Humanoid robot falling control method, device and equipment and storage medium

Abstract

The invention provides a humanoid robot falling control method, device and equipment and a storage medium, and relates to the technical field of humanoid robots. The control method comprises the following steps: acquiring state data of the humanoid robot in real time; predicting the current state of the humanoid robot according to the state data; and if the current state is the high-risk tumble state, controlling the humanoid robot to execute tumble protection action. According to the fall control method for the humanoid robot, the accuracy of fall prediction is improved by monitoring the gravity center position, the movement speed and the acceleration in real time. The method can quickly start the protection action under the high-risk condition, reduce the damage risk and protect the safety of surrounding personnel. The adaptability and autonomy of the robot are enhanced, the stability and safety are improved, the maintenance cost is reduced, and the service life is prolonged, so that the practicability and market competitiveness of the robot are enhanced, and the application range is widened.

Description

Technical Field

[0001] The present application relates to the technical field of humanoid robots, and in particular to a method, device, equipment and storage medium for controlling a fall of a humanoid robot. Background Art

[0002] As an important branch of the field of robotics, humanoid robots have shown broad application potential in many fields such as service, rescue, and entertainment with their ability to imitate human behavior. This type of robot is designed to simulate the bipedal walking mechanism of humans, enabling it to perform tasks in complex and changing environments. However, due to its high dynamics and environmental uncertainty, humanoid robots face the risk of falling when performing tasks, which not only affects the safety of the robot itself, but also the safety of people around it.

[0003] In the prior art, fall prediction of humanoid robots mainly relies on data provided by the inertial measurement unit (IMU). The IMU can measure the linear acceleration and angular velocity of the robot, providing basic data for fall detection. However, this single sensor approach has limitations in capturing subtle changes in the robot's posture, especially in complex environments where the robot may lose balance due to a variety of factors (such as uneven ground, external force interference, etc.). This limits the accuracy and real-time nature of fall prediction, resulting in the robot being unable to respond in time when facing the risk of falling.

[0004] In addition, existing fall protection solutions mostly rely on mechanical structures or simple emergency braking mechanisms. These solutions often lack flexibility in design and cannot adapt to changing fall scenarios. For example, some protection mechanisms may be effective when the robot falls backwards, but not sufficient to provide adequate protection when it falls sideways. This limitation makes the existing protection measures limited in effect in practical applications and cannot effectively reduce the damage caused by falls to the robot.

[0005] In summary, existing technologies have significant deficiencies in fall prediction and protection for humanoid robots. The limitations of IMU data affect the accuracy of fall prediction, while existing protection schemes lack flexibility and adaptability and are difficult to cope with complex fall scenarios. These problems limit the stability and safety of humanoid robots in complex environments and increase the risk of robot operation. Therefore, the development of more accurate and flexible fall prediction and protection technologies is of great significance to improving the practicality and reliability of humanoid robots. Summary of the invention

[0006] In a first aspect, the present invention provides a humanoid robot fall control method, comprising:

[0007] Acquiring status data of the humanoid robot in real time; the status data includes center of gravity position, movement speed and acceleration;

[0008] predicting a current state of the humanoid robot according to the state data;

[0009] If the current state is a high-risk fall state, the humanoid robot is controlled to perform a fall protection action.

[0010] In an optional implementation, predicting the current state of the humanoid robot according to the state data includes:

[0011] Using a model predictive control algorithm, taking the center of gravity position, the movement speed and the acceleration as input, and using a robot whole body dynamics model to determine whether the humanoid robot reaches a preset trigger condition;

[0012] If yes, determining that the current state of the humanoid robot is a high-risk falling state;

[0013] If not, it is determined that the current state of the humanoid robot is not a high-risk falling state.

[0014] In an optional implementation manner, the preset trigger condition includes at least one of the following conditions:

[0015] A. The center of gravity position exceeds the preset safety range;

[0016] B. The change in acceleration exceeds a preset acceleration change threshold;

[0017] C. The decreasing speed of the movement speed exceeds a preset decreasing threshold.

[0018] In an optional implementation, the fall protection action includes:

[0019] Confirming a falling direction and a current robot key protection area corresponding to the falling direction; the current robot key protection area includes legs, vulnerable joints and collision joints; the vulnerable joints include hand joints and head joints; the collision joints include at least one of a knee joint, a hip joint and an elbow joint;

[0020] Controlling the legs to be in a bent state to lower the center of gravity of the humanoid robot;

[0021] Controlling the fragile joint to adjust to a safe posture;

[0022] Controlling the collision joint to enable a smooth collision function;

[0023] The security posture includes at least one of the following methods:

[0024] A. Adjust the hand joints to form a fist;

[0025] B. Adjust the hand joints and bend the elbows to the chest area;

[0026] C. Adjust the head to tilt toward the chest to form a bowed position.

[0027] In an optional implementation, the confirming the falling direction and the current robot key protection area corresponding to the falling direction includes:

[0028] Using an inertial measurement unit to monitor the attitude angle data of the humanoid robot in real time; the attitude angle data includes the absolute value of the elevation angle and / or the roll angle;

[0029] If the posture angle reaches 0.5 radians, it is determined that the humanoid robot is currently in an unstable state, and the legs and / or the vulnerable joints are used as key protection areas of the current robot;

[0030] If the posture angle reaches 1.05 radians, it is determined that the humanoid robot is currently in a tipping state, and the collision joint is used as the key protection area of ​​the current robot.

