A humanoid robot navigation method, system, storage medium and program product

Abstract

The application discloses a kind of humanoid robot navigation method, system, storage medium and program product, involve navigation field, in the method, for the initial path located in standard lighting area, determine first obstacle coordinate set;According to the first obstacle coordinate set, calculate first correction path;For the initial path located in weak lighting area, determine second correction path according to compensation acceleration;For the initial path located in dark area, calculate third correction path according to second obstacle coordinate set;Control humanoid robot walks according to first correction path, second correction path and third correction path respectively in standard lighting area, weak lighting area and dark area.This application is used to divide different lighting areas and adopt different sensor data and processing method, realizes the stable navigation of humanoid robot in each lighting area, improves path tracking precision, and then improves material handling efficiency.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of navigation, and particularly relates to a humanoid robot navigation method and system, a storage medium and a program product. BACKGROUND

[0002] With the rapid development of robot technology, humanoid robots have been widely used in industrial manufacturing, logistics transportation and life service and many other fields. In the motion control process of the humanoid robot, the navigation function is one of the key technologies to ensure its stable operation. However, due to the high complexity and uncertainty of the motion of the humanoid robot, the traditional navigation method is often difficult to adapt to the complex and changeable environment, especially in a large logistics warehouse workshop, in the process of transporting materials, the humanoid robot is prone to unreasonable path planning, incoherent motion and other problems.

[0003] In the related art, the environment information and the robot pose information can be obtained through a visual sensor, and the acceleration and angular velocity data of the robot are collected in real time by using an inertial measurement unit. These data are fused to establish an environment map and plan a motion path. This method can improve the navigation accuracy and stability of the robot in the warehouse environment.

[0004] However, the lighting conditions between the shelves in the logistics warehouse workshop are often poor, and due to the dense stacking of goods, a large area of shadow area is formed in the local area. The related art mainly relies on real-time processing of visual information when processing sensor data, but in areas with insufficient light, the visual sensor is difficult to accurately identify obstacles and path feature points. When the quality of visual information is poor, the system will rely more on inertial sensor data for navigation, but due to the unevenness of the ground in the warehouse workshop and the frequent change of the center of gravity of the humanoid robot when carrying heavy objects, the measurement error of the inertial sensor increases. These factors reduce the path tracking accuracy when navigating for a long distance in a dark environment, and reduce the material handling efficiency. SUMMARY

[0005] The present application provides a humanoid robot navigation method, system, storage medium and program product for dividing different lighting areas and using different sensor data and processing methods to realize stable navigation of the humanoid robot in each lighting area, improve the path tracking accuracy, and further improve the material handling efficiency.

[0006] In a first aspect, the present application provides a humanoid robot navigation method, which obtains an initial path from a current position of a humanoid robot to a target position and environment light intensity data, and divides the environment into a standard lighting area, a weak lighting area and a dark area according to a preset first light intensity threshold and a preset second light intensity threshold, the preset first light intensity threshold being greater than the preset second light intensity threshold;

[0007] For the initial path located in the standard lighting area, a first obstacle coordinate set corresponding to a first obstacle in a first environment image is identified according to the first environment image collected by the visual sensor;

[0008] A first corrected path of the humanoid robot in the standard lighting area is calculated according to the first obstacle coordinate set and the current position of the humanoid robot in the standard lighting area by using a shortest path algorithm;

[0009] For the initial path located in the weak lighting area, acceleration and angular velocity data measured by an inertial measurement unit and support force data collected by a robot foot force sensor are obtained;

[0010] When it is determined according to the support force data that the center of gravity of the humanoid robot deviates beyond a preset deviation threshold, the acceleration is multiplied by a preset compensation coefficient to obtain compensated acceleration, and a second corrected path of the humanoid robot in the weak lighting area is determined according to the compensated acceleration;

[0011] For the initial path located in the dark area, a second obstacle coordinate set corresponding to a second obstacle in the dark area is identified according to ultrasonic data collected by an ultrasonic sensor;

[0012] A third corrected path of the humanoid robot in the dark area is calculated according to the second obstacle coordinate set and the current position of the humanoid robot in the standard lighting area by using a shortest path algorithm;

[0013] The humanoid robot is controlled to walk according to the first corrected path, the second corrected path and the third corrected path in the standard lighting area, the weak lighting area and the dark area respectively.

[0014] By using the above technical solution, the navigation area is divided into a standard lighting area, a weak lighting area and a dark area according to the ambient light intensity, and different sensors and navigation strategies are used for different areas. In the standard lighting area, the visual sensor is used to identify obstacles and plan a path, which ensures the accuracy of navigation; in the weak lighting area, the inertial measurement unit and the foot force sensor are used to obtain data, and when the center of gravity deviates beyond a threshold, compensation is made to avoid unstable walking due to insufficient light; in the dark area, the ultrasonic sensor is used for obstacle identification and path planning, solving the navigation problem in a completely dark environment. This zoned navigation method enables the humanoid robot to adapt to environments with different light intensities, ensuring navigation accuracy while improving navigation safety, achieving stable navigation of the humanoid robot in each lighting area, improving path tracking accuracy, and thus improving material handling efficiency.

[0015] In combination with some embodiments of the first aspect, in some embodiments, the environment is divided into a standard lighting area, a weak lighting area and a dark area according to a preset first light intensity threshold and a preset second light intensity threshold, specifically including:

[0016] acquire real-time light intensity values of a plurality of preset sampling points in the environment;

[0017] divide a region with a real-time light intensity value greater than a preset first light intensity threshold into a standard lighting area;

[0018] divide a region with a real-time light intensity value not greater than the preset first light intensity threshold and greater than a preset second light intensity threshold into a weak lighting area;

[0019] divide a region with a real-time light intensity value not greater than the preset second light intensity threshold into a dark area.

[0020] By adopting the technical solution, the light intensity values are acquired in real time by setting a plurality of preset sampling points in the environment, and the environment is divided into three regions according to the two preset light intensity thresholds. The setting of the sampling points ensures the comprehensive grasp of the lighting conditions of the entire environment, and the real-time acquisition ensures the dynamicity and accuracy of the environment division. By comparing the real-time light intensity values with the two preset thresholds, a clear region division standard is established. This environment division method based on real-time sampling and explicit thresholds improves the accuracy of environment perception, enabling the humanoid robot to accurately identify the type of the current environment and select an appropriate navigation mode.

