid foundation for the navigation module.

[0091] Step S602: Input the current position and target map into the navigation module to predict the angular velocity and linear velocity of the quadruped robot within a preset time period to obtain a second moving strategy.

[0092] Specifically, the navigation module receives the current position and the constructed target map and uses this information to plan a path. By predicting the angular and linear velocities for a preset time period in the future, the model can evaluate the potential outcomes of different strategies. This allows the navigation module to generate the optimal strategy by comprehensively considering factors such as obstacles in the actual environment, feasible paths, and the robot's kinematic performance.

[0093] Through these steps, the second motion strategy model fully leverages real-time point cloud data and SLAM technology to generate an efficient and stable path planning strategy. This approach has proven successful in autonomous navigation tasks for quadruped robots, enabling them to navigate complex and changing environments and complete tasks safely and efficiently.

[0094] As a possible implementation method, the point cloud depth data is input into the SLAM positioning module to obtain the current position of the quadruped robot and the target map built based on the point cloud depth data, including the following steps:

[0095] Step S701: extracting features from the point cloud depth data based on the SLAM algorithm, determining points that match the preset objects, and obtaining key feature points;

[0096] Specifically, at this stage, the SLAM algorithm first processes the input point cloud data and extracts key points that represent the characteristics of the environment. These feature points are the basis for the robot to identify and locate in the environment, and usually include the edges of walls, corners of obstacles, specific patterns, etc. These key feature points can not only effectively describe different environmental areas, but also help the robot understand its location by matching them with known features. The feature extraction process can use various techniques, such as the RANSAC algorithm to remove noise points, or use feature descriptors such as PFH (Point Feature Histograms) to accurately identify object features.

[0097] Step S702: determining the key feature points obtained in the last feature extraction of the point cloud depth data as comparison feature points, and determining the moving trajectory of the quadruped robot based on the key feature points and the comparison feature points;

[0098] Specifically, during this phase, the system matches the currently extracted key feature points with the previously extracted comparison feature points. By calculating the relative positional changes between the current and comparison feature points, the SLAM algorithm can infer the robot's trajectory over time. This trajectory information is crucial for subsequent map reconstruction and pose estimation, helping the robot understand its movement within the environment and effectively update its map and pose information.

[0099] Step S703: Reconstructing a map based on the key feature points and the travel trajectory to obtain a target map;

[0100] Specifically, in this step, the key feature points obtained after matching are combined with the travel trajectory to reconstruct the target map. By performing three-dimensional geometric reconstruction of each feature point in the environment, the SLAM module can construct a map of the robot's environment. The reconstructed map is typically a sparse or dense point cloud model that can more comprehensively reflect the robot's surroundings at a specific moment. The map reconstruction process may use methods such as weighted averaging and B-splines to improve the precision and accuracy of the reconstructed map.

[0101] Step S704: Determine the current position and direction of travel of the robot based on the target map and key feature points to obtain the current posture.

[0102] Specifically, by comprehensively analyzing the reconstructed target map and the currently extracted key feature points, the SLAM algorithm can accurately infer the robot's current position and direction of movement. This process typically involves matching the robot with feature points on the map and optimizing the position estimate using the least squares method to ensure the accuracy and reliability of the current position. Ultimately, the algorithm outputs the robot's current position coordinates (x, y, z) and orientation angles (such as heading and pitch angles), supporting subsequent navigation and movement decisions.

[0103] Through the above steps, the SLAM positioning module efficiently and accurately processes point cloud depth data, helping the quadruped robot continuously update its environmental map and pose information. This process ensures the robot's autonomous navigation in complex environments, enhancing its adaptability and intelligence. This method not only improves the reliability of path planning but also provides important guarantees for the robot to perform various tasks.

[0104] As a possible implementation, after controlling the motion of the quadruped robot according to the target control strategy, the method further includes the following steps:

[0105] Step S801: recollecting point cloud depth data at preset intervals, and updating the target control strategy based on the point cloud depth data using the first motion strategy model and the second motion strategy model;

[0106] Specifically, during this step, the system periodically re-collects point cloud depth data. This new data reflects the real-time dynamic changes in the environment and the robot's new state. Using this collected point cloud depth data, the first and second motion strategy models are re-invoked to generate new control strategies. These strategies each consider the current state and environmental information in different ways to precisely adjust the robot's motion direction and speed in a changing environment. This regular update ensures that strategies are always generated based on the latest data, enabling better response to environmental changes and unexpected situations.

[0107] Step S802: Control the movement of the quadruped robot according to the updated target control strategy.

[0108] Specifically, once new target control policies are generated, the system immediately applies them to control the quadruped's motion. These policies take into account new data and the robot's latest environmental perception, aiming to guide the robot in the most optimal way. This prevents policy staleness and maintains the robot's ability to respond to the environment in real time, ensuring it can continue to perform its mission safely and efficiently.

