Robot pile alignment method, robot and storage medium

Abstract

The invention discloses a robot pile alignment method, a robot and a storage medium, and relates to the technical field of robot control, the robot pile alignment method is applied to a robot control system, the robot is provided with at least one signal receiving device, and the method comprises the steps that charging pile detection is carried out based on a first observation angle of the signal receiving device; after the charging pile is detected, determining an updating probability according to the position of the signal receiving device and a second position in the initial probability distribution of the charging pile; updating the initial probability distribution of the charging pile position according to the updating probability to obtain target probability distribution of the charging pile position; and determining the maximum probability in the target probability distribution, and determining the charging pile position corresponding to the maximum probability as the target position of the charging pile. The probability of the possible position of the charging pile is updated according to the detected signal, and the accuracy of position estimation of the charging pile is improved.

Description

Technical Field

[0001] The present application relates to the field of robot control technology, and in particular to a robot pile alignment method, a robot and a storage medium. Background Art

[0002] When the robot needs to charge, it needs to determine the location of the charging pile. Usually, the charging pile is equipped with an infrared signal transmitter that continuously or periodically sends out infrared signals. The robot is equipped with an infrared signal receiver that can receive infrared signals from the charging pile. The robot adjusts its position and posture based on the information provided by the infrared signal to ensure the docking accuracy with the charging pile. However, the infrared signal only provides discrete signals such as the area where the robot is located, rather than continuous and precise coordinates and other determined position observation data, making it difficult to stably and accurately locate the charging pile.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a robot charging pile method, a robot and a storage medium, aiming to solve the technical problem of how to improve the accuracy of charging pile position estimation.

[0005] To achieve the above purpose, the present application proposes a robot pile alignment method, which includes:

[0006] Performing charging pile detection based on the first observation angle of the signal receiving device;

[0007] After detecting the charging pile, determining an update probability according to the position of the signal receiving device and the second position in the initial probability distribution of the charging pile;

[0008] The initial probability distribution of the charging pile position is updated according to the updated probability to obtain the target probability distribution of the charging pile position;

[0009] The maximum probability in the target probability distribution is determined, and the charging pile position corresponding to the maximum probability is determined as the target position of the charging pile.

[0010] In one embodiment, before the step of detecting the charging pile based on the first observation angle, the method includes:

[0011] Acquire first position information of the charging pile, and determine a discretization range according to the first position information;

[0012] Discretize the coordinates within the discretization range to obtain discretized coordinate points;

[0013] The discretized coordinate points are input into a preset probability distribution model to obtain the initial probability distribution.

[0014] In one embodiment, after detecting the charging pile, the step of determining the update probability according to the position of the signal receiving device and the second position in the initial probability distribution of the charging pile includes:

[0015] After detecting the signal sent by the charging pile, traversing the second position;

[0016] Acquire a position vector between the second position and the position of the signal receiving device, and an angle between the position vector and the axis vector of the signal receiving device;

[0017] The update probability is determined according to the angle.

[0018] In one embodiment, the step of determining the update probability according to the angle comprises:

[0019] Determining whether the second position is within the field of view angle of the signal receiving device according to the included angle;

[0020] If it is within the field of view angle range, determining the update probability according to the distance deviation between the second position and the signal receiving device, and the angle;

[0021] If it is not within the field of view angle range, the update probability is zero.

[0022] In one embodiment, the step of updating the initial probability distribution of the charging pile position according to the updated probability to obtain the target probability distribution of the charging pile position includes:

[0023] determining an amount of confidence decay;

[0024] The initial probability distribution is updated according to the confidence attenuation and the update probability to obtain the target probability distribution.

[0025] In one embodiment, after the step of determining the maximum probability in the target probability distribution and determining the charging pile position corresponding to the maximum probability as the target position of the charging pile, the following steps are included:

[0026] Determining whether the robot needs to spin according to the robot orientation and the target position orientation;

[0027] If necessary, obtaining and adjusting the orientation of the robot according to the spin angle, and controlling the robot to move to the target position in an arc;

[0028] If not necessary, the spinning step is skipped and the robot is controlled to travel to the target position in an arc.

[0029] In one embodiment, the step of determining whether the robot needs to spin according to the robot orientation and the target position orientation includes:

[0030] Obtaining an angle difference between the orientation of the target position and the direction in which the robot points to the target position, to obtain the target orientation of the robot;

[0031] If the target orientation is greater than a preset threshold, it is determined that the robot needs to be controlled to spin.