[0021] In combination with some embodiments of the first aspect, in some embodiments, when it is determined according to the support force data that the center of gravity of the humanoid robot deviates beyond a preset deviation threshold, the acceleration is multiplied by a preset compensation coefficient to obtain a compensated acceleration, and a second corrected path of the humanoid robot in the weak lighting area is determined according to the compensated acceleration, specifically including:

[0022] calculating a zero moment point coordinate of the humanoid robot according to the support force data;

[0023] calculating a deviation distance between a center of gravity projection point of the humanoid robot and a center of the support polygon based on the zero moment point coordinate;

[0024] when the deviation distance is greater than the preset deviation threshold, determining a dynamic compensation coefficient according to a ratio of the deviation distance to the preset deviation threshold;

[0025] multiplying the acceleration by the dynamic compensation coefficient to obtain a compensated acceleration;

[0026] determining a velocity adjustment amount and a position adjustment amount based on the compensated acceleration through integral operation;

[0027] correcting the initial path located in the weak lighting area based on the velocity adjustment amount and the position adjustment amount to obtain the second corrected path of the humanoid robot in the weak lighting area.

[0028] By adopting the technical scheme, when the offset distance exceeds the preset threshold, the compensation coefficient is dynamically adjusted according to the offset degree, the acceleration is corrected through the coefficient, and then the adjustment amount of the speed and the position is determined through integral operation. This path correction method based on dynamic compensation considers the real-time change of the center of gravity offset in the walking process, and the compensation amount matches the offset degree, avoiding the problems of insufficient compensation or excessive compensation. Through accurate correction of the initial path in the weak lighting area, the walking stability of the humanoid robot in the weak lighting environment is improved, and the risk of falling is reduced.

[0029] In combination with some embodiments of the first aspect, in some embodiments, after controlling the humanoid robot to walk along the first corrected path, the second corrected path and the third corrected path in the standard lighting area, the weak lighting area and the dark area respectively, the method further comprises:

[0030] obtaining first end point coordinates, second start point coordinates, second end point coordinates and third start point coordinates corresponding to the first corrected path, the second corrected path and the third corrected path;

[0031] respectively smoothing the first corrected path and the second corrected path, the second corrected path and the third corrected path according to the first end point coordinates and the second start point coordinates, the second end point coordinates and the third start point coordinates, to obtain a corrected walking path;

[0032] controlling the humanoid robot to walk along the corrected walking path.

[0033] By adopting the technical scheme, the connection point coordinates of the corrected paths of different areas are obtained, the adjacent paths are smoothed, and the discontinuity problem between the paths of different areas is solved. By respectively smoothing and connecting the first corrected path and the second corrected path, and the second corrected path and the third corrected path, the mutation when switching paths is eliminated, and the entire navigation path has continuity. This path smoothing method based on connection point coordinates enables the humanoid robot to smoothly transition when switching between different lighting areas, improving the motion fluency and stability of the humanoid robot in a complex lighting environment.

[0034] In combination with some embodiments of the first aspect, in some embodiments, respectively smoothing the first corrected path and the second corrected path, the second corrected path and the third corrected path according to the first end point coordinates and the second start point coordinates, the second end point coordinates and the third start point coordinates, to obtain a corrected walking path, specifically comprises:

[0035] establishing a first transition area with the first end point coordinates as the center;

[0036] connecting the first corrected path and the second corrected path in the first transition area by using a Bezier curve to obtain a first transition path;

[0037] a second transition region is established with the second stop point coordinate as a center;

[0038] a second transition path is obtained by connecting the second correction path and the third correction path by using a Bezier curve in the second transition region;

[0039] the first transition path, the first correction path, the second correction path, and the second transition path are connected to obtain the corrected walking path.

[0040] By using the above technical solutions, the transition regions are established at the first stop point coordinate and the second stop point coordinate respectively, and the correction paths of different lighting regions are connected by using a Bezier curve in the transition regions, so that the abrupt points between the paths of different lighting regions can be eliminated. The Bezier curve has the characteristics of continuity and smoothness, so that the path remains coherent on the geometric level, and the robot can avoid the dramatic change in motion posture at the junction of different lighting regions. The corrected walking path after smoothing has a continuous change in curvature, so that the robot can maintain a stable motion state during the travel process, reduces the dramatic change in the position of the robot's center of gravity due to the path abruptness, and reduces the energy loss of the robot when transitioning between regions. Smooth path transition can also reduce the instantaneous load of the robot joint drive, prolong the service life of the drive, and improve the navigation reliability of the robot in a complex lighting environment.

[0041] In combination with some embodiments of the first aspect, in some embodiments, after controlling the humanoid robot to walk along the corrected walking path, the method further includes:

[0042] obtaining a speed change rate of the humanoid robot on the corrected walking path;

[0043] when the speed change rate is greater than a preset continuity threshold, performing speed planning on the corrected walking path to generate a speed transition curve;

[0044] controlling the humanoid robot to walk along the corrected walking path according to the speed transition curve.

[0045] By adopting the technical scheme, the rate of change of speed of the robot on the corrected walking path is monitored and compared with the preset continuity threshold, so that the path segment that may cause discontinuous motion of the robot in the path can be identified. For the path segment with the rate of change of speed exceeding the preset continuity threshold, the system generates a speed transition curve through speed planning, so that the motion speed of the robot presents a gradual change characteristic in space. The introduction of the speed transition curve avoids sudden acceleration or deceleration of the robot during motion, reduces the impact load of the joints of the robot, and improves the stability of the robot during motion. Through accurate planning of the speed, the robot can realize smooth transition while ensuring navigation efficiency, reduces energy consumption of the robot during navigation, and improves the safety of the navigation process.

[0046] In combination with some embodiments of the first aspect, in some embodiments, the speed planning is performed on the corrected walking path to generate a speed transition curve, specifically including:

[0047] obtaining start and end positions of a path segment on the corrected walking path with a rate of change of speed exceeding a preset continuity threshold;

[0048] establishing a speed transition interval between the start and end positions of the path segment;

[0049] calculating an expected speed distribution in the speed transition interval;

[0050] performing constraint checking on the expected speed distribution to obtain a constraint checking result;

[0051] modifying the expected speed distribution according to the constraint checking result to obtain the speed transition curve.