[0031] In an optional embodiment, the smooth collision function includes:

[0032] The external force and actual speed of the collision joint are monitored in real time; when the external force is sensed to act on the collision joint, the joint acceleration generated by the joint is calculated according to the dynamic model; the expression of the dynamic model is:

[0033]

[0034] Wherein, F represents the fall collision force; M represents the mass parameter of the collision joint; D represents the damping parameter of the collision joint; v real represents the actual speed; a rate of change of the joint acceleration representing the collision joint;

[0035] The joint acceleration is used to control the collision joint to comply with the external force movement; and the damping parameter and the mass parameter are dynamically adjusted according to the actual speed of the collision joint.

[0036] In an optional implementation, after controlling the humanoid robot to perform a fall protection action, the method further includes:

[0037] Performing fault self-checking, posture and position detection, and environmental perception on the humanoid robot, and obtaining self-checking results, posture and position information, and environmental perception results respectively;

[0038] Establishing motion planning data according to the self-check result, the posture position information and the environment perception result;

[0039] Determining whether the humanoid robot can simulate recovery to a stable posture according to the motion planning data;

[0040] If yes, adjusting the current posture of the humanoid robot according to the motion planning data; using a segmented motion strategy to adjust the position and angle of the upper body and / or lower body until the stable posture is restored;

[0041] If not, the motion is determined to be obstructed, the posture adjustment is stopped, and a warning is generated.

[0042] In a second aspect, the present invention provides a humanoid robot fall control device, comprising:

[0043] A monitoring module, used to obtain the status data of the humanoid robot in real time; the status data includes the center of gravity position, movement speed and acceleration;

[0044] A prediction module, used for predicting the current state of the humanoid robot according to the state data;

[0045] The protection module is used to control the humanoid robot to perform a fall protection action when the current state is a high-risk fall state.

[0046] In a third aspect, the present invention provides a computer device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the humanoid robot fall control method described in any one of the aforementioned embodiments.

[0047] In a fourth aspect, the present invention provides a computer storage medium storing a computer program, which, when executed on a processor, implements the humanoid robot fall control method according to any one of the aforementioned embodiments.

[0048] The humanoid robot fall control method provided in this application effectively overcomes the limitations of traditional reliance on a single IMU data and improves the accuracy of fall prediction by acquiring state data including center of gravity position, movement speed and acceleration in real time. It can immediately control the robot to perform protective actions when a high-risk fall state is predicted, providing a more flexible and timely response mechanism, reducing the risk of structural damage, and reducing the safety threat to surrounding personnel. In addition, the method improves the robot's stability and safety in complex environments by enhancing its environmental adaptability and autonomy, while reducing maintenance and operating costs and extending the robot's service life. In summary, this method significantly improves the practicality and market competitiveness of humanoid robots, giving them a wider range of application prospects in various scenarios such as home, industry, and rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be regarded as limiting the scope of protection of the present application. For ordinary technicians in this field, other related drawings can also be obtained based on these drawings without creative work.

[0050] Figure 1 It is a structural schematic diagram of the hardware operating environment involved in the embodiment of the humanoid robot fall control method of the present invention;

[0051] Figure 2 1 is a flow chart of a first embodiment of a humanoid robot fall control method according to the present invention;

[0052] Figure 3 It is a schematic diagram of a detailed flow chart of step S200 in the second embodiment of the humanoid robot fall control method of the present invention;

[0053] Figure 4 1 is a schematic diagram of the overall flow chart of the third embodiment of the humanoid robot fall control method of the present invention, including the refinement of step S300;

[0054] Figure 5 1 is a schematic diagram of a detailed flow chart of step S310 in the third embodiment of the humanoid robot fall control method of the present invention;

[0055] Figure 6 This is a supplementary flowchart of step S400 to step S800 in the fourth embodiment of the humanoid robot fall control method of the present invention;

[0056] Figure 7 A schematic diagram of module connections of a humanoid robot fall control device according to the present invention;

[0057] Figure 8 The overall structure and working process diagram of the humanoid robot fall control device of the present invention;

[0058] Fig. 9 It is a flowchart of three different stages when the humanoid robot fall control device of the present invention executes the method. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0060] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0061] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0062] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0063] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0064] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0065] like Figure 1 , which is a schematic diagram of the structure of the hardware operating environment of the terminal involved in the embodiment of the present invention.

[0066] The humanoid robot fall control system of the embodiment of the present invention can be a PC, or a mobile terminal device such as a smart phone, a tablet computer or a portable computer. The humanoid robot fall control system may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005 and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen, an input unit such as a keyboard, and a remote control. The user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory, such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001. Optionally, the humanoid robot fall control system may also include an RF (Radio Frequency) circuit, an audio circuit, a WiFi module, and the like. In addition, the humanoid robot fall control system can also be configured with other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which will not be described in detail here.

[0067] Those skilled in the art will understand that Figure 1 The humanoid robot fall control system shown in the figure does not constitute a limitation thereof, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a data interface control program, a network connection program, and a humanoid robot fall control program.

[0068] In summary, the method provided by the present invention improves the accuracy of fall prediction by real-time monitoring of key status data, and can quickly respond to high-risk fall states and perform protective actions. This method reduces robot structural damage, reduces safety risks to surrounding personnel, improves the environmental adaptability and economy of the robot, and enhances its stability and reliability in a changing environment.

[0069] Embodiment 1:

[0070] Reference Figure 2 , this embodiment provides a humanoid robot fall control method, comprising:

[0071] Step S100, acquiring the status data of the humanoid robot in real time; the status data includes the center of gravity position, movement speed and acceleration.