[0032] In one embodiment, after the step of performing charging pile detection based on the first observation angle of the signal receiving device, the step further includes:

[0033] When the charging pile is not detected at the first observation angle, adjusting the first observation angle;

[0034] Perform charging pile detection based on the adjusted first observation angle;

[0035] If the charging pile is still not detected, the steps of angle adjustment and charging pile detection are repeated until a preset detection time threshold is reached.

[0036] In addition, to achieve the above objectives, the present application also proposes a robot, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the robot pile-pile method as described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the robot pile-pile method described above are implemented.

[0038] The present application provides a robot charging pile method, which sets an observation angle and uses a signal receiving device on the robot to search for signals emitted by charging piles within a specific range. When the charging pile signal is detected, the initial probability of the possible position of the charging pile is updated according to the robot's own position, and the probability of each possible position is dynamically adjusted. After the probability update is completed, the position corresponding to the maximum probability is found as the target position of the charging pile.

[0039] In this application, by setting the observation angle, targeted detection is performed within an angle range that may contain the charging pile, avoiding directionless blind search and providing area information where the charging pile may exist for the subsequent precise positioning of the charging pile. The initial probability distribution is formed by discretizing the location of the charging pile and assigning a probability value to the discretized location unit. The probability of the possible location of the charging pile is updated according to the detected signal, and the updated probability distribution can more accurately reflect the actual location of the charging pile. This application transforms the location of the charging pile from fuzzy area judgment to precise location positioning, thereby improving the accuracy of the charging pile position estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0042] Figure 1 A schematic diagram of the process flow provided for the first embodiment of the robot pile alignment method of the present application;

[0043] Figure 2 A schematic diagram of the positions of infrared sensors provided on the robot and the charging pile provided in the first embodiment of the robot-to-charging pile method of the present application;

[0044] Figure 3 A schematic diagram of the flow chart provided for the second embodiment of the robot pile alignment method of the present application;

[0045] Figure 4 A schematic diagram of the process flow provided for the third embodiment of the robot pile alignment method of the present application;

[0046] Figure 5 A schematic diagram of the field of view angle range of a signal receiving device provided in Example 3 of the robot pile alignment method of the present application;

[0047] Figure 6 A schematic diagram of a flow chart provided for the fourth embodiment of the robot pile alignment method of the present application;

[0048] Figure 7 A schematic diagram of the robot motion trajectory provided in the fourth embodiment of the robot pile alignment method of the present application;

[0049] Figure 8 A schematic diagram of the process flow provided for the fifth embodiment of the robot pile alignment method of the present application;

[0050] Fig. 9 It is a structural diagram of the hardware operating environment involved in the robot pile method in the embodiment of the present application.

[0051] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] The main solution of the embodiment of the present application is: based on the first observation angle of the signal receiving device, perform charging pile detection; after detecting the charging pile, determine the update probability according to the position of the signal receiving device and the second position in the initial probability distribution of the charging pile; update the initial probability distribution of the charging pile position according to the updated probability to obtain the target probability distribution of the charging pile position; determine the maximum probability in the target probability distribution, and determine the charging pile position corresponding to the maximum probability as the target position of the charging pile.

[0055] When the robot needs to charge, it needs to determine the location of the charging pile. Usually, the charging pile is equipped with an infrared signal transmitter that continuously or periodically sends out infrared signals. The robot is equipped with an infrared signal receiver that can receive infrared signals from the charging pile. The robot adjusts its position and posture based on the information provided by the infrared signal to ensure the docking accuracy with the charging pile. However, the infrared signal only provides discrete signals such as the area where the robot is located, rather than continuous and precise coordinates and other determined position observation data, making it difficult to stably and accurately locate the charging pile.

[0056] In order to solve the above problems, this application provides a robot charging pile method, which sets the observation angle and uses the signal receiving device on the robot to search for the signal emitted by the charging pile within a specific range. When the charging pile signal is detected, the initial probability of the possible position of the charging pile is updated according to the robot's own position, and the probability of each possible position is dynamically adjusted. After the probability update is completed, the position corresponding to the maximum probability is found as the target position of the charging pile.

[0057] In this application, by setting the observation angle, targeted detection is performed within an angle range that may contain the charging pile, avoiding directionless blind search and providing area information where the charging pile may exist for the subsequent precise positioning of the charging pile. The initial probability distribution is formed by discretizing the location of the charging pile and assigning a probability value to the discretized location unit. The probability of the possible location of the charging pile is updated according to the detected signal, and the updated probability distribution can more accurately reflect the actual location of the charging pile. This application transforms the location of the charging pile from fuzzy area judgment to precise location positioning, thereby improving the accuracy of the charging pile position estimation.