[0052] By adopting the technical scheme, the start and end positions of the path segment with the rate of change of speed exceeding the preset continuity threshold are obtained, and a speed transition interval is established in the interval, so that the system can accurately locate the path range that needs to be planned for speed. The expected speed distribution is calculated in the speed transition interval, and constraint checking is performed thereon, so as to ensure that the generated speed transition curve meets the dynamic constraint of the robot. The expected speed distribution is modified according to the constraint checking result, so that a speed transition curve that meets the motion continuity requirement and does not exceed the performance limit of the robot can be obtained. This speed planning method based on constraint conditions enables the robot to realize optimal speed adjustment while ensuring motion stability, and improves the navigation performance of the robot in a complex environment.

[0053] In a second aspect, the embodiments of the present application provide a humanoid robot navigation system, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprising computer instructions, and the one or more processors invoke the computer instructions to cause the system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0054] In a third aspect, the embodiments of the present application provide a computer-readable storage medium, comprising instructions, when the instructions run on a system, cause the system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0055] In a fourth aspect, the embodiments of the present application provide a computer program product, when the computer program product runs on a system, cause the system to perform the method described in any possible implementation manner of the first aspect.

[0056] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0057] 1. The present application provides a humanoid robot navigation method, which divides the navigation area into standard lighting area, weak lighting area and dark area according to the intensity of ambient light, and adopts different sensors and navigation strategies for different areas. In the standard lighting area, visual sensors are used to identify obstacles and plan paths, ensuring the accuracy of navigation; in the weak lighting area, data is obtained through the inertial measurement unit and the plantar force sensor, and compensation is made when the center of gravity deviates beyond the threshold, avoiding unstable walking caused by insufficient light; in the dark area, ultrasonic sensors are used for obstacle identification and path planning, solving the navigation problem in complete darkness. This zoned navigation method enables the humanoid robot to adapt to different light intensity environments, ensuring navigation accuracy while improving navigation safety, achieving stable navigation of the humanoid robot in each lighting area, improving path tracking accuracy, and thus improving material handling efficiency.

[0058] 2. The present application provides a humanoid robot navigation method, which obtains the coordinates of the connection points of the modified paths in different areas, and smoothes the adjacent paths, solving the discontinuity problem between the paths in different areas. By smoothing the connection between the first modified path and the second modified path, and the connection between the second modified path and the third modified path, respectively, the sudden change when switching paths is eliminated, and the entire navigation path has continuity. This path smoothing method based on connection point coordinates enables the humanoid robot to maintain smooth transition when switching between different light areas, improving the motion fluency and stability of the humanoid robot in complex lighting environments.

[0059] 3、The application provides a humanoid robot navigation method. By monitoring the speed change rate of the robot on the corrected walking path and comparing the speed change rate with a preset continuity threshold, a path segment in the path that may cause discontinuous motion of the robot can be identified. For the path segment with a speed change rate exceeding the preset continuity threshold, the system generates a speed transition curve through speed planning, so that the motion speed of the robot presents a gradual change characteristic in space. The introduction of the speed transition curve avoids sudden acceleration or deceleration of the robot during motion, reduces the impact load of the robot joints, and improves the stability of the robot during motion. Through accurate planning of the speed, the robot can realize smooth transition while ensuring navigation efficiency, reduces the energy consumption of the robot during navigation, and improves the safety of the navigation process. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 is a flowchart of a humanoid robot navigation method in an embodiment of the application.

[0061] Figure 2 is another flowchart of a humanoid robot navigation method in an embodiment of the application.

[0062] Figure 3 is a schematic diagram of an entity device structure of a humanoid robot navigation system provided in an embodiment of the application. DETAILED DESCRIPTION

[0063] The terms used in the following embodiments of the application are only for the purpose of describing the specific embodiments and are not intended to be limiting on the application. As used in the specification and the appended claims of the application, the singular forms "a," "an," and "the" are intended to include both singular and plural forms, unless the context clearly indicates otherwise. It will be further understood that the terms "and / or" used in the application means any or all possible combinations of one or more of the listed items.

[0064] Hereinafter, the terms "first" and "second" are only for the purpose of description, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features, and in the description of the embodiments of the application, the meaning of "multiple" is two or more, unless otherwise specified.

[0065] The following uses an embodiment and combines Figure 1 A humanoid robot navigation method in an embodiment of the application is described:

[0066] Please refer to Figure 1A flowchart of a humanoid robot navigation method in an embodiment of the present application.

[0067] S101, obtain an initial path from the current position of the humanoid robot to the target position and environmental light intensity data, and divide the environment into a standard lighting area, a weak lighting area and a dark area according to a preset first light intensity threshold and a preset second light intensity threshold;

[0068] The system obtains an initial path from the current position of the humanoid robot to the target position and environmental light intensity data, and divides the environment into a standard lighting area, a weak lighting area and a dark area according to a preset first light intensity threshold and a preset second light intensity threshold, the preset first light intensity threshold being greater than the preset second light intensity threshold, specifically including: obtaining real-time light intensity values of a plurality of preset sampling points in the environment; dividing the area with a real-time light intensity value greater than the preset first light intensity threshold into a standard lighting area; dividing the area with a real-time light intensity value not greater than the preset first light intensity threshold and greater than the preset second light intensity threshold into a weak lighting area; and dividing the area with a real-time light intensity value not greater than the preset second light intensity threshold into a dark area.

[0069] In this step, the system first obtains an initial path from the current position of the humanoid robot to the target position, which can be obtained by a global path planning algorithm, such as A* algorithm, Dijkstra algorithm, etc. At the same time, the system also obtains light intensity data in the environment, which can be obtained by real-time collection of light intensity sensors. According to the preset first light intensity threshold and the second light intensity threshold, the system divides the environment into three areas of standard lighting area, weak lighting area and dark area, wherein the first light intensity threshold is greater than the second light intensity threshold.