[0072] The humanoid robot mentioned in this embodiment, i.e., a humanoid robot, is a high-tech product designed to imitate human appearance and behavior. They have a human-like head, torso, arm and leg structure, and can move flexibly and perform various actions. These robots usually have multiple degrees of freedom, can walk on two feet, adapt to uneven ground and go up and down stairs, so that they can be seamlessly integrated in the environment where humans live and work. Humanoid robots are also equipped with advanced sensors and artificial intelligence technologies, including machine learning, natural language processing and computer vision, to achieve autonomous decision-making and the execution of complex tasks. They are widely used in many fields such as service industry, education, entertainment, industrial automation, disaster relief, etc., and as a research platform, they have promoted the development of related technologies such as motion control, human-computer interaction and cognitive science. With the continuous advancement of technology, the autonomy and intelligence level of humanoid robots are constantly improving, and their role and influence in human society are also expanding.

[0073] Humanoid robots require specific fall control methods, mainly because they mimic the bipedal walking mechanism of humans, which makes them face more complex challenges in dynamic balance control, especially when adapting to complex environments such as uneven ground, stairs, and narrow spaces. In addition, in order to ensure safety when working in an environment that interacts with humans and avoid falls that cause harm to personnel and equipment, effective fall control methods are essential. Finally, fall control methods help reduce maintenance costs, extend service life, and improve task execution efficiency, thereby improving the economy and practicality of humanoid robots.

[0074] The above steps involve using sensors to monitor the key status data of the humanoid robot in real time. The status data includes the center of gravity position, movement speed and acceleration, which are crucial for evaluating the stability of the robot and predicting the risk of falling. By acquiring this data in real time, the robot's movement status and possible imbalance trends can be accurately captured, providing the necessary information for subsequent fall prediction.

[0075] Specifically, this can be achieved through sensors integrated into the robot, such as inertial measurement units (IMUs), force sensors, etc. The IMU can provide data about acceleration and angular velocity, while the force sensor can provide information about the contact force between the robot and the ground, which together help determine the center of gravity.

[0076] Step S200: predicting the current state of the humanoid robot according to the state data.

[0077] In the above, the state data obtained in the first step is analyzed, and an algorithm is used to predict the current stability state of the robot to determine whether there is a risk of falling. The prediction results can help identify whether the robot is in a high-risk state of falling, so that measures can be taken in advance.

[0078] Specifically, machine learning algorithms, such as random forest, support vector machine (SVM) or neural network, can be used to train models based on historical data to predict the risk of falls.

[0079] Step S300: If the current state is a high-risk fall state, control the humanoid robot to perform a fall protection action.

[0080] As mentioned above, when the prediction results show that the robot is at a high risk of falling, the system will automatically trigger the preset fall protection action to reduce the damage caused by the fall. Executing the fall protection action can significantly reduce the damage to the robot when it falls, protect key components, and ensure that the robot can quickly return to normal.

[0081] The fall protection action can be implemented through a preset control strategy, such as adjusting the joint angle to absorb the impact, starting the compliance control to reduce joint damage, etc. The specific control algorithm can adopt PID control or a more advanced adaptive control algorithm.

[0082] The humanoid robot fall control method provided in this embodiment effectively overcomes the limitations of traditional reliance on a single IMU data and improves the accuracy of fall prediction by acquiring state data including the center of gravity position, movement speed and acceleration in real time. It can immediately control the robot to perform protective actions when a high-risk fall state is predicted, providing a more flexible and timely response mechanism, reducing the risk of structural damage, and reducing the safety threat to surrounding personnel. In addition, the method improves the robot's stability and safety in complex environments by enhancing its environmental adaptability and autonomy, while reducing maintenance and operating costs and extending the robot's service life. In summary, this method significantly improves the practicality and market competitiveness of humanoid robots, giving them a wider range of application prospects in various scenarios such as home, industry, and rescue.

[0083] Embodiment 2:

[0084] Reference Figure 3 This embodiment provides a humanoid robot fall control method. Based on the above embodiment 1, the step S200 predicts the current state of the humanoid robot according to the state data, including:

[0085] Step S210, using a model predictive control algorithm, taking the center of gravity position, the movement speed and the acceleration as input, and using a robot whole-body dynamics model to determine whether the humanoid robot reaches a preset trigger condition.

[0086] The above steps involve using a Model Predictive Control (MPC) algorithm to process the state data acquired in real time. MPC is an advanced control strategy that uses the robot's dynamic model to predict future behavior and optimize control inputs. By using MPC, the robot's future state can be predicted based on its dynamic model, thereby more accurately determining the risk of falling.

[0087] The specific implementation of MPC requires the establishment of a mathematical model of the robot, which describes the robot's dynamic behavior, including the relationship between the center of gravity position, movement speed and acceleration.

[0088] As mentioned above, the center of gravity position, motion speed and acceleration data acquired in real time are used as input parameters of the MPC algorithm. These data provide the current motion state of the robot, and the MPC algorithm can use this information to predict the future state and make more accurate control decisions.

[0089] These data can be obtained by direct measurement of sensors. For example, IMU sensors provide acceleration and angular velocity data, while the movement speed can be obtained by integrating acceleration data.

[0090] In the above, the robot's whole-body dynamics model is used to evaluate the current state data and determine whether the preset fall risk trigger conditions are met. The whole-body dynamics model can provide a more comprehensive understanding of the robot's motion state, thereby more accurately identifying the fall risk. Specifically, a complex mathematical model that can describe the dynamic behavior of all joints and body parts of the robot may be required. This model can be a physics-based model or a data-driven model.