[0109] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the anti-fall control method of the quadruped robot in the tunnel scenario of the present application will be described in detail below with reference to specific embodiments.

[0110] This embodiment relates to a specific anti-fall control method for a quadruped robot in a tunnel scenario, such as Figure 3 As shown, the following steps are included:

[0111] Step S1: Install a laser radar on the quadruped robot to measure the distance to surrounding obstacles;

[0112] Step S1 includes the following steps:

[0113] Step S11, obtaining point cloud data through laser radar, and obtaining depth data on both sides of the robot after preprocessing;

[0114] Step S12, publishing the point cloud depth data through the ROS node;

[0115] In step S13, relevant nodes can obtain the above point cloud depth data by subscribing to the ROS node.

[0116] Step S2: Based on the reinforcement learning algorithm (DQN), the agent is continuously trial-and-errored through interaction with the environment, and more intelligent decision-making and control of the system is achieved through environmental evaluation feedback.

[0117] Step S2 includes the following steps:

[0118] S21, through pre-measurement, the average width of the tunnel is d, and the average width of the pit is s;

[0119] S22, the reinforcement learning algorithm module (DQN) subscribes to the above node, obtains environmental information for training, traverses the point cloud depth data, and obtains the minimum value x. The specific process of DQN (supplemented in point 2) is as follows: DQN is a deep reinforcement learning algorithm that uses a neural network to learn the Q-value function. The Q-value function is a function that maps states and actions to Q values, which represent the expected reward obtained by performing the action in a specific state. The steps are as follows:

[0120] S221, initialize the experience pool and neural network parameters.

[0121] S222, reset the environment and observe the initial state.

[0122] S223, select an action at each time step and observe the next state and reward returned by the environment.

[0123] S224, stores this information in the experience pool. That is, the tuple (state, action, reward, next_state, done) is stored in the experience pool.

[0124] S225, trains a neural network using a randomly selected batch of experiences.

[0125] S226: Use the target network to update the policy network. Specifically, before updating the policy network, the target network is first used to calculate the target Q value. The maximum Q value of the next state is then used as the target Q value to update the policy network. Furthermore, after a certain number of iterations, the parameters of the target network need to be updated to be consistent with those of the policy network. Updating the parameters of the target network can be achieved by assigning the parameters of the policy network to the parameters of the target network.

[0126] S227, repeat steps S222-S226 until convergence or the maximum number of training times is reached.

[0127] S23, the reward and penalty values ​​obtained through training are used to obtain the control strategy to determine the next action of the robot;

[0128] S24: The above reward and penalty values ​​are used to make a final reward or penalty determination according to the rules. The specific rewards and penalties are shown in Table 1.

[0129] Table 1

[0130] state Reward / penalty value x<1.1s -20 1.1s<x<d / 2 20 x>d / 2 0 The distance to the target point decreases 5 Increased distance to target point -5 Collision -20

[0131] Step S3: Through iterative training of the SLAM+DQN algorithm, the quadruped robot can be controlled to always move along the center of the tunnel, reducing the risk of the quadruped robot falling from the platform into the tunnel and improving the reliability of inspections.

[0132] Step S3 includes the following steps:

[0133] Step S31: SLAM and navigation algorithms are used to calculate sensor information, odometer information, and map information to parse the robot's angular velocity and linear velocity, thereby obtaining the underlying control instruction M1.

[0134] In step S32, the robot can obtain the underlying control instructions M2 through the reinforcement learning module. The specific process is shown in the figure below. The robot dog transmits the lidar data through the scan topic, and then performs deep reinforcement learning training on the collected data to obtain the underlying motion control commands of the robot dog;

[0135] Step S33: Perform weighted averaging of the two control instructions through the decision module to obtain a final control instruction M3 = β*(M1 + M2);

[0136] Step S34, the weighting coefficient β is in the range of 0.1-1;

[0137] Step S35, through the above steps, the robot's motion trajectory is controlled to always be near the tunnel centerline.

[0138] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0139] The embodiments of the present application also provide an anti-fall control device for a quadruped robot in a tunnel scenario. It should be noted that the anti-fall control device for a quadruped robot in a tunnel scenario in the embodiments of the present application can be used to execute the anti-fall control method for a quadruped robot in a tunnel scenario provided in the embodiments of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been explained will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceived.

[0140] The following introduces the anti-fall control device of the quadruped robot in the tunnel scene provided by the embodiment of the present application.

[0141] Figure 4 This is a structural block diagram of the anti-fall control device of the quadruped robot in the tunnel scene according to the embodiment of the present application. Figure 4 As shown, the device includes: a first acquisition unit 10, a first input unit 20, a second input unit 30 and a first calculation unit 40.