[0070] Specifically, the system can set a plurality of preset sampling points in the environment, and collect real-time light intensity values of each sampling point by light intensity sensors. The area with a real-time light intensity value greater than the first light intensity threshold is divided into a standard lighting area, the area with a real-time light intensity value between the first light intensity threshold and the second light intensity threshold is divided into a weak lighting area, and the area with a real-time light intensity value less than the second light intensity threshold is divided into a dark area. In this way, the environment can be divided according to the environmental lighting conditions.

[0071] It should be noted that steps S102-S103, steps S104-S105 and steps S106-S107 are three branch steps of unrelated time sequence, i.e. the three branch steps have no time sequence, and the specific execution time sequence is not limited.

[0072] S102, for the initial path located in the standard lighting area, identifying a first obstacle coordinate set corresponding to a first obstacle in the first environment image according to a first environment image collected by a vision sensor;

[0073] This step is for the initial path located in the standard lighting area. The system collects the environmental image of the standard lighting area through the visual sensor (such as camera), and analyzes and processes the image to identify the obstacles in the image and obtain the coordinate set of the obstacles. The coordinate set records the position information of the obstacles existing in the standard lighting area.

[0074] In specific implementation, the system can use computer vision algorithms such as target detection and semantic segmentation to process the environmental image and accurately identify the obstacles in the image. Considering the complexity of the actual environment, obstacles may have different sizes, shapes and materials, so the system needs to use robust identification algorithms. In addition, the system can also use depth sensors to collect depth information of the environment, and combine with RGB images for RGB-D target detection to improve the accuracy of obstacle identification.

[0075] S103, according to the first obstacle coordinate set and the current position of the humanoid robot in the standard lighting area, using the shortest path algorithm to calculate the first corrected path of the humanoid robot in the standard lighting area;

[0076] After obtaining the coordinate set of the obstacles in the standard lighting area, the system needs to correct the initial path located in the standard lighting area according to the position information of these obstacles to obtain the walking path of the humanoid robot in the standard lighting area, i.e. the first corrected path. The corrected path needs to avoid all obstacles and shorten the path length as much as possible.

[0077] In order to calculate the first corrected path, the system can use the shortest path algorithm, such as A* algorithm, Dijkstra algorithm, etc. The current position of the humanoid robot in the standard lighting area is taken as the starting point, the target position is taken as the end point, and the coordinate set of the obstacles is taken as the constraint condition. The shortest path algorithm is used to search a collision-free path from the starting point to the end point as the walking path of the humanoid robot in the standard lighting area.

[0078] S104, for the initial path located in the weak lighting area, obtaining the acceleration and angular velocity data measured by the inertial measurement unit and the support force data collected by the robot foot force sensor;

[0079] This step is for the initial path located in the weak lighting area. Due to the poor lighting conditions in the weak lighting area, it is difficult for the visual sensor to accurately perceive the environmental information. Therefore, the system obtains the acceleration and angular velocity data of the humanoid robot through the inertial measurement unit (IMU), and obtains the support force data through the force sensor of the robot foot, which is used for subsequent path correction.

[0080] Specifically, the IMU can measure the acceleration and angular velocity changes of the humanoid robot during movement, reflecting the motion state of the robot. The plantar force sensor can measure the support force size and distribution on the robot foot, reflecting the contact state of the robot with the ground. The system can fuse the IMU data and force sensor data to estimate the position and attitude changes of the humanoid robot in the weak lighting area.

[0081] S105, when the center of gravity of the humanoid robot is determined to deviate from the preset deviation threshold according to the support force data, the acceleration is multiplied by a preset compensation coefficient to obtain a compensation acceleration, and the second corrected path of the humanoid robot in the weak lighting area is determined according to the compensation acceleration;

[0082] When the system determines that the center of gravity of the humanoid robot deviates from the preset deviation threshold according to the support force data, the acceleration is multiplied by a preset compensation coefficient to obtain a compensation acceleration, and the second corrected path of the humanoid robot in the weak lighting area is determined according to the compensation acceleration, specifically including: calculating the zero moment point coordinates of the humanoid robot according to the support force data; calculating the offset distance between the center of gravity projection point of the humanoid robot and the center of the support polygon based on the zero moment point coordinates; when the offset distance is greater than the preset offset threshold, the dynamic compensation coefficient is determined according to the ratio of the offset distance to the preset offset threshold; the acceleration is multiplied by the dynamic compensation coefficient to obtain the compensation acceleration; the velocity adjustment amount and the position adjustment amount are determined by integral operation based on the compensation acceleration; the initial path located in the weak lighting area is corrected based on the velocity adjustment amount and the position adjustment amount to obtain the second corrected path of the humanoid robot in the weak lighting area.

[0083] After obtaining the IMU data and force sensor data, the system needs to correct the initial path located in the weak lighting area according to these data to obtain the second corrected path of the humanoid robot in the weak lighting area.

[0084] Specifically, the system first calculates the zero moment point (ZMP) coordinates of the humanoid robot according to the support force data collected by the plantar force sensor. ZMP is the point of force balance of the robot, reflecting the center of gravity of the robot. Then, the system calculates the offset distance between ZMP and the center of the robot support polygon. When the offset distance exceeds the preset offset threshold, it means that the center of gravity of the robot deviates greatly, and there is a risk of falling. The offset distance calculation process is as follows: let the vertical component of the force measured by the robot plantar force sensor be F1, F2, …, Fn (n is the number of supporting feet), and the ZMP (Zero Moment Point) coordinates of the robot are calculated according to the zero moment equation:

[0085] ; Where (xi, yi) is the coordinates of the i th supporting foot.

[0086] ​​Calculate the offset distance d of the ZMP from the center of the robot support polygon: ; wherein is the coordinate of the center of the support polygon.