[0091] Step S220: If yes, it is determined that the current state of the humanoid robot is a high-risk falling state.

[0092] Step S230: If not, it is determined that the current state of the humanoid robot is not a high-risk falling state.

[0093] As described above, the prediction results of the MPC algorithm are used to finally determine whether the robot is at a high risk of falling. This judgment provides a clear basis for decision-making, enabling the robot to quickly take protective measures when a high risk of falling is predicted.

[0094] A series of thresholds or rules can be set, and when the prediction results of the MPC algorithm exceed these thresholds, it is determined to be a high-risk fall state.

[0095] Furthermore, the preset trigger condition includes at least one of the following conditions:

[0096] A. The center of gravity position exceeds the preset safety range.

[0097] As described above, the center of gravity position of the humanoid robot is monitored and compared with a preset safety range. If the center of gravity position of the robot is outside this range, this may mean that the robot is about to lose balance. By monitoring the center of gravity position, risks can be identified in time before the robot is about to fall, so that preventive measures can be taken. The center of gravity position can be monitored in real time by sensors integrated inside the robot, such as IMU. Then, the monitored center of gravity position is compared with the preset safety range.

[0098] For example, assuming C is the current center of gravity, C safe is the preset safety range, then: if |CC safe ∣>∈, then the fall protection action is triggered. ∈ is the set threshold, indicating the boundary of the safety range.

[0099] B. The change in acceleration exceeds a preset acceleration change threshold.

[0100] As mentioned above, this condition involves monitoring the acceleration change of the humanoid robot and comparing it with a preset acceleration change threshold. If the acceleration change exceeds this threshold, it may mean that the robot has encountered a sudden external force or violent movement. By monitoring the acceleration change, sudden movement or impact that may cause a fall can be detected.

[0101] The change in acceleration can be monitored by the IMU sensor. Then, the rate of change of acceleration is calculated and compared with the preset threshold.

[0102] For example, assuming a is the current acceleration, a th The preset acceleration change threshold, then: if |aa prev ∣>a th , then the fall protection action is triggered, where a prev is the acceleration at the previous moment.

[0103] C. The decreasing speed of the movement speed exceeds a preset decreasing threshold.

[0104] The above conditions involve monitoring the decrease in the speed of the humanoid robot and comparing it with a preset decrease threshold. If the speed decreases too quickly, it may mean that the robot is losing power or control. By monitoring the decrease in the speed of movement, the possible loss of control of the robot can be identified and timely measures can be taken to prevent it from falling. The change in the speed of movement can be monitored by a speed sensor. Then, the rate of change of the speed is calculated and compared with the preset threshold.

[0105] For example, assuming v is the current speed, v th is the preset speed drop threshold, then: if d v / dt <-v th , then the fall protection action is triggered; where d v / d t Indicates the rate of change of speed.

[0106] Embodiment 3:

[0107] Reference Figure 4 This embodiment provides a humanoid robot fall control method. Based on the above embodiment 1, further, in step S300, the fall protection action includes:

[0108] Step S310, confirming the falling direction and the current robot key protection area corresponding to the falling direction. The current robot key protection area includes legs, vulnerable joints and collision joints; the vulnerable joints include hand joints and head joints; the collision joints include at least one of the knee joint, hip joint and elbow joint.

[0109] It should be noted that confirming the direction of the fall and determining the corresponding key protection area are crucial for the fall control of humanoid robots, because this allows the robot to carry out targeted protection, optimize the allocation of limited control resources, reduce the risk of secondary injuries, improve the efficiency of recovery from the fall state, plan adaptive actions to mitigate impact, enhance the safety of working in human environments, improve the reliability and robustness of robots, and improve the interactive experience with humans. Through such prediction and protection measures, humanoid robots can respond faster and more effectively when facing a fall, thereby minimizing damage and ensuring the safety of the robot and surrounding people.

[0110] The above steps involve quickly identifying the direction of the fall after predicting the risk of a fall, and determining the areas of the robot that need to be protected, such as the legs, vulnerable joints (hand joints and head joints), and joints that may collide (knee joints, hip joints, and elbow joints). By quickly identifying the direction of the fall and the key protection areas, protective actions can be performed in a targeted manner to reduce injuries.

[0111] The direction of the fall can be determined by analyzing sensor data, such as accelerometer and gyroscope data. Then, based on the direction of the fall, the area that needs to be protected is determined.

[0112] Step S320, controlling the legs to be in a bent state to lower the center of gravity of the humanoid robot.

[0113] This step involves flexing the robot's legs by controlling the leg joints when a fall is predicted, so as to lower the center of gravity and reduce the impact force when falling. Lowering the center of gravity can increase stability and reduce injuries when falling. Specifically, the leg flexion action can be achieved by controlling the angle of the leg joints through electric servo motors.

[0114] Step S330, controlling the fragile joint to adjust to a safe posture.

[0115] As mentioned above, before falling or hitting the ground, the hand joints and head joints are adjusted to a safe posture, such as clenching fists, bending elbows to the chest area, and tilting the head to form a head-down state. Adjusting vulnerable joints to a safe posture can reduce the damage to these parts during a fall. A series of safe postures can be preset, and when the risk of falling is detected, the joints are adjusted to these postures through the control algorithm.

[0116] The security posture includes at least one of the following methods:

[0117] A. Adjust the hand joints to form a fist;

[0118] B. Adjust the hand joints and bend the elbows to the chest area;

[0119] C. Adjust the head to tilt toward the chest to form a bowed position.

