Risk control method and device for demolition robot

Abstract

A risk control method and device for a demolition robot. During the traveling process of a demolition robot, an operating condition of the demolition robot during traveling is determined on the basis of orientation information of the demolition robot. A neural network is employed to determine a risk category. When only a travel-path risk exists, travel-path replanning is performed. When only an overturning risk exists, an overturning direction of the demolition robot is determined, and the orientation of the robot is adjusted on the basis of the overturning direction. When both the travel-path risk and the overturning risk exist, priority is given to addressing the overturning risk first, followed by handling the travel-path risk. In this way, the overturning risk and the travel-path risk during traveling of the demolition robot in complex environments are reduced, thereby effectively enhancing the stability and safety of the demolition robot in complex environments.

Description

Risk control method and device for forcible entry robot TECHNICAL FIELD

[0001] The present application relates to a risk control method and device for forcible entry robot, belonging to the field of mechanical engineering. BACKGROUND

[0002] With the development of industrial automation and robot technology, unmanned three-section arm forcible entry robots are increasingly widely used in complex environments, especially in complex environments requiring high-precision positioning, minimum energy consumption, multi-task operation efficiency and obstacle avoidance. When the three-section arm forcible entry robot is in a working state, it is rarely at risk of overturning due to the support of the supporting legs, but it is prone to overturning risk and walking path risk (such as being blocked by obstacles and unable to bypass, or walking into a pit, etc.) when walking in a complex environment.

[0003] SUMMARY

[0004] The present application provides a risk control method and device for forcible entry robot, which solves the problems disclosed in the background art.

[0005] According to one aspect of the present disclosure, a risk control method for a forcible entry robot is provided, including a first method implemented in real time during the walking process of the forcible entry robot, the first method comprising:

[0006] determining the posture of the forcible entry robot according to the posture information of the forcible entry robot;

[0007] determining the risk category of the forcible entry robot using a trained neural network according to the posture parameters of the forcible entry robot, the posture information of the forcible entry robot and the environmental information of the forcible entry robot;

[0008] in response to the risk category being a walking path risk, re-planning a walking path according to the environmental information of the forcible entry robot and controlling the forcible entry robot using the re-planned walking path;

[0009] in response to the risk category being an overturning risk, determining the overturning direction of the forcible entry robot according to the posture information of the forcible entry robot and the overturning line, and adjusting the posture of the forcible entry robot according to the overturning direction;

[0010] in response to the risk category including an overturning risk and a walking path risk, determining the overturning direction of the forcible entry robot according to the posture information of the forcible entry robot and the overturning line, adjusting the posture of the forcible entry robot according to the overturning direction, re-planning a walking path according to the environmental information of the forcible entry robot after the overturning risk is removed, and controlling the forcible entry robot using the re-planned walking path.

[0011] In some embodiments of the present disclosure, a second method implemented in real time during the working process of the forcible entry robot is also included, the second method comprising:

[0012] determine the posture of the forced-entry robot according to the posture information of the forced-entry robot;

[0013] determine whether the forced-entry robot has a risk of overturning according to the posture of the forced-entry robot, the posture information of the forced-entry robot, and the overturning line;

[0014] in response to the risk of overturning, determine the overturning direction of the forced-entry robot according to the posture information of the forced-entry robot and the overturning line, and adjust the posture of the forced-entry robot according to the overturning direction.

[0015] In some embodiments of the present disclosure, determining the overturning direction of the forced-entry robot according to the posture information of the forced-entry robot and the overturning line comprises:

[0016] calculate the probability that each overturning angle exceeds the corresponding angle threshold according to the overturning angle on the overturning line in the posture information;

[0017] determine the overturning direction of the forced-entry robot according to the overturning line corresponding to the maximum probability.

[0018] In some embodiments of the present disclosure, the third method is further implemented when the forced-entry robot is working or walking, and the third method comprises:

[0019] determine the posture of the forced-entry robot according to the posture information of the forced-entry robot;

[0020] determine whether the forced-entry robot has a risk of overturning according to the posture of the forced-entry robot, the posture information of the forced-entry robot when the forced-entry robot is suddenly stopped, and the overturning line;

[0021] in response to the risk of overturning, determine the overturning direction of the forced-entry robot according to the posture information of the forced-entry robot when the forced-entry robot is suddenly stopped, and adjust the posture of the forced-entry robot according to the overturning direction.

[0022] In some embodiments of the present disclosure, determining whether the forced-entry robot has a risk of overturning comprises:

[0023] calculate the stability coefficient of the forced-entry robot according to the moment length of the center of gravity of the forced-entry robot component and the corresponding overturning line in the posture information; wherein the stability coefficient of the forced-entry robot is the ratio of the stability moment of the forced-entry robot to the overturning moment, and the corresponding overturning line is the overturning line corresponding to the posture of the forced-entry robot;

[0024] in response to the stability coefficient of the forced-entry robot being less than the stability threshold, determine that the forced-entry robot has a risk of overturning.