[0142] The first acquisition unit 10 is configured to acquire point cloud data centered on the quadruped robot through a laser radar to obtain point cloud depth data;

[0143] Specifically, a lidar is installed on the body of the quadruped robot to measure the distance to surrounding obstacles. Point cloud data is obtained through the lidar. After preprocessing, depth data on both sides of the robot is obtained. The point cloud depth data is published through the ROS node. Relevant nodes can obtain the above point cloud depth data by subscribing to the ROS node. The point cloud data centered on the quadruped robot is obtained through the lidar, and then the depth data of the surrounding environment is obtained.

[0144] A first input unit 20 is used to input the point cloud depth data into a first motion strategy model to obtain a first moving strategy, where the first moving strategy at least includes an angular velocity and a linear velocity of the quadruped robot. The first motion strategy model is a model trained based on a DQN algorithm that generates a moving mode based on the quadruped robot's surrounding environment;

[0145] Specifically, a first motion strategy model, which generates a movement pattern based on the quadruped robot's surroundings, is trained using the DQN algorithm. Inputting point cloud depth data yields a first movement strategy, including angular and linear velocity. This strategy rapidly generates movement patterns based on the real-time environment, improving the quadruped robot's responsiveness in dynamic environments.

[0146] A second input unit 30 is used to input the point cloud depth data into a second motion strategy model to obtain a second moving strategy, where the second moving strategy at least includes an angular velocity and a linear velocity of the quadruped robot, and the second motion strategy model includes a SLAM positioning module and a navigation module;

[0147] Specifically, the second motion strategy model includes a SLAM positioning module and a navigation module. Taking the same point cloud depth data as input, it generates a second motion strategy, including angular velocity and linear velocity. This strategy offers higher precision in positioning and navigation, ensuring the quadruped robot's path planning capabilities in complex environments.

[0148] The first calculation unit 40 is configured to perform a weighted average operation based on the first moving strategy and the second moving strategy to obtain a target control strategy, and control the movement of the quadruped robot according to the target control strategy.

[0149] Specifically, the first and second driving strategies are combined through a weighted average method to generate a target control strategy. This approach optimizes the complementary advantages and disadvantages of the strategies, enhancing the synergy between the quadruped robot's environmental perception, path planning, and motion control, and further enhancing its autonomy and adaptability in complex environments. Based on the target control strategy, the quadruped robot's motion is precisely controlled.

[0150] An embodiment of the present application provides a fall prevention control device for a quadruped robot in a tunnel scenario. The device comprises a first acquisition unit, a first input unit, a second input unit, and a first calculation unit. Based on point cloud depth data acquired by a laser radar, the device then inputs a first motion strategy model trained using a DQN algorithm and a second motion strategy model including a SLAM positioning and navigation module to generate a movement strategy for the quadruped robot. This solves the existing problem of quadruped robots becoming inoperable in power cable tunnels due to falls from pits and elevated platforms.

[0151] As a possible implementation, the device further includes: an acquisition unit, an initial state determination unit, a behavior value acquisition unit, a scoring unit, a storage unit, a network update unit, and a first model unit.

[0152] an acquisition unit, configured to acquire the tunnel width, the pit width, and the distance between the quadruped robot and the tunnel wall on one side of the pit, obtain a first target distance, a second target distance, and a third target distance, obtain an initial position of the quadruped robot, obtain a first position, obtain an end position of the quadruped robot, and obtain a second position;

[0153] Specifically, this process involves data collection and processing from sensors, obtaining information about the surrounding environment through devices such as lidar, and providing a basis for subsequent data analysis and model training.

[0154] an initial state determining unit, configured to determine the first target distance, the second target distance, the third target distance, the first position, and the second position as an initial state of the model;

[0155] Specifically, the initial state is set as the operating benchmark for the robot in a specific environment, laying the foundation for subsequent motion strategy generation.

[0156] A behavior evaluation unit is used to determine the angular velocity and linear velocity of the quadruped robot as behaviors, and randomly evaluate the angular velocity and linear velocity to obtain a plurality of first target behaviors;

[0157] Specifically, this step generates multiple possible movement strategies through random sampling, providing data support for the model to explore different movement schemes.

[0158] a scoring unit, configured to determine a plurality of updated states based on the initial state and each first target behavior, score each updated state based on a preset rule, and obtain a state reward;

[0159] Specifically, by defining scoring rules, the effect of each behavior can be quantitatively evaluated so as to optimize the model in subsequent training.

[0160] A storage unit, configured to determine the initial state, the first target behavior, the state reward, the updated state, and whether the first position and the second position overlap as an experience group, and store the group in an experience pool;

[0161] Specifically, the experience groups saved in the experience pool will provide a rich data basis for subsequent neural network training and promote knowledge accumulation in the learning process.

[0162] a network updating unit, configured to train a neural network based on samples in the experience pool, calculate a Q value based on a target Q network, determine a maximum Q value corresponding to the updated state as a target Q value, update the neural network based on the target Q value, and update the target Q network based on the neural network at intervals of a first preset number of times;

[0163] Specifically, this process involves the Q-learning mechanism in deep reinforcement learning, which improves the decision-making ability of the model by continuously updating network parameters.