[0120] As mentioned above, at the beginning of the fall, the robot uses motion planning to clench its hand joints into fists and bend its elbows so that the hands are in front of the chest and protected by the elbow joints. When falling backwards, in order to avoid the head from being hit, the robot also uses motion planning to lower its head at the beginning of the fall.

[0121] Step S340, controlling the collision joint to enable a smooth collision function.

[0122] The above-mentioned flexible collision function means that when the joint is subjected to external force, it can move accordingly following the direction and magnitude of the external force. Through this elastic collision method, the impact on the joint can be reduced.

[0123] As mentioned above, when falling, the compliance function of joints prone to collision, such as knee joints, hip joints and elbow joints, is turned on to reduce the impact. The compliance function allows the joints to have a certain deformation space when impacted, reducing damage to the joints. This can be achieved by changing the stiffness parameters of the joints or using a special compliance control algorithm.

[0124] Specifically, the specific method of implementing the fall protection action may include, first, using sensor data (such as IMU) to predict the fall direction and calculate the fall time; then, using PID control or other robot control algorithms to accurately adjust the joint angles; and, using a compliant control algorithm to dynamically adjust the stiffness of the joints to adapt to different impact situations.

[0125] It should be noted that any one of steps S320 to S340 can be performed first, or they can be performed simultaneously.

[0126] For further reference, Figure 5 The step S310, confirming the falling direction and the current robot key protection area corresponding to the falling direction, includes:

[0127] Step S311, using an inertial measurement unit to monitor the attitude angle data of the humanoid robot in real time; the attitude angle data includes the absolute value of the elevation angle and / or the roll angle.

[0128] It should be noted that the pitch angle, also known as the pitch angle, is used to describe the rotation angle of the robot around its horizontal axis (left-right direction). A positive value indicates that the robot's head is rotating upward and its tail is rotating downward, while a negative value indicates a rotation in the opposite direction. The roll angle, also known as the roll angle, is used to describe the rotation angle of the robot around its longitudinal axis (front-back direction). A positive value indicates that the robot's right side is rotating upward and its left side is rotating downward, while a negative value indicates a rotation in the opposite direction.

[0129] Pitch and roll angles are key parameters for evaluating the posture stability of humanoid robots. They can not only help predict the direction of a fall, such as determining whether the robot is tilting forward or backward by analyzing their absolute values, but also trigger protective actions when they exceed preset thresholds to stabilize the robot or initiate emergency protection measures. In addition, controlling these posture angles is crucial for maintaining dynamic balance. They allow the robot to adjust its gait and joint angles in real time to adapt to different ground conditions and movement requirements. Accurate monitoring of pitch and roll angles is also very important for improving the safety of humanoid robots, helping to avoid falls and reduce the risk of injury, especially in environments that interact with humans. Therefore, the absolute values ​​of pitch and roll are crucial for evaluating and controlling the posture stability of humanoid robots, predicting the risk of falling, triggering protective actions, and maintaining dynamic balance.

[0130] In the above steps, an inertial measurement unit (IMU) is used to monitor the elevation angle and / or roll angle of the humanoid robot in real time. By monitoring these attitude angles, the dynamic stability of the robot can be understood in real time, providing key data for subsequent fall risk assessment.

[0131] IMU sensors can provide continuous attitude angle data, which can be directly used for subsequent analysis and processing.

[0132] Step S312: If the posture angle reaches 0.5 radians, it is determined that the humanoid robot is currently in an unstable state, and the legs and / or the vulnerable joints are used as key protection areas of the current robot.

[0133] In the above, the monitored attitude angle data is compared with the preset threshold (0.5 radians) to determine whether the robot is in an unstable state. Setting the threshold can help quickly identify the unstable state of the robot and take timely measures, such as focusing on protecting the legs and vulnerable joints.

[0134] Specifically, a simple comparison algorithm can be used. When the absolute value of the attitude angle exceeds 0.5, the corresponding protection measures are triggered. If |attitude angle|>0.5 radians, it is determined to be an unstable state.

[0135] Step S313: If the posture angle reaches 1.05 radians, it is determined that the humanoid robot is currently in a tipping state, and the collision joint is used as a key protection area of ​​the current robot.

[0136] In the above, the attitude angle data is compared with another preset threshold value (1.05 radians) to determine whether the robot is in a tipping state. A higher threshold value indicates a more serious unstable state, and it is necessary to focus on protecting the joints that may collide.

[0137] Similar to the aforementioned step S312, a comparison algorithm is used, but a higher threshold is used to trigger a more urgent protection measure. If |attitude angle|>1.05 radians, it is determined to be a tipping state.

[0138] Furthermore, in step S340, the smooth collision function includes:

[0139] Step S341, monitoring the external force and actual speed of the collision joint in real time; when the external force is sensed to act on the collision joint, calculating the joint acceleration generated by the joint according to the dynamic model.

[0140] As mentioned above, sensors are used to monitor the external force and actual speed of the collision joints (such as knee joints, hip joints and elbow joints) of the humanoid robot in real time. By monitoring the external force and speed, it is possible to respond to external impacts in a timely manner and reduce joint damage.

[0141] These parameters can be monitored using force sensors and velocity sensors, or using IMU sensors to estimate velocity and acceleration.

[0142] When external forces act on a joint, the joint acceleration is calculated using a dynamic model.