[0087] To maintain the balance of the robot, the system can compensate the acceleration measured by the IMU. Specifically, the system calculates a dynamic compensation factor according to the ratio of the offset distance and the offset threshold. Multiply the original acceleration by the compensation factor to obtain the compensated acceleration. The compensated acceleration reflects the motion adjustment that the robot needs to make to maintain balance. The specific calculation function of the dynamic compensation factor k is: ;

[0088] Finally, the system uses the compensated acceleration to obtain the speed adjustment and position adjustment of the robot through integration operation. Apply these adjustments to the initial path to correct the initial path to obtain the second corrected path of the humanoid robot in the weak lighting area. The corrected path can help the robot maintain balance and avoid falling in the weak lighting area. Specifically, let the real-time acceleration measured by the IMU be a, calculate the compensated acceleration ac: ac = k · a, through twice integration, calculate the speed adjustment Δv and position adjustment Δp generated by the compensated acceleration ac: ; ; Let the original discrete path points of the second corrected path of the robot walking in the weak lighting area be (x1, y1), (x2, y2), …, (xm, ym), modify the coordinates of each path point according to Δp: xi' = xi + Δp·cosθ; yi' = yi + Δp·sinθ.

[0089] Where θ is the tangent direction angle of Δp at the path point. All the modified path points (x1', y1'), (x2', y2'), …, (xm', ym') constitute the second corrected path of the humanoid robot in the weak lighting area.

[0090] S106, for the initial path located in the dark area, according to the ultrasonic data collected by the ultrasonic sensor, identify the second obstacle coordinate set corresponding to the second obstacle in the dark area;

[0091] This step processes the initial path located in the dark area. In the dark area with extremely poor lighting conditions, both the vision sensor and the IMU are difficult to accurately perceive environmental information. Therefore, the system collects ultrasonic data through the ultrasonic sensor to identify obstacles in the dark area.

[0092] Specifically, the ultrasonic sensor can emit ultrasonic waves and receive the reflected ultrasonic waves, and calculate the distance between the obstacle and the sensor by measuring the time of flight of the ultrasonic waves. The system can collect distance data in different directions using multiple ultrasonic sensors to scan the dark area environment. According to the ultrasonic data, the system can identify the position coordinates of the obstacles in the dark area to obtain a second obstacle coordinate set.

[0093] During the processing of ultrasonic data, there may be ranging errors, multiple reflections, and other problems that affect the accuracy of obstacle identification. In order to improve the identification accuracy, the system can use median filtering, Kalman filtering, and other algorithms to filter the ultrasonic data and remove abnormal data points. In addition, the system can also analyze the time sequence of multiple frames of data to determine the motion state of the obstacle and distinguish between static obstacles and dynamic obstacles.

[0094] S107, calculating a third corrected path of the humanoid robot in the dark area according to the second obstacle coordinate set and the current position of the humanoid robot in the standard lighting area using a shortest path algorithm;

[0095] After obtaining the coordinate set of the obstacles in the dark area, the system needs to correct the initial path located in the dark area according to the position information of these obstacles to obtain the walking path of the humanoid robot in the dark area, i.e. the third corrected path. The corrected path needs to avoid all obstacles and consider the position of the humanoid robot when entering the dark area from the standard lighting area.

[0096] Similar to the standard lighting area, the system can use a shortest path algorithm, such as A* algorithm, Dijkstra algorithm, etc., to calculate the third corrected path. The current position of the humanoid robot in the standard lighting area is taken as the starting point, the target position is taken as the end point, and the second obstacle coordinate set is taken as the constraint condition to search for a collision-free path as the walking path of the humanoid robot in the dark area.

[0097] S108, controlling the humanoid robot to walk according to the first corrected path, the second corrected path, and the third corrected path in the standard lighting area, the weak lighting area, and the dark area respectively.

[0098] This step is the last step of the navigation method, which sends the three corrected paths obtained in the previous steps to the robot to control the robot to walk according to the corresponding corrected paths in the standard lighting area, the weak lighting area, and the dark area, respectively, to complete the navigation task.

[0099] Specifically, the system converts the first, second and third corrected paths into control instructions and issues them to the motion control module of the humanoid robot. The motion control module controls the joint motors, balance system, etc. of the robot according to the received path instructions to realize the movement of the robot in different areas. During the movement of the robot, the state and environmental information of the robot need to be monitored in real time to ensure the stability and safety of the movement.

[0100] In actual navigation, the robot may encounter unexpected situations, such as sudden appearance of obstacles, changes in road conditions, etc. In order to deal with these unexpected situations, the system can use a real-time obstacle avoidance algorithm to dynamically adjust the movement trajectory of the robot according to the environmental information fed back by the sensors. For example, when an obstacle is detected in front of the robot, the system can control the robot to slow down and plan an obstacle avoidance path to ensure the safety of the robot.

[0101] In the above embodiment, the navigation area is divided into standard lighting area, weak lighting area and dark area according to the intensity of the ambient light, and different sensors and navigation strategies are used for different areas. In the standard lighting area, visual sensors are used to identify obstacles and plan paths, ensuring the accuracy of navigation; in the weak lighting area, data is obtained through inertial measurement units and foot force sensors, and compensation is made when the center of gravity deviates beyond the threshold, avoiding unstable walking due to insufficient light; in the dark area, ultrasonic sensors are used for obstacle identification and path planning, solving the problem of navigation in complete darkness. This zoned navigation method enables the humanoid robot to adapt to different light intensity environments, ensuring navigation accuracy while improving navigation safety, achieving stable navigation of the humanoid robot in each lighting area, improving path tracking accuracy, and thus improving material handling efficiency.

[0102] After completing the path planning in different lighting areas, in order to enable the humanoid robot to complete the entire navigation process more smoothly, the problem of path connection between different lighting areas also needs to be solved. Since different sensors and navigation strategies are used in different lighting areas, there may be a discontinuity in the path at the boundary of the areas, which will cause the robot to have a sharp movement change when switching between areas. The following describes another embodiment of the humanoid robot navigation method in the present application in combination with Figure 2 Another embodiment of the humanoid robot navigation method in the present application is described as follows:

[0103] Please refer to Figure 2 Another flowchart of the humanoid robot navigation method in the present application is shown in FIG. 6.

[0104] S201, obtaining first, second and third corrected paths corresponding to first end point coordinates, second start point coordinates, second end point coordinates and third start point coordinates;

[0105] In this step, the system first obtains the key coordinate points of the first, second and third modified paths. These coordinate points include the end point coordinate of the first modified path (first end point coordinate), the start point coordinate and end point coordinate of the second modified path (second start point coordinate and second end point coordinate), and the start point coordinate of the third modified path (third start point coordinate). These coordinate points are obtained in order to connect the paths smoothly in the subsequent steps. It should be noted that the way to obtain these modified paths can be various, such as collecting images through a visual sensor and planning a path, scanning and mapping through a laser radar, etc. This step does not limit how to obtain these modified paths.