[0164] The first model unit is used to determine the updated state as the initial state, and regenerate the first target behavior and the updated state and the experience group corresponding to the updated state based on the iterated initial state, and train the neural network according to the iterated updated state and the experience group until the number of iterations reaches a second preset number, thereby obtaining a first motion strategy model.

[0165] Specifically, through state updates and behavior adjustments in the iterative process, the output of the model is continuously optimized, so that the generated first motion strategy can better adapt to the actual needs in complex environments.

[0166] Through the above steps, the final first motion strategy model not only takes environmental factors into account, but also can dynamically adjust the movement strategy to adapt to different obstacles and spatial constraints, thereby improving the flexibility and stability of the quadruped robot in different walking environments.

[0167] As a possible implementation manner, the apparatus further includes: a distance calculation unit, a first preset unit, a second preset unit, a third preset unit, a fourth preset unit, a fifth preset unit, and a sixth preset unit.

[0168] a distance calculation unit, configured to calculate the product of the first target distance and the first preset coefficient to obtain a fourth target distance, and calculate the product of the second target distance and the second preset coefficient to obtain a fifth target distance;

[0169] Specifically, by setting different preset coefficients, the target distance can be weighted, introducing adaptability to different scenarios. For example, if the environment is complex, the first preset coefficient can be set to a smaller value, allowing the fourth target distance to have a larger safety margin. This dynamic adjustment of the target distance can better reflect the actual environmental obstacles encountered, ensuring the robot's path planning is flexible and responsive.

[0170] The first preset unit is configured to determine a first preset rule as follows: if the third target distance is less than or equal to the fifth target distance in the updated state, the first preset score is determined as the state reward;

[0171] Specifically, this means that when the distance between the robot and the obstacle is less than the safe distance, the lowest score is given, encouraging the robot to maintain the safe range and avoid potential collisions. This rule ensures that the robot will try to maintain a safe distance when approaching obstacles, thereby improving operational safety.

[0172] The second preset unit is configured to determine the second preset rule as follows: if the third target distance is greater than the fifth target distance and less than the fourth target distance in the updated state, the second preset score is determined as the state reward;

[0173] Specifically, a reward is given when the robot navigates within a relatively safe boundary. At this point, while still within a safe range despite being far from obstacles, this rule encourages the robot to maintain a stable speed and direction, enhancing path planning flexibility. This scoring mechanism also enhances the robot's ability to self-adjust its behavior, making it more adaptable in complex environments.

[0174] a third preset unit, configured to determine a third preset rule as determining a third preset score as a status reward when the third target distance in the updated status is greater than or equal to the fourth target distance;

[0175] Specifically, this rule aims to encourage robots to stay away from potentially dangerous areas. Effective distance management between existing obstacles and targets allows robots to earn more rewards by moving to safer areas, ensuring that robots avoid sharp turns and other unsafe behaviors, thereby enhancing their stability.

[0176] a fourth preset unit, configured to determine a fourth preset rule as follows: when the distance between the first position and the second position decreases in the updated state, determining a fourth preset score as a state reward;

[0177] Specifically, this rule ensures that sufficient rewards are given as the robot approaches the target location, encouraging it to move toward the target. Reducing distance not only improves travel efficiency but also promotes optimal path selection, reducing travel time and energy consumption, and accelerating task completion.

[0178] a fifth preset unit, configured to determine a fifth preset rule as follows: when the distance between the first position and the second position increases in the updated state, determining a fifth preset score as a state reward;

[0179] Specifically, this rule prevents the robot from straying from the target point, reducing the risk of unexpected situations. If the distance continues to increase, this indicates that the robot's path selection is inappropriate, which will negatively impact the overall mission. Therefore, this reward system is designed to warn the robot to adjust its direction in a timely manner.

[0180] The sixth preset unit is used to determine the sixth preset rule: when the quadruped robot collides in the update state, the first preset score is determined as the state reward, the first preset score is less than the fifth preset score, the fifth preset score is less than the third preset score, the third preset score is less than the fourth preset score, and the fourth preset score is less than the second preset score.

[0181] Specifically, by setting the penalty for collisions to the lowest possible score, this emphasizes the importance of warning during path planning. This rule not only helps the robot recognize the severity of a collision but also prompts it to reflect on and adjust its driving strategy to avoid similar situations in the future. This creates a positive feedback mechanism, allowing the robot to gradually learn and optimize its behavioral strategies, enabling it to interact more intelligently with its environment.

[0182] Through these steps, pre-set rules can effectively manage the robot's safety and efficiency in complex environments, enabling it to make autonomous decisions in dynamically changing environments, reducing collision risks and improving movement efficiency. Furthermore, this detailed evaluation system provides reliable feedback for subsequent action optimization, profoundly benefiting the training of deep learning models.

[0183] As a possible implementation manner, the first input unit includes: a data updating module, a position determining module, a state determining module, a strategy generating module, a strategy scoring module and a first traveling strategy module.