[0025] In some embodiments of the present disclosure, the stability coefficient calculation formula of the breaking machine is: K=M1 / M0; M1=G7*L7+G6*L6+G5*L5+G3*L3+G2*L2+G1*L1; M0=G4*L4;

[0026] In the formula, K is the stability coefficient of the breaking machine, M1 is the stability moment of the breaking machine, M0 is the overturning moment of the breaking machine, G7-G1 are the weights of the machine shed, the mechanical arm, the hydraulic system, the electrical system, the power system, the rotating platform and the tracked chassis of the breaking machine respectively, and L7-L1 are the distances from the centers of gravity of the machine shed, the mechanical arm, the hydraulic system, the electrical system, the power system, the rotating platform and the tracked chassis to the corresponding overturning lines respectively.

[0027] In some embodiments of the present disclosure, the attitude of the breaking machine is determined according to the attitude information of the breaking machine, which includes:

[0028] The front and rear height differences of the two sides of the tracked chassis at the same time in the attitude information are calculated.

[0029] If the front and rear height differences of the two sides of the tracked chassis are both greater than 0 and greater than a first height difference threshold, the breaking machine is in an uphill attitude; wherein the front and rear height differences of the two sides of the tracked chassis are parameters of the uphill attitude.

[0030] If the front and rear height differences of the two sides of the tracked chassis are both less than 0 and less than the negative of the first height difference threshold, the breaking machine is in a downhill attitude; wherein the front and rear height differences of the two sides of the tracked chassis are parameters of the downhill attitude.

[0031] The height difference between the left and right tracked chassis at the same time in the attitude information is calculated.

[0032] If the height difference between the left and right tracked chassis is greater than a second height difference threshold, it is determined that the breaking machine is in an inclined attitude; wherein the height difference between the left and right tracked chassis is a parameter of the inclined attitude.

[0033] If the front and rear height differences of the two sides of the tracked chassis are both within the range of the first threshold and the negative of the first threshold, and the height difference between the left and right tracked chassis is not greater than the second height difference threshold, it is determined that the breaking machine is in a horizontal attitude; wherein the parameter of the horizontal attitude is 0.

[0034] According to another aspect of the present disclosure, a breaking machine risk control device is provided, which includes a first device that works in real time during the walking process of the breaking machine, and the first device includes:

[0035] The working condition module determines the posture of the forced-entry robot according to the posture information of the forced-entry robot.

[0036] The risk category module determines the risk category of the forced-entry robot according to the posture parameter of the forced-entry robot, the posture information of the forced-entry robot and the environment information of the forced-entry robot by using the trained neural network.

[0037] The path planning module re-plans the walking path according to the environment information of the forced-entry robot in response to the risk category being the walking path risk, and controls the forced-entry robot by using the re-planned walking path.

[0038] The stability control module determines the overturning direction of the forced-entry robot according to the posture information of the forced-entry robot and the overturning line in response to the risk category being the overturning risk, and adjusts the posture of the forced-entry robot according to the overturning direction.

[0039] The sequence control module determines the overturning direction of the forced-entry robot according to the posture information of the forced-entry robot and the overturning line in response to the risk category including the overturning risk and the walking path risk, adjusts the posture of the forced-entry robot according to the overturning direction, re-plans the walking path according to the environment information of the forced-entry robot after the overturning risk is removed, and controls the forced-entry robot by using the re-planned walking path.

[0040] According to another aspect of the present disclosure, a computer-readable storage medium is provided, which stores one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the forced-entry robot risk control method.

[0041] According to another aspect of the present disclosure, a computer device is provided, which includes one or more processors and one or more memories, one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing the forced-entry robot risk control method.

[0042] The present application has the following beneficial effects: In the walking process of the forced-entry robot, the working condition of the forced-entry robot in walking is determined according to the posture information of the forced-entry robot, the risk category is judged by using the neural network, the walking path is re-planned only when there is the walking path risk, the overturning direction of the forced-entry robot is determined only when there is the overturning risk, the posture of the forced-entry robot is adjusted according to the overturning direction, the overturning risk is preferentially processed when both the walking path risk and the overturning risk exist, and then the walking path risk is processed, so as to reduce the overturning risk and the walking path risk of the forced-entry robot in the complex environment, and effectively improve the stability and safety of the forced-entry robot in the complex environment. BRIEF DESCRIPTION OF DRAWINGS

[0043] Fig. 1 is a flow chart of a first method in the risk control method of the breaking robot;

[0044] Fig. 2 is a schematic diagram of a tipping line;

[0045] Fig. 3 is a flow chart of a second method in the risk control method of the breaking robot;

[0046] Fig. 4 is a schematic diagram of a moment in a horizontal posture;

[0047] Fig. 5 is a flow chart of a third method in the risk control method of the breaking robot. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and not intended to limit the present disclosure and its applications or uses in any way. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present disclosure.