[0143] For example, taking the x direction of the hip joint as an example, the interaction model between the robot and the external environment can be simplified to a mass-spring-damper model, and its dynamic equation can be expressed as:

[0144]

[0145] Wherein, F represents the fall collision force; M represents the mass parameter of the collision joint; D represents the damping parameter of the collision joint; v real represents the actual speed; x real represents the actual spatial position; represents the rate of change of the joint acceleration of the collision joint; v des represents the expected speed; x des represents the desired spatial position; K represents the critical stiffness parameter of the collision;

[0146] After the humanoid robot falls, it moves following the collision force, so:

[0147] v des =0; stiffness parameter K = 0, therefore, the above formula 1 can be further simplified to obtain the following expression of the dynamic model:

[0148]

[0149] Wherein, F represents the fall collision force; M represents the mass parameter of the collision joint; D represents the damping parameter of the collision joint; v real represents the actual speed; Represents the rate of change of the joint acceleration of the collision joint.

[0150] The above model helps calculate the necessary movement of the joints under the action of external forces, so that the joints can adapt to the external forces and reduce impact damage.

[0151] Step S342, using the joint acceleration to control the collision joint to move in accordance with the external force; and dynamically adjusting the damping parameter and the mass parameter according to the actual speed of the collision joint.

[0152] As described above, the movement of the joint is controlled according to the calculated joint acceleration so that it complies with the external force and achieves a compliant collision. By complying with the external force, the joint can reduce impact and damage and improve the safety and reliability of the robot. Compliant control can be achieved by adjusting the control algorithm of the joint, such as a PID controller.

[0153] Then, according to the actual speed of the joint, the damping parameter D and the mass parameter M are dynamically adjusted to optimize the effect of the smooth collision. Dynamic adjustment of parameters can make the response of the joint more adaptable to the current motion state and improve the protection effect. Specifically, D and M can be adjusted in real time according to the change of actual speed through the feedback control algorithm.

[0154] Embodiment 4:

[0155] Reference Figure 6This embodiment provides a humanoid robot fall control method. Based on the above embodiment 1, the step S300, after controlling the humanoid robot to perform a fall protection action, further includes:

[0156] Step S400, performing fault self-check, posture and position detection, and environmental perception on the humanoid robot, and obtaining self-check results, posture and position information, and environmental perception results respectively.

[0157] It should be noted that the purpose of performing fault self-checking, posture and position detection, and environmental perception after performing fall protection actions is to comprehensively evaluate the status and safety of the robot. Fault self-checking ensures that the robot has no structural damage or functional failure after a fall, and posture and position detection provides the robot's current precise position and posture information, which is essential for planning recovery actions. Environmental perception ensures that the surrounding environment is safe during the robot's recovery process, and there are no obstacles that will hinder the recovery action or cause additional risks to the robot and surrounding personnel. These steps help avoid secondary injuries, increase the success rate of recovery, and enable the robot to adapt to changing environmental conditions. At the same time, the collected data can be used for subsequent analysis to improve the robot's design and fall recovery algorithm, reduce the risk of future falls, enhance the robot's autonomy and intelligence, and ensure compliance with safety standards and regulatory requirements.

[0158] The above steps involve a series of checks and tests on the robot after performing the fall protection action, including fault self-checking, posture and position detection, and environmental perception. Through these tests, the robot's health, current posture, and surrounding environment can be evaluated to provide necessary information for subsequent recovery actions. Fault self-checking can be achieved through the built-in diagnostic system, posture and position detection can be achieved through IMU and other sensors, and environmental perception can be achieved through the visual system and sensors.

[0159] For example, first, the humanoid robot performs a self-check of each part to detect whether it has structural damage, such as joint damage, motor failure, etc. Then use built-in sensors (such as gyroscopes and accelerometers) to detect the robot's posture and position detection, that is, to detect the current posture and position. In addition, use the robot's visual system to perceive the environment and confirm that there are no obstacles around that will hinder the standing process. Use a physical engine or dynamic model to simulate the process of the robot standing up from the current state to evaluate whether it is likely to succeed. Make sure that the machine has the conditions for normal movement before starting the recovery program.

[0160] Step S500, establishing motion planning data according to the self-check result, the posture position information and the environment perception result.

[0161] It should be noted that before adjusting the current posture of the humanoid robot, the motion planning data is first established and simulated to ensure that the planned recovery action is both safe and feasible, while optimizing the recovery path to improve efficiency. This step allows the robot to predict and avoid potential risks before the actual action is performed, verify the adaptability and flexibility of the recovery action, and reduce damage and maintenance costs caused by incorrect operations. In addition, it enhances the robot's autonomous decision-making ability, improves the reliability of performing complex tasks, and helps build user trust in the robot's performance. Through data-driven decision-making, the robot can handle abnormal situations more scientifically and accurately, ensuring safe and effective recovery to a stable state in an uncertain or dynamically changing environment.

[0162] As described above, based on the detection results, motion planning data is established to provide guidance for the robot's recovery action. Motion planning data can help the robot determine how to safely and effectively recover from the current posture to a stable posture. Path planning algorithms, such as the A* algorithm or the RRT algorithm, can be used to generate motion planning data in combination with the robot's dynamic model and environmental information.

[0163] As mentioned above, the A* algorithm (A Star Algorithm) is a heuristic search algorithm for finding the shortest path from a starting point to a target point in a graph. It combines the characteristics of Dijkstra's algorithm (guaranteed to find the shortest path) and greedy best-first search (selecting the most promising node to expand at each step).