[0106] The system can obtain these key coordinate points in various ways. One possible implementation is to directly extract the start and end point coordinates of each path after obtaining the first, second and third modified paths. Another way is to record these key point coordinates simultaneously when generating each modified path, and then read them out. In addition, the system can also obtain more path points on each modified path through interpolation and other mathematical algorithms, so as to obtain a more detailed path description.

[0107] S202, establishing a first transition area centered on the first end point coordinate;

[0108] After obtaining the end point coordinate of the first modified path (first end point coordinate), the system establishes a transition area centered on this coordinate, which is named the first transition area. The function of this area is to provide a smooth transition space between the first modified path and the second modified path, avoiding discontinuous motion such as sharp turns when the robot switches paths. The specific size and shape of the first transition area can be set according to actual needs, and this step does not limit it.

[0109] The system can establish the first transition area in various ways. One simple implementation is to set a fixed radius with the first end point coordinate as the center to establish a circular transition area. The radius of the circle can be adjusted according to the motion characteristics of the robot and environmental conditions, etc. Another more flexible way is to dynamically generate an irregular polygon area according to the trend of the first modified path and the second modified path near the first end point. The boundary of the area should be tangent to the trend of the two paths to achieve a more natural transition effect.

[0110] S203, connecting the first modified path and the second modified path in the first transition area by using a Bezier curve to obtain a first transition path;

[0111] After the first transition region is established, the system needs to connect the end point of the first correction path and the start point of the second correction path in the region. In this step, the system selects to use the Bezier curve as the generation method of the transition path. The Bezier curve is a parametric curve, and by setting the control points, a smooth and continuous curvature curve can be generated. Using this characteristic of the Bezier curve, the system can generate a natural and smooth transition path in the first transition region to connect the two correction paths and obtain the first transition path.

[0112] The specific steps of the system generating the Bezier curve as the first transition path are as follows: first, the end point of the first correction path and the start point of the second correction path are taken as the start point and the end point of the Bezier curve; then, according to the trend of the two paths in the transition region, appropriate control points are selected, and the boundary points of the transition region can usually be selected as the control points; finally, the coordinates of the sampling points on the first transition path are calculated by using the mathematical expression of the Bezier curve, so that the complete transition path is obtained. In order to make the transition path more smooth and natural, the system can appropriately increase the order of the Bezier curve, but too high order will also increase the calculation amount.

[0113] S204, a second transition region is established with the second end point coordinates as the center;

[0114] Similar to step S202, the system establishes a second transition region with the end point coordinates of the second correction path (second end point coordinates) as the center. The role of this region is to provide a smooth transition space between the second correction path and the third correction path. The size and shape of the second transition region are the same as those of the first transition region, and can be flexibly set according to actual needs.

[0115] When establishing the second transition region, the system can use the same method as the first transition region, such as establishing a circular region with the second end point coordinates as the center, or establishing an irregular polygon region according to the trend of the second correction path and the third correction path. At the same time, if the distance between the end point of the second correction path and the start point of the third correction path is too large and exceeds the preset threshold, the system can also use the method of inserting intermediate points between the two points to establish multiple small transition regions instead of one large region, in order to improve the flexibility and success rate of subsequent path connection.

[0116] S205, connecting the second correction path and the third correction path in the second transition region by using the Bezier curve to obtain the second transition path;

[0117] This step is similar to step S203, except that the system is in the second transition region, and the end point of the second modified path and the start point of the third modified path are smoothly connected to obtain the second transition path. Similarly, the system uses the Bezier curve as the generation method of the transition path, and generates a smooth and natural transition path by selecting appropriate control points.

[0118] The specific steps of generating the second transition path are similar to generating the first transition path: taking the end point of the second modified path and the start point of the third modified path as the start point and end point of the Bezier curve, selecting appropriate control points (such as the boundary points of the transition region), and then using the mathematical expression of the Bezier curve to generate the sample point coordinates on the transition path.

[0119] Similarly, if the angle between the second modified path and the third modified path is large, resulting in a transition path with a too small curvature radius, which is difficult for the robot to pass through, the system can use the segmented Bezier curve method to solve it. The transition path is divided into multiple segments, each segment is fitted with a Bezier curve, and the adjacent two curves satisfy the position and tangent line continuity conditions at the boundary points. In this way, a transition path with a larger curvature radius can be generated, which is more consistent with the kinematic characteristics of the robot.

[0120] S206, connecting the first transition path with the first modified path and the second modified path, and connecting the second transition path with the second modified path and the third modified path to obtain a modified walking path;

[0121] After generating the first transition path and the second transition path, the system needs to splice them with the original modified path to obtain a complete and continuous walking path, that is, the modified walking path. Specifically, the system connects the first transition path with the first modified path and the second modified path, and connects the second transition path with the second modified path and the third modified path. The connection method can be simply connecting the paths end to end, or performing certain smoothing processing at the connection point to make the entire modified walking path meet the continuity conditions in terms of position, speed, etc.

[0122] In actual path splicing, the system can use the following steps: first, arrange the first modified path, the first transition path, the second modified path, the second transition path and the third modified path in order; then, check the connection points of the adjacent two paths to ensure that they are coincident in position, if there is deviation, then perform appropriate adjustment such as translation, rotation, etc.; next, calculate the kinematic parameters such as velocity and acceleration at the connection point to ensure that the motion of the robot is smooth and continuous when switching paths; finally, splice all the adjusted paths in order to form the final modified walking path.

[0123] S207. Control the humanoid robot to walk according to the corrected walking path.

[0124] After obtaining the corrected walking path, the system can control the humanoid robot according to the path, making it move along the planned trajectory. Specifically, the system can divide the corrected walking path into a series of discrete path points, each containing position coordinates and attitude information. Then, the system can generate corresponding motion control instructions, such as joint angle, motion speed, etc., according to these path points, and send them to the motion control module of the humanoid robot. After receiving the instructions, the motion control module can drive the joints of the robot to perform corresponding movements, so that the overall movement trajectory of the robot matches the corrected walking path. During the control process, the system can also obtain real-time position and attitude feedback of the robot through sensors, and dynamically adjust the motion control instructions according to the feedback information to compensate for errors in the path tracking process.