[0049] Unless otherwise specified, the relative arrangement of the components and steps, numerical expressions, and values set forth in these embodiments do not limit the scope of the present disclosure.

[0050] It should be understood that the sizes of the various parts shown in the drawings are not necessarily drawn to scale to facilitate description.

[0051] Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail herein. However, where appropriate, such techniques, methods, and devices can be considered part of the present disclosure.

[0052] In all examples shown and discussed herein, any specific values should be interpreted as merely illustrative and not as a limitation. Thus, other examples of the example embodiments can have different values.

[0053] It should be noted that similar symbols and letters represent similar items in the following drawings, and thus, once an item is defined in one drawing, it need not be discussed further in subsequent drawings.

[0054] To solve the risk problem of the breaking robot in a complex environment, the present disclosure proposes a risk control method of the breaking robot, which specifically includes a first method implemented in real time during the walking process of the breaking robot, a second method implemented in real time during the working process of the breaking robot, and a third method implemented in an emergency stop during the working or walking process of the breaking robot.

[0055] FIG. 1 is a schematic diagram of one embodiment of a first method of the present disclosure, which can be performed by a vehicle-mounted controller of a demolition robot, and which is implemented in real time during the walking of the demolition robot.

[0056] As shown in FIG. 1, in step 1 of the embodiment, the attitude of the demolition robot is determined according to attitude information of the demolition robot.

[0057] It should be noted that the attitude information is used to reflect the state of the demolition robot, and can include track height, overturning angle on the overturning line, moment length of the component center of gravity and the corresponding overturning line, etc.; wherein the height information can be collected by a laser radar, which can be installed on a rotating platform connected to the track chassis, and the track height can be obtained according to the collected height and the calibrated height of the track chassis and the rotating platform; the inclination angle is collected by an inclination sensor, which is installed on the track chassis in the diagonal, lateral and longitudinal directions; the moment length can also be collected by a rotatable laser radar, which collects the length of the center of gravity to a preset point on the overturning line, and then calculates the moment length according to the rotation angle of the laser radar.

[0058] It should be noted that in the scene, the attitude of the demolition robot mainly includes uphill, downhill, tilt and horizontal, and since the risks and controls of different attitudes are different, in order to ensure the accuracy of the control, in some embodiments, the process of determining the attitude of the demolition robot can be as follows:

[0059] 1) Calculate the front and rear height difference of the same track at the same time in the attitude information, which can be expressed by the formula: Δh = h1 - h2;

[0060] In the formula, Δh is the height difference of the same track before and after, and h1 and h2 are the heights before and after the same track, respectively.

[0061] 2) If the front and rear height difference of the same track on both sides is greater than 0 and greater than the first height difference threshold, the demolition robot is in an uphill attitude; wherein the front and rear height difference of the same track on both sides is a parameter of the uphill attitude:

[0062] Wherein the first height difference threshold can be 60 cm, and the front and rear height difference of the same track on both sides can be used as a parameter of the uphill attitude.

[0063] If the front and rear height difference of the same track on both sides is less than 0 and less than the negative value of the first height difference threshold, the demolition robot is in a downhill attitude; wherein the front and rear height difference of the same track on both sides is a parameter of the downhill attitude.

[0064] 3) Calculate the height difference of the left track and the right track at the same time in the attitude information, which can be expressed by the formula: ΔH = H1 - H2;

[0065] In the formula, △H is the height difference between the left track and the right track, H1 and H2 are the heights of the left track and the right track respectively.

[0066] 4) If the height difference between the left track and the right track is greater than the second height difference threshold, it is determined that the forced-entry robot is in an inclined posture, which can be expressed by the formula:

[0067] wherein the second height difference threshold can be 40 cm, and the height difference between the left track and the right track can be used as a parameter of the inclined posture.

[0068] 5) If the front and rear height differences of the two tracks are within the range of the first threshold and the negative value of the first threshold, and the height difference between the left track and the right track is not greater than the second height difference threshold, it is determined that the forced-entry robot is in a horizontal posture; wherein the parameter of the horizontal posture is 0.

[0069] Returning to FIG. 1, step 2 of the embodiment, according to the posture parameter of the forced-entry robot, the posture information of the forced-entry robot and the environment information of the forced-entry robot, a trained neural network is used to determine the risk category of the forced-entry robot.