[0164] As mentioned above, the RRT algorithm (Rapidly-exploring Random Tree) is a sampling-based tree search algorithm for solving path planning problems in unstructured environments. It is particularly suitable for high-dimensional spaces and complex obstacle environments.

[0165] Both algorithms are suitable for robot path planning, and the choice of which algorithm depends on the specific application scenario and requirements. The A* algorithm is suitable for path planning in grid maps and known environments, while the RRT algorithm is suitable for path planning in continuous space and complex environments.

[0166] Step S600, determining whether the humanoid robot can simulate recovery to a stable posture according to the motion planning data.

[0167] This step involves simulating the possibility of the robot recovering to a stable posture based on the motion planning data. Through simulation, the feasibility of the recovery action can be evaluated without actually performing the action, avoiding possible dangers. The robot's actions can be simulated using a physics engine or dynamic model to predict possible problems during the recovery process.

[0168] Step S700: If yes, adjust the current posture of the humanoid robot according to the motion planning data; and use a segmented motion strategy to adjust the position and angle of the upper body and / or lower body until the stable posture is restored.

[0169] If the simulation results show that the robot can be restored to a stable posture, the robot's posture is adjusted according to the motion planning data. By adjusting the posture, the robot can be restored to a stable state to avoid injuries caused by falling. The posture adjustment can be achieved by adjusting the joint angle and strength through a control algorithm, such as a PID controller.

[0170] And, adopt a segmented motion strategy to adjust the upper body and / or lower body of the robot in stages until it returns to a stable posture. The segmented motion strategy can more finely control the robot's movements and improve the success rate and safety of recovery. A segmented motion control algorithm can be designed to adjust the upper body first, then the lower body, and gradually return to a stable posture.

[0171] For example, if a stable posture can be achieved through motion planning data simulation, the posture adjustment is performed first, that is, according to the current posture, the robot needs to adjust the position of each part of the body to prepare for standing. Then the robot will adopt a segmented motion strategy, first lifting the upper body to a certain angle, and then the lower body. For example, using the weight of the arms and upper body as levers, the body is pushed up through the legs. During the standing process, the robot needs to constantly adjust the center of gravity to maintain dynamic balance.

[0172] Use a PID controller or other control algorithm to fine-tune joint motion to maintain balance.

[0173] Once the robot is close to standing, it needs to fine-tune the joint angles and forces to finally stand. If the standing attempt fails, the robot needs to be able to reassess the state and decide whether to try again or seek other recovery strategies.

[0174] Step S800: If not, it is determined that the movement is blocked, the posture adjustment is stopped, and a warning is generated.

[0175] As mentioned above, if it is determined that the motion is obstructed and cannot be restored to a stable posture according to the motion planning data, the posture adjustment is stopped and a warning is generated. Ineffective or dangerous actions are stopped in time to avoid further damage and to remind the operator or system to take other measures. The motion can be determined by monitoring the robot's motion and sensor feedback, and the motion can be stopped and a warning can be issued if necessary.

[0176] In addition, reference Figure 7 In an embodiment of the present application, a humanoid robot fall control device is also provided, comprising:

[0177] A monitoring module 10 is used to obtain the status data of the humanoid robot in real time; the status data includes the center of gravity position, movement speed and acceleration;

[0178] A prediction module 20, configured to predict a current state of the humanoid robot according to the state data;

[0179] The protection module 30 is used to control the humanoid robot to perform a fall protection action when the current state is a high-risk fall state.

[0180] In addition, in some embodiments, reference Figure 8 In an embodiment of the present application, a humanoid robot fall control device is also provided, comprising:

[0181] Sensor module 40: This module integrates a variety of sensors, including but not limited to gyroscopes, accelerometers, six-dimensional force sensors on the soles of the feet, etc., and is used to collect information such as the posture, speed, and ground contact force of the humanoid robot in real time.

[0182] Data processing module 50: This module processes the data collected by the sensor module in real time, and provides an accurate data basis for the subsequent prediction module through technologies such as signal filtering and feature value extraction.

[0183] Prediction module 60: uses machine learning algorithms and models, combined with the feature values ​​extracted by the data processing module, to evaluate the possibility of the robot falling, and when the risk of falling is predicted, determines the direction of falling and the joints that may touch the ground.

[0184] Control module 70: Based on the evaluation results of the prediction module, the control module adjusts the motion state of the robot in real time to avoid falling or reduce the damage caused by falling.

[0185] refer to Fig. 9 ,Based on the above-mentioned humanoid robot fall control device, the fall control of the humanoid robot can be divided into three stages: body stabilization stage, fall protection stage and fall recovery stage.

[0186] (1) Body stabilization stage: Before a fall occurs, the posture detection system works in conjunction with the balance stability controller to obtain the body posture angle through the IMU and use the six-dimensional force sensor on the sole of the foot to measure the contact force between the robot and the ground. Combining these data, the system calculates the zero moment point (ZMP) and adjusts the position of the robot's waist and hip joints in real time to ensure that the body's center of gravity remains within the support polygon. If external force interference causes the ZMP to exceed the support polygon, the robot will adjust its gait based on the IMU and ZMP data and try to restore balance. When these adjustment strategies cannot restore balance, the system will determine the direction of the fall and activate the fall protection function.

[0187] (2) Fall protection stage: Once a fall occurs, the system will perform the following protection actions:

[0188] Based on the predicted fall direction, determine which joints will contact the ground first and the direction of force applied.

[0189] The knee and hip joints of the legs quickly perform protective movements to lower the center of gravity to reduce the impact force when falling to the ground.