[0184] A data updating module, configured to update the first target distance, the second target distance, and the third target distance based on the point cloud depth data;

[0185] Specifically, the robot uses the depth data from the point cloud scan to update the distance parameters in front of it, to its left and right (i.e., the first, second, and third target distances) in real time. By updating these distance parameters, the robot can quickly respond to dynamic changes in its surroundings. For example, when it detects an approaching obstacle, it can adjust its distance in a timely manner to prevent collisions and ensure safe movement.

[0186] a position determination module, configured to determine a first position and a second position based on the point cloud depth data;

[0187] Specifically, point cloud data combined with SLAM technology accurately determines the robot's current position (first position) and target position (second position). This step provides accurate information about the robot's current posture and target point. This information is used to guide the robot's path planning, enabling it to select the optimal path based on its current state and target position, thereby improving navigation accuracy and efficiency.

[0188] a state determination module, configured to determine the first target distance, the second target distance, the third target distance, the first position, and the second position as a current state;

[0189] Specifically, all key environmental information and robot states are combined into a single, integrated state description. This step provides a comprehensive, up-to-date picture of the current state, encompassing both environmental perception and pose information. The model relies on this detailed information for policy generation and decision-making, ensuring that the path planning strategy is both responsive and robust.

[0190] A strategy generation module is used to randomly generate the angular velocity and linear velocity of the quadruped robot based on the current state to obtain multiple alternative movement strategies;

[0191] Specifically, based on the current state information, multiple sets of candidate angular and linear velocities are randomly generated. These alternative strategies ensure diverse and exploratory paths, preventing the robot from becoming trapped in local optima and improving the adaptability and robustness of the entire system. Different speed combinations ensure that the robot can try multiple possible movement methods in a changing environment, ultimately finding the optimal strategy.

[0192] A strategy scoring module is used to determine the corresponding predicted state based on the current state and each alternative driving strategy, and determine the state reward corresponding to the predicted state to obtain the alternative strategy score;

[0193] Specifically, the model predicts future states based on the current state and each set of candidate strategies, and then scores these states. This scoring is based on pre-set state-reward rules, comprehensively evaluating factors such as robot safety, path efficiency, and target proximity. This process, by simulating various possible future states, helps the robot weigh the pros and cons of each candidate strategy, improving the rationality and effectiveness of strategy selection.

[0194] The first traveling strategy module is configured to determine the alternative traveling strategy corresponding to the maximum alternative strategy score as the first traveling strategy.

[0195] Specifically, the strategy with the highest score among all candidate strategies is selected as the primary strategy. This decision-making process ensures that the robot selects the safest and most efficient strategy. By selecting the best from the best, it significantly improves the success rate of path planning and travel efficiency. This strategy optimization process enables the robot to find the optimal path in complex and changing environments when performing tasks.

[0196] Through the detailed steps described above, the first motion strategy model not only responds quickly to real-time point cloud data but also generates an efficient and safe movement strategy based on accurate environmental perception. This approach provides powerful technical support for the quadruped robot's autonomous navigation in complex environments, ensuring its excellent adaptability and reliability in various tasks.

[0197] As a possible implementation manner, the second input unit includes: a map construction module and a second strategy module.

[0198] The map construction module is used to input the point cloud depth data into the SLAM positioning module to obtain the current posture of the quadruped robot and the target map constructed based on the point cloud depth data;

[0199] Specifically, SLAM (Simultaneous Localization and Mapping) technology processes real-time point cloud depth data to determine the robot's current precise pose (including position and orientation) and environmental map. This step ensures that the robot can accurately perceive its current environment and its own precise position. SLAM not only constructs a detailed map of the surrounding environment but also improves the accuracy of pose estimation and the reliability of the map through loop closure detection and pose graph optimization, providing a solid foundation for the navigation module.

[0200] The second strategy module is used to input the current posture and target map into the navigation module to predict the angular velocity and linear velocity of the quadruped robot within a preset time period to obtain a second travel strategy.

[0201] Specifically, the navigation module receives the current position and the constructed target map and uses this information to plan a path. By predicting the angular and linear velocities for a preset time period in the future, the model can evaluate the potential outcomes of different strategies. This allows the navigation module to generate the optimal strategy by comprehensively considering factors such as obstacles in the actual environment, feasible paths, and the robot's kinematic performance.

[0202] Through these steps, the second motion strategy model fully leverages real-time point cloud data and SLAM technology to generate an efficient and stable path planning strategy. This approach has proven successful in autonomous navigation tasks for quadruped robots, enabling them to navigate complex and changing environments and complete tasks safely and efficiently.

[0203] As a possible implementation method, the map construction module includes: a feature extraction submodule, a feature comparison submodule, a map reconstruction submodule and a pose module.