[0125] In implementing the above control function, the system can use various control algorithms and strategies. For example, the system can use a position-based PID control algorithm to calculate the target angle of the robot joints according to the position coordinates of the path points, and use a PID controller to drive the joints to the target angle.

[0126] In the above embodiment, by obtaining the connection point coordinates of the corrected paths in different regions, the adjacent paths are smoothed, solving the discontinuity problem between different region paths. By smoothly connecting the first corrected path and the second corrected path, and the second corrected path and the third corrected path, respectively, the mutation when switching paths is eliminated, making the entire navigation path continuous. This path smoothing method based on connection point coordinates allows the humanoid robot to smoothly transition between different lighting regions, improving the motion fluency and stability of the humanoid robot in complex lighting environments.

[0127] Further, in another embodiment, after controlling the humanoid robot to walk according to the corrected walking path, it further comprises: obtaining the speed change rate of the humanoid robot on the corrected walking path;

[0128] When the speed change rate is greater than the preset continuity threshold, the speed of the corrected walking path is planned, and a speed transition curve is generated, specifically including: obtaining the start and end positions of the path segment on the corrected walking path where the speed change rate exceeds the preset continuity threshold; establishing a speed transition interval between the start and end positions of the path segment; calculating the expected speed distribution in the speed transition interval; performing constraint test on the expected speed distribution to obtain the constraint test result; modifying the expected speed distribution according to the constraint test result to obtain the speed transition curve;

[0129] Control the humanoid robot to walk according to the speed transition curve on the corrected walking path.

[0130] On the basis of the above-mentioned embodiments, the system can further optimize the motion control of the humanoid robot, improve the motion continuity and stability of the humanoid robot on the corrected walking path. Specifically, the system can monitor the speed change of the humanoid robot on the corrected walking path in real time, and judge whether the motion has mutation or discontinuity by calculating the speed change rate. When it is detected that the speed change rate exceeds the preset continuity threshold, it means that the motion of the robot has a large speed mutation, which may cause problems such as motion instability and mechanical vibration.

[0131] To solve this problem, the system can plan the speed of the corrected walking path and generate a speed transition curve to smooth the speed change of the robot. In specific implementation, the system can first obtain the start and end positions of the path segment on the corrected walking path where the speed change rate exceeds the preset continuity threshold, and determine the interval range that needs to be speed transitioned. Then, the system can establish a speed transition interval between the start and end positions of the path segment, and calculate the expected speed distribution according to the path characteristics and the dynamics constraints of the robot in the interval. The expected speed distribution here can be a continuous and smooth curve, representing the speed change law of the robot in the speed transition interval.

[0132] After obtaining the expected speed distribution, the system also needs to perform constraint checking to ensure that the generated speed transition curve meets the kinematics and dynamics constraints of the robot, such as maximum speed, acceleration, etc. The system can compare the expected speed distribution with the constraints of the robot, and make necessary corrections and adjustments to the expected speed distribution according to the results of the constraint checking, to finally obtain a speed transition curve that meets the constraints.

[0133] After generating the speed transition curve, the system can use it as a reference input for the motion control of the humanoid robot, and control the robot to walk on the corrected walking path according to the curve. In specific implementation, the system can discretize the speed transition curve into a series of speed control points, and generate corresponding joint motion instructions according to these control points. By introducing the speed transition curve, the speed change of the robot on the walking path can be effectively smoothed, the influence of speed mutation on motion stability can be reduced, and the continuity and stability of the humanoid robot navigation can be improved.

[0134] In the above embodiment, by monitoring the rate of change of the speed of the robot on the corrected walking path and comparing it with the preset continuity threshold, the path segment in the path that may cause discontinuous motion of the robot can be identified. For the path segment whose rate of change of speed exceeds the preset continuity threshold, the system generates a speed transition curve through speed planning, so that the motion speed of the robot presents a gradual change characteristic in space. The introduction of the speed transition curve avoids sudden acceleration or deceleration of the robot during motion, reduces the impact load of the joints of the robot, and improves the stability of the robot during motion. Through accurate planning of the speed, the robot can realize smooth transition while ensuring the navigation efficiency, reduces the energy consumption of the robot during navigation, and improves the safety of the navigation process.

[0135] The system in the embodiment of the present application will be described from the perspective of hardware processing. Please refer to Figure 3 FIG. 1 is a schematic structural diagram of an entity device of a humanoid robot navigation system provided by the embodiment of the present application.

[0136] It should be noted that Figure 3 The structure of the system shown is only an example, and should not bring any limitation to the function and use range of the embodiment of the present application.

[0137] As Figure 3 shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 302 or programs loaded from a storage portion 308 to a random access memory (RAM) 303, such as performing the method in the above embodiment. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0138] The following components are connected to the I / O interface 305: an input section 306 including a camera, a microphone, and the like; an output section 307 including a liquid crystal display (LCD), a speaker, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication section 309 performs a communication process via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as necessary. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 310 as necessary, so that a computer program read out therefrom is installed in the storage section 308 as necessary.

[0139] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing a computer program for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present application are executed.

[0140] It should be noted that the computer-readable medium in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable computer programs. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above.

[0141] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Each block in the flowcharts or block diagrams can represent a module, a program segment, or a part of code containing one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than that shown in the drawings. For example, two blocks that are shown in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0142] As another aspect, the present application also provides a computer readable storage medium, which can be included in the system described in the above embodiments, or can exist independently without being assembled into the system. The above storage medium carries one or more computer programs, which, when executed by a processor of a system, enable the system to implement the method provided in the above embodiments.

[0143] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still make modifications to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0144] In the above embodiments, according to the context, the term "when" can be interpreted as "if" or "after" or "in response to determining" or "in response to detecting". Similarly, according to the context, the phrase "upon determining" or "if detecting (the stated condition or event)" can be interpreted as "if determining" or "in response to determining" or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)".