[0070] It should be noted that the neural network here can use a ResNet50 deep learning model. Before the parameters and information are input into the model, the posture parameter and the posture information will be filtered and normalized. The environment information is mainly the video image captured, which will be sequentially denoised and adjusted to a standard size of 224x224 pixels, and then the preprocessed data will be input into the model to obtain the risk category of the forced-entry robot; for example, according to the posture parameter and the posture information, the trend of the posture of the forced-entry robot can be obtained, so as to determine whether there is a risk of overturning, and according to the video image, key visual information such as surrounding terrain and obstacles can be obtained, so as to determine whether there is a risk of walking path.

[0071] Returning to FIG. 1, step 3 of the embodiment, in response to the risk category being only the walking path risk, a walking path is re-planned according to the environment information of the forced-entry robot, and the forced-entry robot is controlled using the re-planned walking path.

[0072] It should be noted that the environment information (i.e. the video image) often contains terrain, obstacle position, slope information, etc. If there is a risk of walking path, the path can be re-planned according to these information.

[0073] Path planning is a multi-objective optimization problem, and a target function can be defined, which comprehensively considers multiple objectives in the walking process of the forced-entry robot, including high-precision positioning, minimum energy consumption, obstacle avoidance safety and other requirements. By defining a function of a multi-objective optimization problem, the function is expressed by a mathematical model, and a multi-objective optimization algorithm is used to find the optimal or suboptimal solution.

[0074] Assume that the objective function is F(x), where x is the decision variable of the broken robot walking, including path planning parameters, speed control parameters, etc. Through a multi-objective optimization algorithm, a solution set is found, so that the value of the objective function (cost function) is as small as possible, while meeting the constraint conditions of the objective function. This solution set can contain multiple solutions, each of which represents a possible broken robot walking strategy. By analyzing the solution set, the optimal or suboptimal solution is found to provide support and guidance for path planning.

[0075] For example, F(x) = f1(x) + f2(x) + f3(x);

[0076] In the formula, f1(x) = k1 × (actual accuracy-target accuracy) 2 , f2(x) = k2 × energy consumption, f3(x) = k3 × (obstacle avoidance safety distance-safety distance threshold), k1-k3 are weight coefficients for adjusting the priority of different objectives, f1(x) is the accuracy cost, f2(x) is the energy consumption cost, which depends on the driving mode of the broken robot. If it is electric energy driving, the energy consumption cost is the product of the electric energy consumption and the electric energy cost. If it is fuel driving, the energy consumption cost is the product of the fuel consumption and the fuel cost. f3(x) is the obstacle avoidance cost, which represents the safety loss of the broken robot in the obstacle avoidance process; wherein the safety distance threshold is generally 70 cm.

[0077] Returning to Fig. 1, step 4 of the embodiment, in response to the risk category being only the overturning risk, the overturning direction of the broken robot is determined according to the attitude information of the broken robot and the overturning line, and the attitude of the broken robot is adjusted according to the overturning direction.

[0078] It should be noted that the broken robot will overturn along a certain overturning line, and the overturning line refers to the axis around which the whole vehicle turns when it overturns.

[0079] According to existing experience, the overturning line mainly includes a longitudinal overturning line, a lateral overturning line and an oblique overturning line. The longitudinal overturning line includes the intersection of the vertical plane where the center of the front walking wheel on both sides of the tracked chassis is located and the ground, and the intersection of the vertical plane where the center of the rear walking wheel on both sides is located and the ground; the lateral overturning line includes the intersection of the vertical plane where the walking wheel on one side of the tracked chassis is located and the ground, and the intersection of the vertical plane where the walking wheel on the other side of the tracked chassis is located and the ground; the oblique overturning line is the intersection of the vertical plane where the intersection point is located and the ground; wherein the diagonal line is the diagonal line of the quadrilateral enclosed by all longitudinal overturning lines and lateral overturning lines, and the intersection point is the intersection point of the longitudinal overturning line and the lateral overturning line. The setting of the overturning line can be seen from Fig. 2, there are 2 longitudinal overturning lines, 2 lateral overturning lines and 4 oblique overturning lines.

[0080] It should be noted that the overturning direction is determined, that is, the maximum probability overturning line of the breaking robot is determined, and therefore in some embodiments, the specific process of determining the overturning direction of the breaking robot can include:

[0081] 41) According to the overturning angle on the overturning line in the attitude information, the probability that each overturning angle exceeds the corresponding angle threshold is calculated.