[0058] It should be noted that the execution subject of this embodiment can be a computing service device with network communication and program running functions, such as a robot, an unmanned vehicle, a server, a server cluster, etc., or an electronic device, device, etc. that can realize the above functions. The following takes a robot as an example to illustrate this embodiment and the following embodiments.

[0059] Based on this, the embodiment of the present application provides a robot pile method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the robot pile alignment method of the present application.

[0060] In this embodiment, the robot pile alignment method is applied to a robot control system, and at least one signal receiving device is provided on the robot. The method includes steps S100 to S400:

[0061] Step S100: performing charging pile detection based on a first observation angle of the signal receiving device.

[0062] In this embodiment, at least one signal sending device is provided on the charging pile, and at least one signal receiving device is provided at the position of the charging contact piece of the robot. The signal sending device and the signal receiving device can be infrared lights, laser radars, Bluetooth signal devices, etc. The signal receiving device can scan the surrounding environment at a certain angle and receive signals within the corresponding range of the angle. When the robot needs to be charged, it detects whether a signal from the charging pile is received within the first observation angle range. If a signal of a specific frequency or intensity is received, it is considered that a charging pile is detected, and there is a charging pile near the current position of the robot. Path planning can be performed to control the robot to move to the position of the charging pile for alignment. After successful alignment, the charging operation is performed.

[0063] In this embodiment, please refer to Figure 2, the signal receiving device is an infrared sensor, and four infrared emitting lamps S1, S2, S3 and S4 are arranged on the charging pile, and the four infrared emitting lamps emit infrared signals at different angles. The charging contact piece is arranged behind the robot, and two external receiving lamps R1 and R2 are arranged at the position of the charging contact piece. R1 and R2 may receive signals sent by the transmitting terminals S1, S2, S3 and S4 respectively. Four infrared emitting lamps are arranged on the charging pile, and the infrared signals emitted by the emitting lamps at different positions form different signal distributions in space. When the infrared receiving sensors R1 and R2 on the robot receive these signals, the position of the robot can be inferred by the source and intensity of the signal. Multiple emitting lamps can provide more positioning reference points. Compared with a single emitting lamp, four emitting lamps can emit signals from different directions and cover a larger spatial range, so that the robot can receive signals at different positions, thereby improving the accuracy and reliability of positioning. By integrating the signal information of multiple emitting lamps, the position coordinates of the robot can be calculated more accurately and the positioning error can be reduced.

[0064] Step S200, after detecting the charging pile, determining the update probability according to the position of the signal receiving device and the second position in the initial probability distribution of the charging pile.

[0065] In this embodiment, after the charging pile is detected, the initial probability distribution of the position of the charging pile is obtained. The position of the signal receiving device set on the robot can be determined based on the robot's own positioning system or based on the signal strength, angle, etc. of the received infrared signal. If R1 receives a signal from S1, indicating that the probability of the robot in the direction corresponding to the charging pile S1 will increase, the increased probability (i.e., the updated probability) is determined based on the position of the signal receiving device and the second position in the initial probability distribution of the charging pile.

[0066] In this embodiment, the signals received by R1 and R2 are processed separately, and the initial probability distribution of the charging pile is updated twice in succession. The first update is based on the signal received by R1, which can initially narrow the range of possible locations of the charging pile. The second update is based on the signal received by R2, combined with the result of the first update, which can further narrow the range, making the final estimated charging pile location more accurate. By receiving and processing the signal twice in succession, the uncertainty of the charging pile location can be gradually reduced, so that the probability distribution is more concentrated near the actual location.

[0067] Step S300: updating the initial probability distribution of the charging pile position according to the updated probability to obtain the target probability distribution of the charging pile position.

[0068] Step S400, determining the maximum probability in the target probability distribution, and determining the charging pile position corresponding to the maximum probability as the target position of the charging pile.

[0069] In this embodiment, the probability in the initial probability distribution is updated according to the obtained update probability. The probability in the initial probability distribution is subtracted from the confidence attenuation, and then added to the calculated update probability to obtain the estimated probability at the current moment. Since the latest update probability is continuously obtained at different times, after obtaining the latest update probability, the probability corresponding to the possible location of the charging pile is updated based on the probability of the previous moment and the latest update probability until the condition for stopping the update is met. The probability update formula is: P t+1 =P t -P C +P; where P t+1 is the estimated probability at the current moment, P t is the probability at the previous moment. PC is an algorithm parameter, which represents the decay of the confidence of the charging pile location over time. P is the updated probability calculated at the current moment. This means that as time goes by, the probability of the previous moment will decrease due to the decay of confidence, and will be adjusted according to the new calculation result (updated probability) at the current moment. After stopping the probability update and obtaining the target probability distribution, find the position with the highest probability in the target probability distribution. The position corresponding to the maximum probability is determined as the target position of the charging pile. In the target probability distribution, find the probability P x,y The maximum value of is taken as the target position.