[0145] In the above embodiments, all or some of the steps can be implemented by using software, hardware, firmware or any combination thereof. When implemented by using software, all or some of the steps can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded into and executed by a computer, all or some of the steps as described in the embodiments of the present application are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatuses. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, solid state disk), etc.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned method embodiments can be implemented by a computer program instructing relevant hardware to complete, the program can be stored in a computer readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The aforementioned storage medium includes ROM or random storage memory RAM, magnetic disc or optical disc and various storage code medium.

Claims

1. A navigation method for a humanoid robot, characterized in that, include: The initial path from the current position of the humanoid robot to the target position and the ambient light intensity data are obtained, and the environment is divided into a standard lighting area, a weak lighting area and a dark area according to a preset first light intensity threshold and a preset second light intensity threshold, wherein the preset first light intensity threshold is greater than the preset second light intensity threshold. For the initial path located in the standard lighting area, the first obstacle coordinate set corresponding to the first obstacle in the first environment image is identified based on the first environment image acquired by the visual sensor; Based on the first set of obstacle coordinates and the current position of the humanoid robot in the standard lighting area, the shortest path algorithm is used to calculate the first corrected path of the humanoid robot in the standard lighting area; For the initial path located in the dimly lit area, acquire the acceleration and angular velocity data measured by the inertial measurement unit and the support force data collected by the robot's foot force sensor; When it is determined from the support force data that the center of gravity of the humanoid robot deviates beyond a preset offset threshold, the acceleration is multiplied by a preset compensation coefficient to obtain a compensation acceleration, and the second correction path of the humanoid robot in the dim lighting area is determined based on the compensation acceleration. For the initial path located in the dark area, the coordinate set of the second obstacle corresponding to the second obstacle in the dark area is identified based on the ultrasonic data collected by the ultrasonic sensor; Based on the second set of obstacle coordinates and the current position of the humanoid robot in the standard lighting area, the shortest path algorithm is used to calculate the third corrected path of the humanoid robot in the dark area; The humanoid robot is controlled to walk in the standard lighting area, the dim lighting area, and the dark area according to the first correction path, the second correction path, and the third correction path, respectively.

2. The method according to claim 1, characterized in that, The process of dividing the environment into a standard lighting area, a low lighting area, and a dark area based on a preset first light intensity threshold and a preset second light intensity threshold specifically includes: Acquire real-time light intensity values ​​at multiple preset sampling points in the environment; The area where the real-time light intensity value is greater than a preset first light intensity threshold is divided into a standard lighting area; The area where the real-time light intensity value is not greater than the preset first light intensity threshold but is greater than the preset second light intensity threshold is divided into a weak lighting area. The area where the real-time light intensity value is not greater than the preset second light intensity threshold is divided into dark areas.

3. The method according to claim 1, characterized in that, When the center of gravity shift of the humanoid robot exceeds a preset shift threshold based on the support force data, the acceleration is multiplied by a preset compensation coefficient to obtain a compensation acceleration, and a second correction path for the humanoid robot in the dimly lit area is determined based on the compensation acceleration. Specifically, this includes: The coordinates of the zero-moment point of the humanoid robot are calculated based on the supporting force data; The offset distance between the center of gravity projection point of the humanoid robot and the center of the supporting polygon is calculated based on the coordinates of the zero torque point. When the offset distance is greater than a preset offset threshold, a dynamic compensation coefficient is determined based on the ratio of the offset distance to the preset offset threshold. Multiply the acceleration by the dynamic compensation coefficient to obtain the compensated acceleration; Based on the compensated acceleration, the velocity adjustment amount and the position adjustment amount are determined by integral calculation; Based on the speed adjustment and the position adjustment, the initial path located in the dimly lit area is corrected to obtain the second corrected path of the humanoid robot in the dimly lit area.

4. The method according to claim 1, characterized in that, After the humanoid robot is controlled to walk in the standard lighting area, the dim lighting area, and the dark area according to the first correction path, the second correction path, and the third correction path, respectively, the method further includes: Obtain the coordinates of the first endpoint, the second starting point, the second endpoint, and the third starting point corresponding to the first corrected path, the second corrected path, and the third corrected path; The first corrected path and the second corrected path, and the second corrected path and the third corrected path are smoothed according to the first end point coordinates and the second start point coordinates, and the second end point coordinates and the third start point coordinates, respectively, to obtain the corrected walking path; Control the humanoid robot to walk according to the corrected walking path.

5. The method according to claim 4, characterized in that, The process of smoothing the first corrected path and the second corrected path, and the second corrected path and the third corrected path, respectively, based on the coordinates of the first endpoint and the second starting point, and the coordinates of the second endpoint and the third starting point, to obtain the corrected walking path, specifically includes: Establish a first transition region centered on the first endpoint coordinates; Within the first transition region, a Bézier curve is used to connect the first correction path and the second correction path to obtain the first transition path; A second transition region is established with the second endpoint coordinates as the center; Within the second transition region, the Bézier curve is used to connect the second correction path and the third correction path to obtain the second transition path; Connect the first transition path with the first correction path and the second correction path, and connect the second transition path with the second correction path and the third correction path to obtain the corrected walking path.

6. The method according to claim 4, characterized in that, After controlling the humanoid robot to walk according to the corrected walking path, the method further includes: Obtain the rate of change of the humanoid robot's velocity along the corrected walking path; When the rate of change of speed is greater than a preset continuity threshold, speed planning is performed on the corrected walking path to generate a speed transition curve; The humanoid robot is controlled to walk on the corrected walking path according to the speed transition curve.

7. The method according to claim 6, characterized in that, The step of speed planning for the corrected walking path and generating a speed transition curve specifically includes: Obtain the start and end positions of the path segments on the corrected walking path where the rate of change of speed exceeds the preset continuity threshold; Establish a speed transition interval between the start and end positions of the path segment; Calculate the desired velocity distribution within the velocity transition interval; The desired velocity distribution is subjected to a constraint test, and the constraint test results are obtained. The desired velocity distribution is corrected based on the results of the constraint test to obtain the velocity transition curve.

8. A humanoid robot navigation system, characterized in that, The system includes: One or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the system to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on the system, the system performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the system, the system performs the method as described in any one of claims 1-7.

Images