[0082] It should be noted that assuming that there are N overturning lines, N = 8, and the overturning angles on each overturning line are represented as θ1~ θ N , the angle threshold corresponding to each overturning line is represented as [θ1]~ [θ N ](Here, the angle threshold is generally 30°), and the probability distribution of the overturning angle on each overturning line can be represented as P(θ i ), where i = 1, 2, …, N.

[0083] The most dangerous overturning line with the maximum probability is realized by comparing the probability that each overturning line exceeds the angle threshold, and the maximum probability that exceeds the angle threshold found is P max , which is represented as: P max = max(P(θ1>[θ1]), P(θ2>[θ2]), …, P(θ N >[θ N ]);

[0084] The overturning line corresponding to P max is the most dangerous overturning line, that is, the breaking robot is likely to overturn along the most dangerous overturning line.

[0085] 42) According to the overturning line corresponding to the maximum probability, the overturning direction of the breaking robot is determined.

[0086] It should be noted that after the most dangerous overturning line is determined, the maximum probability overturning direction is also known.

[0087] In order to prevent overturning, the posture of the breaking robot can be adjusted according to the overturning direction, specifically by controlling the mechanical arm, for example: the breaking robot has the possibility of overturning along the longitudinal overturning line 1, then the mechanical arm is retracted backward; the breaking robot has the possibility of overturning along the longitudinal overturning line 2, then the mechanical arm is extended forward. Adjustment is mainly torque adjustment through the movement of the mechanical arm, such as a three-section mechanical arm structure, the vehicle body and one section of the arm, one section of the arm and two sections of the arm, two sections of the arm and three sections of the arm, and the three sections of the arm at the end effector are connected by oil cylinders. The extension and retraction of each oil cylinder changes the posture and adjusts the torque again. This is a continuous adjustment process (a relatively common process, which is not described in detail here), until the breaking robot is free of overturning risk.

[0088] Returning to FIG. 1, step 5 of the embodiment, in response to the risk category including the overturning risk and the walking path risk, determining the overturning direction of the forced-entry robot according to the posture information of the forced-entry robot and the overturning line, adjusting the posture of the forced-entry robot according to the overturning direction, and replanning the walking path of the forced-entry robot according to the environmental information of the forced-entry robot after the overturning risk is removed, and controlling the forced-entry robot by using the replanned walking path.

[0089] The above method determines the posture of the forced-entry robot according to the posture information of the forced-entry robot in the walking process of the forced-entry robot, judges the risk category by using the neural network, replans the walking path when only the walking path risk exists, determines the overturning direction of the forced-entry robot when only the overturning risk exists, adjusts the posture of the forced-entry robot according to the overturning direction, and preferentially processes the overturning risk and then processes the walking path risk when both the walking path risk and the overturning risk exist, thereby reducing the overturning risk and the walking path risk of the forced-entry robot in the walking process in a complex environment and effectively improving the stability and safety of the forced-entry robot in the complex environment.

[0090] It should be noted that in addition to walking, the forced-entry robot will also perform work in the scene, mainly including forced-entry work, rotary stone-pushing work and excavation work. During the work, the forced-entry robot will extend the support legs around to ensure stability during the work.

[0091] However, if a certain support leg always supports a relatively large gravity during a long work process, the service life of the support leg will be greatly reduced. Therefore, the second method implemented in real time during the work process of the forced-entry robot is also disclosed in the present disclosure.

[0092] FIG. 3 is a schematic diagram of one embodiment of the second method of the present disclosure, and the embodiment of FIG. 3 can be executed by the vehicle-mounted controller of the forced-entry robot.

[0093] As shown in FIG. 3, S1 of the embodiment, the posture of the forced-entry robot is determined according to the posture information of the forced-entry robot.

[0094] It should be noted that the posture determination process is consistent with that in the first method, which is not repeated here.

[0095] Returning to FIG. 3, S2 of the embodiment, whether the forced-entry robot has an overturning risk is judged according to the posture of the forced-entry robot, the posture information of the forced-entry robot and the overturning line.

[0096] It should be noted that the overturning risk here refers to the tendency of the forced-entry robot to overturn to one side, which means that the support leg on the side bears a relatively large force and needs to be adjusted.

[0097] Since the support leg supports the forced-entry robot, the torque can be directly used for judgment here, and the specific process can be as follows:

[0098] S21) According to the moment length of the center of gravity of the forced-entry robot component in the attitude information and the corresponding overturning line, the stability coefficient of the forced-entry robot is calculated; wherein the corresponding overturning line is the overturning line corresponding to the attitude of the forced-entry robot.

[0099] The center of gravity of the forced-entry robot component can be seen from Figures 4 and 5, from which it can be seen that the corresponding overturning line is different under different attitudes. Figure 4 is a horizontal attitude, and the corresponding overturning line is a longitudinal overturning line 1. The attitude of the uphill corresponds to the longitudinal overturning line 2. Other attitudes have different overturning lines, such as downhill, which is also a longitudinal overturning line 1, and one side tilt can be a lateral overturning.