[0204] The feature extraction submodule is used to extract features from point cloud depth data based on the SLAM algorithm, determine the points that match the preset objects, and obtain key feature points;

[0205] Specifically, at this stage, the SLAM algorithm first processes the input point cloud data and extracts key points that represent the characteristics of the environment. These feature points are the basis for the robot to identify and locate in the environment, and usually include the edges of walls, corners of obstacles, specific patterns, etc. These key feature points can not only effectively describe different environmental areas, but also help the robot understand its location by matching them with known features. The feature extraction process can use various techniques, such as the RANSAC algorithm to remove noise points, or use feature descriptors such as PFH (Point Feature Histograms) to accurately identify object features.

[0206] The feature comparison submodule is used to determine the key feature points obtained in the last feature extraction of the point cloud depth data as comparison feature points, and determine the moving trajectory of the quadruped robot based on the key feature points and the comparison feature points;

[0207] Specifically, during this phase, the system matches the currently extracted key feature points with the previously extracted comparison feature points. By calculating the relative positional changes between the current and comparison feature points, the SLAM algorithm can infer the robot's trajectory over time. This trajectory information is crucial for subsequent map reconstruction and pose estimation, helping the robot understand its movement within the environment and effectively update its map and pose information.

[0208] The map reconstruction submodule is used to reconstruct the map based on key feature points and travel trajectories to obtain the target map;

[0209] Specifically, in this step, the key feature points obtained after matching are combined with the travel trajectory to reconstruct the target map. By performing three-dimensional geometric reconstruction of each feature point in the environment, the SLAM module can construct a map of the robot's environment. The reconstructed map is typically a sparse or dense point cloud model that can more comprehensively reflect the robot's surroundings at a specific moment. The map reconstruction process may use methods such as weighted averaging and B-splines to improve the precision and accuracy of the reconstructed map.

[0210] The posture module is used to determine the current position and direction of the robot based on the target map and key feature points to obtain the current posture.

[0211] Specifically, by comprehensively analyzing the reconstructed target map and the currently extracted key feature points, the SLAM algorithm can accurately infer the robot's current position and direction of movement. This process typically involves matching the robot with feature points on the map and optimizing the position estimate using the least squares method to ensure the accuracy and reliability of the current position. Ultimately, the algorithm outputs the robot's current position coordinates (x, y, z) and orientation angles (such as heading and pitch angles), supporting subsequent navigation and movement decisions.

[0212] Through the above steps, the SLAM positioning module efficiently and accurately processes point cloud depth data, helping the quadruped robot continuously update its environmental map and pose information. This process ensures the robot's autonomous navigation in complex environments, enhancing its adaptability and intelligence. This method not only improves the reliability of path planning but also provides important guarantees for the robot to perform various tasks.

[0213] As a possible implementation manner, the device further includes: a policy updating unit and a control unit.

[0214] A strategy updating unit, configured to recollect point cloud depth data at intervals of a preset duration, and update the target control strategy based on the point cloud depth data using the first motion strategy model and the second motion strategy model;

[0215] Specifically, during this step, the system periodically re-collects point cloud depth data. This new data reflects the real-time dynamic changes in the environment and the robot's new state. Using this collected point cloud depth data, the first and second motion strategy models are re-invoked to generate new control strategies. These strategies each consider the current state and environmental information in different ways to precisely adjust the robot's motion direction and speed in a changing environment. This regular update ensures that strategies are always generated based on the latest data, enabling better response to environmental changes and unexpected situations.

[0216] The control unit is used to control the movement of the quadruped robot according to the updated target control strategy.

[0217] Specifically, once new target control policies are generated, the system immediately applies them to control the quadruped's motion. These policies take into account new data and the robot's latest environmental perception, aiming to guide the robot in the most optimal way. This prevents policy staleness and maintains the robot's ability to respond to the environment in real time, ensuring it can continue to perform its mission safely and efficiently.

[0218] The anti-fall control device for the quadruped robot in the tunnel scenario described above includes a processor and memory. The first acquisition unit, first input unit, second input unit, and first calculation unit are all stored as program units in the memory. The processor executes the program units stored in the memory to implement the corresponding functions. All of the above modules are located in the same processor; alternatively, the above modules can be located in different processors in any combination.

[0219] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the communication efficiency can be improved by adjusting the kernel parameters.

[0220] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0221] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is running, the device where the computer-readable storage medium is located is controlled to execute the anti-fall control method for the quadruped robot in the tunnel scene.

[0222] An embodiment of the present invention provides a quadruped robot, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the anti-fall control method of the quadruped robot in the above-mentioned tunnel scenario.

[0223] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0224] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt 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.) that contain computer-usable program code.

[0225] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0226] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1The function specified in one or more boxes.