[0190] The joints with the smooth drag function turn on the smooth state before touching the ground, contacting the ground in an elastic manner to reduce damage to the joints.

[0191] Vulnerable joints such as fingers, wrists and head adjust themselves to a safe position to avoid direct impact with the ground.

[0192] For joints and areas prone to collision, a soft control elasticity factor is added, and protective materials are added to the outside to further reduce impact forces.

[0193] (3) Fall recovery phase: After a fall occurs, the robot self-diagnoses the state of the body through IMU data, joint motor position data, and force sensor data, including checking whether there are motor abnormalities and judging the current posture. The robot will classify different fall postures, such as lying flat, lying prone, lying on the side, or other situations. Through motion planning, the robot adjusts to a stable posture or returns to a normal working state to achieve autonomous recovery.

[0194] The present application also provides a computer device. Exemplarily, the computer device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program to enable the computer device to execute the functions of each module in the above-mentioned humanoid robot fall control method or the above-mentioned humanoid robot fall control device.

[0195] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU) and a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0196] The memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0197] The present application also provides a computer storage medium for storing the computer program used in the above-mentioned computer device. The computer storage medium may be a readable storage medium, or a non-volatile storage medium or a volatile storage medium. For example, the computer storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0198] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0199] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0200] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.

[0201] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A humanoid robot fall control method, characterized in that: include: Acquiring status data of the humanoid robot in real time; the status data includes center of gravity position, movement speed and acceleration; predicting a current state of the humanoid robot according to the state data; If the current state is a high-risk fall state, the humanoid robot is controlled to perform a fall protection action.

2. The humanoid robot fall control method according to claim 1, characterized in that: The predicting the current state of the humanoid robot according to the state data comprises: Using a model predictive control algorithm, taking the center of gravity position, the movement speed and the acceleration as input, and using a robot whole body dynamics model to determine whether the humanoid robot reaches a preset trigger condition; If yes, determining that the current state of the humanoid robot is a high-risk falling state; If not, it is determined that the current state of the humanoid robot is not a high-risk falling state.

3. The humanoid robot fall control method as claimed in claim 2, characterized in that: The preset trigger condition includes at least one of the following conditions: A. The center of gravity position exceeds the preset safety range; B. The change in acceleration exceeds a preset acceleration change threshold; C. The decreasing speed of the movement speed exceeds a preset decreasing threshold.

4. The humanoid robot fall control method according to claim 1, characterized in that: The fall protection action includes: Confirming a falling direction and a current robot key protection area corresponding to the falling direction; the current robot key protection area includes legs, vulnerable joints and collision joints; the vulnerable joints include hand joints and head joints; the collision joints include at least one of a knee joint, a hip joint and an elbow joint; Controlling the legs to be in a bent state to lower the center of gravity of the humanoid robot; Controlling the fragile joint to adjust to a safe posture; Controlling the collision joint to enable a smooth collision function; The security posture includes at least one of the following methods: A. Adjust the hand joints to form a fist; B. Adjust the hand joints and bend the elbows to the chest area; C. Adjust the head to tilt toward the chest to form a bowed position.

5. The humanoid robot fall control method according to claim 4, characterized in that: The determining of the falling direction and the current robot key protection area corresponding to the falling direction includes: Using an inertial measurement unit to monitor the attitude angle data of the humanoid robot in real time; the attitude angle data includes the absolute value of the elevation angle and / or the roll angle; If the posture angle reaches 0.5 radians, it is determined that the humanoid robot is currently in an unstable state, and the legs and / or the vulnerable joints are used as key protection areas of the current robot; If the posture angle reaches 1.05 radians, it is determined that the humanoid robot is currently in a tipping state, and the collision joint is used as the key protection area of ​​the current robot.

6. The humanoid robot fall control method according to claim 4, characterized in that: The smooth collision function includes: The external force and actual speed of the collision joint are monitored in real time; when the external force is sensed to act on the collision joint, the joint acceleration generated by the joint is calculated according to the dynamic model; the expression of the dynamic model is: Wherein, F represents the fall collision force; M represents the mass parameter of the collision joint; D represents the damping parameter of the collision joint; v real represents the actual speed; a rate of change of the joint acceleration representing the collision joint; The joint acceleration is used to control the collision joint to comply with the external force movement; and the damping parameter and the mass parameter are dynamically adjusted according to the actual speed of the collision joint.

7. The humanoid robot fall control method according to claim 1, characterized in that: After controlling the humanoid robot to perform the fall protection action, the method further includes: Performing fault self-checking, posture and position detection, and environmental perception on the humanoid robot, and obtaining self-checking results, posture and position information, and environmental perception results respectively; Establishing motion planning data according to the self-check result, the posture position information and the environment perception result; Determining whether the humanoid robot can simulate recovery to a stable posture according to the motion planning data; If yes, adjusting the current posture of the humanoid robot according to the motion planning data; using a segmented motion strategy to adjust the position and angle of the upper body and / or lower body until the stable posture is restored; If not, it is determined that the movement is blocked, the posture adjustment is stopped, and a warning is generated.

8. A humanoid robot fall control device, characterized in that: include: A monitoring module, used to obtain the status data of the humanoid robot in real time; the status data includes the center of gravity position, movement speed and acceleration; A prediction module, used for predicting the current state of the humanoid robot according to the state data; The protection module is used to control the humanoid robot to perform a fall protection action when the current state is a high-risk fall state.

9. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the humanoid robot fall control method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: It stores a computer program, which, when executed on a processor, implements the humanoid robot fall control method according to any one of claims 1-7.

Images