[0100] The stability coefficient of the forced-entry robot can be the ratio of the stability moment of the forced-entry robot to the overturning moment. The disclosure can be as follows: K = M1 / M0; M1 = G7 x L7 + G6 x L6 + G5 x L5 + G3 x L3 + G2 x L2 + G1 x L1; M0 = G4 x L4;

[0101] In the formula, K is the stability coefficient of the forced-entry robot, M1 is the stability moment of the forced-entry robot, M0 is the overturning moment of the forced-entry robot, G7-G1 are the weights of the forced-entry robot's shed, mechanical arm, hydraulic system, electrical system, power system, rotating platform and tracked chassis, respectively, and L7-L1 are the distances from the center of gravity of the shed to the corresponding overturning line, the center of gravity of the mechanical arm to the corresponding overturning line, the center of gravity of the hydraulic system to the corresponding overturning line, the center of gravity of the electrical system to the corresponding overturning line, the center of gravity of the power system to the corresponding overturning line, the center of gravity of the rotating platform to the corresponding overturning line and the center of gravity of the tracked chassis to the corresponding overturning line, respectively.

[0102] S22) In response to the stability coefficient of the forced-entry robot being less than the stability threshold (generally 1.15), it is determined that the forced-entry robot has an overturning risk.

[0103] Returning to S3 of the embodiment shown in 3, in response to the existence of the overturning risk, the overturning direction of the forced-entry robot is determined according to the attitude information and the overturning line of the forced-entry robot, and the attitude of the forced-entry robot is adjusted according to the overturning direction.

[0104] It should be noted that the determination of the overturning direction of the forced-entry robot and the adjustment method are consistent with those in the first method, which will not be described here.

[0105] The above method determines the attitude of the forced-entry robot according to the attitude information of the forced-entry robot during the working process of the forced-entry robot, judges whether there is an overturning risk by using the stability moment and the overturning moment, determines the overturning direction of the forced-entry robot when there is an overturning risk, and adjusts the attitude of the forced-entry robot according to the overturning direction, so as to adjust the stress of the supporting leg and reduce the risk of damage to the supporting leg, thereby effectively improving the stability and safety of the forced-entry robot in complex environments.

[0106] It should be noted that the breaking robot is inevitable to have emergency situations in the process of walking and working, such as component damage, oil leakage, battery low power, etc. At this time, the remote control end will issue an emergency stop instruction. At this time, the breaking robot may have a risk of overturning due to inertia, such as emergency stop when walking forward, which may be prone to forward overturning. Therefore, the third method for implementing emergency stop in the process of working or walking of the breaking robot is also disclosed in the present disclosure.

[0107] FIG. 5 is a schematic diagram of an embodiment of the third method of the present disclosure. The embodiment of FIG. 5 can be executed by the vehicle-mounted controller of the breaking robot.

[0108] As shown in FIG. 5, A1 of the embodiment, according to the attitude information of the breaking robot, the attitude of the breaking robot is determined.

[0109] It should be noted that the attitude determination process is consistent with the first method, which is not repeated here.

[0110] Returning to FIG. 5, A2 of the embodiment, according to the attitude of the breaking robot, the attitude information of the breaking robot when emergency stop, and the overturning line, it is judged whether the breaking robot has a risk of overturning.

[0111] It should be noted that the specific process of this step can be the same as in the second method, which is not repeated here.

[0112] Returning to FIG. 5, A3 of the embodiment, in response to the existence of the risk of overturning, according to the attitude information of the breaking robot when emergency stop, the overturning direction of the breaking robot is determined, and the attitude of the breaking robot is adjusted according to the overturning direction.

[0113] It should be noted that due to the inertia of overturning when emergency stop, only the attitude at the time of emergency stop needs to be known, that is, the corresponding overturning line, that is, the overturning direction, is known. Taking the example of emergency stop when walking forward, the overturning direction is forward overturning, and the corresponding overturning line is the longitudinal overturning line 1.

[0114] It should be noted that the adjustment method is consistent with the first method, which is not repeated here.

[0115] The above method determines the attitude of the breaking robot according to the attitude information of the breaking robot in the process of emergency stop of the breaking robot, judges whether there is a risk of overturning by using the stable moment and the overturning moment, determines the overturning direction of the breaking robot when there is a risk of overturning, and adjusts the attitude of the breaking robot according to the overturning direction, thereby ensuring the stability when emergency stop, and effectively improving the stability and safety of the breaking robot in complex environment.