[0227] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0228] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0229] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0230] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0231] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0232] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0233] 1) The anti-fall control method of the quadruped robot in the tunnel scene of the present application first obtains point cloud data centered on the quadruped robot through a laser radar to obtain point cloud depth data; then the point cloud depth data is input into a first motion strategy model to obtain a first moving strategy, the first moving strategy at least includes the moving angular velocity and moving linear velocity of the quadruped robot, and the first motion strategy model is a model based on the DQN algorithm trained to generate a moving mode based on the surrounding environment of the quadruped robot; then the point cloud depth data is input into a second motion strategy model to obtain a second moving strategy, the second moving strategy at least includes the moving angular velocity and moving linear velocity of the quadruped robot, and the second motion strategy model includes a SLAM positioning module and a navigation module; finally, a weighted average operation is performed based on the first moving strategy and the second moving strategy to obtain a target control strategy, and the movement of the quadruped robot is controlled according to the target control strategy. The present application is based on the point cloud depth data obtained by the laser radar, and then obtains the moving strategy of the quadruped robot by inputting a first motion strategy model trained with a DQN algorithm and a second motion strategy model including a SLAM positioning and navigation module. The present invention solves the problem in the prior art that in power cable tunnel scenarios, a quadruped robot cannot work after falling due to pits and high platforms.

[0234] 2) The present application discloses a device for preventing a quadruped robot from falling in tunnel scenarios. The device comprises a first acquisition unit, a first input unit, a second input unit, and a first calculation unit. Based on point cloud depth data acquired by a laser radar, the device then inputs a first motion strategy model trained using a DQN algorithm and a second motion strategy model including a SLAM positioning and navigation module to determine the quadruped robot's movement strategy. This device solves the existing problem of quadruped robots becoming inoperable after falling into tunnels and elevated platforms in power cable tunnels.

[0235] The above are merely preferred embodiments of the present application and are not intended to limit the present application. Those skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for preventing a quadruped robot from falling in a tunnel scene, characterized in that: include: Use laser radar to obtain point cloud data centered on the quadruped robot and obtain point cloud depth data; Inputting the point cloud depth data into a first motion strategy model to obtain a first movement strategy, wherein the first movement strategy includes at least an angular velocity and a linear velocity of the quadruped robot, and the first motion strategy model is a model trained based on a DQN algorithm that generates a movement mode based on the surrounding environment of the quadruped robot; Inputting the point cloud depth data into a second motion strategy model to obtain a second travel strategy, wherein the second travel strategy includes at least a travel angular velocity and a travel linear velocity of the quadruped robot, and the second motion strategy model includes a SLAM positioning module and a navigation module; Performing a weighted average operation based on the first moving strategy and the second moving strategy to obtain a target control strategy, and controlling the movement of the quadruped robot according to the target control strategy; Before inputting the point cloud depth data into the first motion strategy model, the method includes: Obtaining the tunnel width, the pit width, and the distance between the quadruped robot and the tunnel wall on one side of the pit, obtaining a first target distance, a second target distance, and a third target distance, obtaining an initial position of the quadruped robot to obtain a first position, obtaining an end position of the quadruped robot to obtain a second position; Inputting the point cloud depth data into a first motion strategy model to obtain a first moving strategy includes: updating the first target distance, the second target distance, and the third target distance based on the point cloud depth data; determining the first position and the second position based on the point cloud depth data; determining the first target distance, the second target distance, the third target distance, the first position, and the second position as a current state; Randomly generating the traveling angular velocity and the traveling linear velocity of the quadruped robot based on the current state to obtain a plurality of alternative traveling strategies; Determining a corresponding predicted state based on the current state and each of the alternative travel strategies, and determining a state reward corresponding to the predicted state to obtain an alternative strategy score; Determining the alternative traveling strategy corresponding to the maximum value of the alternative strategy score as the first traveling strategy; Inputting the point cloud depth data into a second motion strategy model to obtain a second movement strategy, including: Inputting the point cloud depth data into the SLAM positioning module to obtain the current posture of the quadruped robot and a target map constructed based on the point cloud depth data; The current posture and the target map are input into the navigation module to predict the angular velocity and the linear velocity of the quadruped robot within a preset time period to obtain the second travel strategy.

2. The method according to claim 1, characterized in that Before inputting the point cloud depth data into the first motion strategy model, the method further includes: determining the first target distance, the second target distance, the third target distance, the first position, and the second position as an initial state of a model; Determining the angular velocity and the linear velocity of the quadruped robot as behaviors, and randomly taking values ​​of the angular velocity and the linear velocity to obtain a plurality of first target behaviors; Determine a plurality of updated states based on the initial state and each of the first target behaviors, score each of the updated states based on a preset rule, and obtain a state reward; Determine the initial state, the first target behavior, the state reward, the updated state, and whether the first position and the second position overlap as an experience group, and store the group in an experience pool; Training a neural network based on samples in the experience pool, calculating a Q value based on a target Q network, determining a maximum Q value corresponding to the updated state as a target Q value, updating the neural network based on the target Q value, and updating the target Q network based on the neural network at intervals of a first preset number of times; The updated state is determined as the initial state, and the first target behavior and the updated state and the experience group corresponding to the updated state are regenerated based on the iterated initial state, and the neural network is trained according to the iterated updated state and the experience group until the number of iterations reaches a second preset number, thereby obtaining the first motion strategy model.