[0116] The disclosure also discloses a virtual device corresponding to the above method, namely a disassembly robot risk control device, which can be loaded and executed by a vehicle-mounted controller of the disassembly robot, and specifically includes a first device that works in real time during walking of the disassembly robot, a second device that works in real time during working of the disassembly robot, and a third device that works in an emergency stop during working or walking of the disassembly robot.

[0117] The first device includes a working condition module, a risk category module, a path planning module, and a stability control module.

[0118] The working condition module of the embodiment is configured to determine the posture of the disassembly robot according to the posture information of the disassembly robot.

[0119] The risk category module of the embodiment is configured to determine the risk category of the disassembly robot according to the posture parameter of the disassembly robot, the posture information of the disassembly robot, and the environment information of the disassembly robot, using a trained neural network.

[0120] The path planning module of the embodiment is configured to, in response to the risk category being a walking path risk, re-plan a walking path according to the environment information of the disassembly robot, and control the disassembly robot using the re-planned walking path.

[0121] The stability control module of the embodiment is configured to, in response to the risk category being a tipping risk, determine the tipping direction of the disassembly robot according to the posture information of the disassembly robot and the tipping line, and adjust the posture of the disassembly robot according to the tipping direction.

[0122] The second device includes a working condition module, a risk judgment module, and a first posture adjustment module.

[0123] The working condition module of the embodiment is configured to determine the posture of the disassembly robot according to the posture information of the disassembly robot.

[0124] The risk judgment module of the embodiment is configured to judge whether the disassembly robot has a tipping risk according to the posture of the disassembly robot, the posture information of the disassembly robot, and the tipping line.

[0125] The first posture adjustment module of the embodiment is configured to, in response to the existence of the tipping risk, determine the tipping direction of the disassembly robot according to the posture information of the disassembly robot and the tipping line, and adjust the posture of the disassembly robot according to the tipping direction.

[0126] The third device includes a working condition module, a risk judgment module, and a second posture adjustment module.

[0127] The working condition module of the embodiment is configured to determine the posture of the disassembly robot according to the posture information of the disassembly robot.

[0128] The risk judgment module of the embodiment is configured to: judge whether the demolition robot has a risk of overturning according to the posture of the demolition robot, the posture information when the demolition robot stops urgently, and the overturning line.

[0129] The second posture adjustment module of the embodiment is configured to: in response to the risk of overturning, determine the overturning direction of the demolition robot according to the posture information when the demolition robot stops urgently, and adjust the posture of the demolition robot according to the overturning direction.

[0130] The above device ensures the stability of the demolition robot when walking, working, and stopping urgently, and effectively improves the stability and safety of the demolition robot in a complex environment.

[0131] Based on the same technical solution, the present disclosure also relates to a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions that, when executed by a computing device, cause the computing device to perform the risk control method of the demolition robot.

[0132] Based on the same technical solution, the present disclosure also relates to a computer device, which includes one or more processors and one or more memories, and one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for executing the risk control method of the demolition robot.

[0133] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0134] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0135] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart or flowsheets and / or block or blocks of the block diagrams.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheets and / or block or blocks of the block diagrams.

[0137] The above merely provides an embodiment of the present application, but is not intended to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A risk control method for a demolition robot, characterized in that, The first method includes a method implemented in real time during the movement of the demolition robot, the first method comprising: The orientation of the demolition robot is determined based on its orientation information. Based on the posture parameters of the demolition robot, the posture information of the demolition robot, and the environmental information described by the demolition robot, a trained neural network is used to determine the risk category of the demolition robot. In response to the risk category being only walking path risk, the walking path is replanned based on the environmental information provided by the demolition robot, and the demolition robot is controlled using the replanned walking path. In response to the risk category being only overturning risk, the overturning direction of the demolition robot is determined based on the robot's posture information and overturning line, and the robot's posture is adjusted according to the overturning direction. In response to risk categories including overturning risk and walking path risk, the overturning direction of the demolition robot is determined based on the robot's posture information and overturning line. The robot's posture is adjusted according to the overturning direction. Once the overturning risk is eliminated, the walking path is replanned based on the environmental information provided by the demolition robot, and the replanned walking path is used to control the demolition robot.

2. The risk control method for demolition robots according to claim 1, characterized in that, It also includes a second method implemented in real time during the operation of the demolition robot, the second method including: The orientation of the demolition robot is determined based on its orientation information. Based on the robot's posture, posture information, and overturning line, determine whether the robot is at risk of overturning. In response to the risk of tipping over, the tilting direction of the demolition robot is determined based on its posture information and tilting line, and the robot's posture is adjusted accordingly.