3. The method according to claim 2, characterized in that Before scoring each of the update states based on preset rules and obtaining a state reward, the method further includes: Calculating the product of the first target distance and a first preset coefficient to obtain a fourth target distance, and calculating the product of the second target distance and a second preset coefficient to obtain a fifth target distance; Determining a first preset rule as follows: when the third target distance in the updated state is less than or equal to the fifth target distance, determining a first preset score as the state reward; Determining the second preset rule as follows: when, in the updated state, the third target distance is greater than the fifth target distance and less than the fourth target distance, determining the second preset score as the state reward; Determining a third preset rule as follows: if the third target distance in the updated state is greater than or equal to the fourth target distance, determining a third preset score as the state reward; Determining a fourth preset rule as follows: when the distance between the first position and the second position decreases in the updated state, determining a fourth preset score as the state reward; Determining a fifth preset rule as follows: when the distance between the first position and the second position increases in the updated state, determining a fifth preset score as the state reward; The sixth preset rule is determined as follows: when the quadruped robot collides in the updated state, the first preset score is determined as the state reward, the first preset score is less than the fifth preset score, the fifth preset score is less than the third preset score, the third preset score is less than the fourth preset score, and the fourth preset score is less than the second preset score.

4. The method according to claim 1, wherein Inputting the point cloud depth data into the SLAM positioning module to obtain the current posture of the quadruped robot and a target map constructed based on the point cloud depth data, including: Perform feature extraction on the point cloud depth data based on the SLAM algorithm, determine the points therein that match the preset objects, and obtain key feature points; determining the key feature points obtained in the last feature extraction of the point cloud depth data as comparison feature points, and determining the moving trajectory of the quadruped robot based on the key feature points and the comparison feature points; Reconstructing a map based on the key feature points and the travel trajectory to obtain the target map; The current position and direction of travel of the quadruped robot are determined based on the target map and the key feature points to obtain the current posture.

5. The method according to claim 1, wherein After controlling the movement of the quadruped robot according to the target control strategy, the method further includes: Recollecting the point cloud depth data at intervals of a preset time, and updating the target control strategy based on the point cloud depth data using the first motion strategy model and the second motion strategy model; The movement of the quadruped robot is controlled according to the updated target control strategy.

6. A quadruped robot anti-fall control device in a tunnel scene, characterized in that: The device comprises: The first acquisition unit is used to acquire point cloud data centered on the quadruped robot through a laser radar to obtain point cloud depth data; a first input unit, configured to input the point cloud depth data into a first motion strategy model to obtain a first movement strategy, wherein the first movement strategy includes at least an angular velocity and a linear velocity of the quadruped robot, and the first motion strategy model is a model trained based on a DQN algorithm that generates a movement mode based on the surrounding environment of the quadruped robot; A second input unit is used to input the point cloud depth data into a second motion strategy model to obtain a second travel strategy, wherein the second travel strategy at least includes a travel angular velocity and a travel linear velocity of the quadruped robot, and the second motion strategy model includes a SLAM positioning module and a navigation module; a first computing unit, configured to perform a weighted average operation based on the first moving strategy and the second moving strategy to obtain a target control strategy, and control the movement of the quadruped robot according to the target control strategy; The device comprises: an acquisition unit, configured to, before inputting the point cloud depth data into the first motion strategy model, acquire the tunnel width, the pit width, and the distance between the quadruped robot and the tunnel wall on one side of the pit, obtain a first target distance, a second target distance, and a third target distance, obtain an initial position of the quadruped robot to obtain a first position, obtain an end position of the quadruped robot to obtain a second position; The first input unit includes: a data updating module, configured to update the first target distance, the second target distance, and the third target distance based on the point cloud depth data; a position determination module, configured to determine the first position and the second position based on the point cloud depth data; a state determining module, configured to determine the first target distance, the second target distance, the third target distance, the first position, and the second position as a current state; A strategy generation module is used to randomly generate the angular velocity and the linear velocity of the quadruped robot based on the current state to obtain multiple alternative travel strategies; a strategy scoring module, configured to determine a corresponding predicted state based on the current state and each of the alternative driving strategies, and determine a state reward corresponding to the predicted state, thereby obtaining a score for the alternative strategy; a first traveling strategy module, configured to determine the alternative traveling strategy corresponding to the maximum value of the alternative strategy score as the first traveling strategy; The second input unit includes: A map construction module, configured to input the point cloud depth data into the SLAM positioning module to obtain the current posture of the quadruped robot and a target map constructed based on the point cloud depth data; The second strategy module is used to input the current posture and the target map into the navigation module to predict the angular velocity and the linear velocity of the quadruped robot within a preset time period to obtain the second travel strategy.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 5.

8. A quadruped robot, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing the method of any one of claims 1 to 5.

Images