3. The risk control method for demolition robots according to claim 1 or 2, characterized in that, Based on the attitude information and overturning line of the demolition robot, determine the overturning direction of the demolition robot, including: Based on the overturning angles on the overturning line in the attitude information, calculate the probability that each overturning angle exceeds the corresponding angle threshold; The tilting direction of the demolition robot is determined based on the tilting line corresponding to the highest probability.

4. The risk control method for demolition robots according to claim 1, characterized in that, This also includes a third method for implementing emergency stops during the operation or movement of the demolition robot, which includes: The orientation of the demolition robot is determined based on its orientation information. Based on the robot's posture, posture information during emergency stops, and overturning line, determine whether the robot is at risk of overturning. In response to the risk of tipping over, the tilting direction of the demolition robot is determined based on its posture information during an emergency stop, and the robot's posture is adjusted accordingly.

5. The risk control method for demolition robots according to claim 2 or 4, characterized in that, Determining whether a demolition robot poses a risk of tipping over includes: The stability coefficient of the demolition robot is calculated based on the moment length between the center of gravity of the demolition robot component and the corresponding overturning line in the posture information. The stability coefficient of the demolition robot is the ratio of the stability moment to the overturning moment of the demolition robot, and the corresponding overturning line is the overturning line corresponding to the posture of the demolition robot. If the stability coefficient of the demolition robot is less than the stability threshold, it is determined that the demolition robot is at risk of tipping over.

6. The risk control method for demolition robots according to claim 5, characterized in that, The formula for calculating the stability coefficient of the demolition robot is: K=M1 / M0; M1=G7×L7+G6×L6+G5×L5+G3×L3+G2×L2+G1×L1; M0=G4×L4; In the formula, K is the stability coefficient of the demolition robot, M1 is the stabilizing torque of the demolition robot, M0 is the overturning torque of the demolition robot, G7~G1 are the gravity of the demolition robot's canopy, robotic arm, hydraulic system, electrical system, power system, rotating platform and tracked chassis, respectively, and L7~L1 are the distances between the center of gravity of the canopy and the corresponding overturning line, the center of gravity of the robotic arm and the corresponding overturning line, the center of gravity of the hydraulic system and the corresponding overturning line, the center of gravity of the electrical system and the corresponding overturning line, the center of gravity of the power system and the corresponding overturning line, the center of gravity of the rotating platform and the corresponding overturning line, and the center of gravity of the tracked chassis and the corresponding overturning line, respectively.

7. The risk control method for demolition robots according to claim 1, 2, or 4, characterized in that, Based on the attitude information of the demolition robot, determine the attitude of the demolition robot, including: Calculate the front and rear height difference of the two tracks at the same moment in the attitude information; If the height difference between the front and rear of both tracks is greater than 0 and greater than the first threshold for height difference, the demolition robot is in an uphill posture; where the height difference between the front and rear of both tracks is a parameter of the uphill posture. If the front and rear height differences of the two tracks are both less than 0 and less than the negative value of the first threshold of height difference, then the demolition robot is in a downhill posture; where the front and rear height differences of the two tracks are parameters of the downhill posture. Calculate the height difference between the left and right tracks at the same moment in the attitude information; If the height difference between the left and right tracks is greater than the second threshold for height difference, the demolition robot is determined to be in a tilted posture; where the height difference between the left and right tracks is a parameter of the tilted posture. If the height difference between the front and rear of the two tracks is within the range of the first threshold and the negative value of the first threshold, and the height difference between the left track and the right track is not greater than the second threshold of height difference, then the demolition robot is determined to be in a horizontal posture; where the parameter of the horizontal posture is 0.

8. A risk control device for a demolition robot, characterized in that, The first device includes a device that operates in real time during the movement of the demolition robot. The working condition module determines the posture of the demolition robot based on its posture information. The risk category module uses a trained neural network to determine the risk category of the demolition robot based on its posture parameters, posture information, and environmental information. The path planning module, in response to the risk category of walking path risk, replans the walking path based on the environmental information provided by the demolition robot, and uses the replanned walking path to control the demolition robot. The stabilization control module, in response to the risk category of overturning risk, determines the overturning direction of the demolition robot based on the robot's posture information and overturning line, and adjusts the robot's posture according to the overturning direction. The sequence control module, in response to risk categories including overturning risk and walking path risk, determines the overturning direction of the demolition robot based on the robot's posture information and overturning line, adjusts the robot's posture according to the overturning direction, and replans the walking path based on the environmental information provided by the demolition robot after the overturning risk is removed, and controls the demolition robot using the replanned walking path.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the method of any one of claims 1 to 7.

10. A computer device, characterized in that, include: One or more processors and one or more memories, one or more programs stored in one or more memories and configured to be executed by one or more processors, the one or more programs including instructions for performing the method of any one of claims 1 to 7.

Images