[0070] Among them, the calculation formula of the target position p2 is:

[0071] In this embodiment, the condition for stopping the update may be that after several consecutive updates, the estimated probability P at the current moment is t+1 If the change is within the preset range of change, it is considered that the probability has stabilized and the update can be stopped at this time. The condition for stopping the update can also be that the number of updates reaches the preset number of updates. The condition for stopping the update can also be that the maximum probability in the probability distribution is greater than the preset probability threshold. At this time, it is considered that the confidence of the charging pile position determined according to the current probability distribution is high enough and the update can be stopped.

[0072] When the robot needs to charge, it needs to determine the location of the charging pile. Usually, the charging pile is equipped with an infrared signal transmitter that continuously or periodically sends out infrared signals. The robot is equipped with an infrared signal receiver that can receive infrared signals from the charging pile. The robot adjusts its position and posture based on the information provided by the infrared signal to ensure the docking accuracy with the charging pile. However, the infrared signal only provides discrete signals such as the area where the robot is located, rather than continuous and precise coordinates and other determined position observation data, making it difficult to stably and accurately locate the charging pile.

[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , before step S100, steps S01 to S03 may be included:

[0074] Step S01, obtaining first position information of the charging pile, and determining a discretization range according to the first position information.

[0075] Step S02, discretizing the coordinates within the discretization range to obtain discretized coordinate points.

[0076] Step S03: input the discretized coordinate points into a preset probability distribution model to obtain the initial probability distribution.

[0077] In this embodiment, the recorded charging pile location is obtained. Among them, C represents the charging pile coordinate system, m represents the map coordinate system, It is a 3*3 rotation matrix, which is used to describe the rotation of the charging pile coordinate system relative to the map coordinate system; It is a 3*1 translation matrix, which is used to describe the translation of the charging pile coordinate system relative to the map coordinate system. The charging pile coordinate system is a local coordinate system established with the charging pile as the origin. In the charging pile coordinate system, the position of the charging pile is fixed as the origin (0, 0, 0), and other points are located according to their positions relative to the charging pile. The map coordinate system is a global, unified coordinate system used to locate all points on the map. In the map coordinate system, each point has a unique, fixed position. By converting the position of the charging pile from the charging pile coordinate system to the map coordinate system, the position of the charging pile can be associated and matched with other geographic elements (such as roads, buildings, etc.), thereby providing more accurate and intuitive location information.

[0078] In this embodiment, the coordinate points around the charging pile position are discretized, and the discretized coordinate points form a grid or dot matrix for simulating the charging demand distribution around the charging pile. The discretization range can be determined by a pre-set fixed radius. With the charging pile position as the center, a fixed radius range is set, and all coordinate points within this radius range are discretized. The area where the charging pile is located can also be divided into a series of grids (such as square, rectangular or hexagonal grids), and the coordinate points of the grid where the charging pile is located and its adjacent grids are used as the discretization range. When performing discretization, a step size (or resolution) is determined, and the continuous coordinate values ​​are divided into discrete intervals by the step size. The coordinate value is divided by the step size and rounded to the integer, and each continuous coordinate value is mapped to the discrete interval to which it belongs. A unique index value is assigned to each discrete interval, and each coordinate value is represented by a simple integer index. For example, if the step size is 0.5, then the coordinate value 2.3 will be mapped to the discrete interval 4 (2.3 / 0.5=4.6, which is rounded to 4).

[0079] Exemplarily, the step size is 0.05, and the coordinates after discretization are x=(-1, -0.95, -0.90, ..., 0, 0.0, 0.1, ..., 1), y=(-1, -0.95, -0.90, ..., 0, 0.05, 0.1, ..., 1).

[0080] In this embodiment, based on the charging pile position T and the discretized coordinate points, the probability distribution p of the charging pile is constructed. x，y ; Where x and y represent the offset position relative to the charging pile. The preset probability distribution model can be Gaussian distribution, binomial distribution, Poisson distribution, uniform distribution, etc. Exemplarily, the probability of each point is initialized to Gaussian distribution, and σ1 is an algorithm parameter, which represents the degree of discreteness of the distribution. In Gaussian distribution, the farther the distance from the initial charging pile, the smaller the probability. The discretized coordinate point data is used as input, and the mean μ and standard deviation σ of the Gaussian distribution are estimated according to the distribution of discrete coordinate points. The mean represents the center position P of the data. 0,0 =1, the standard deviation σ reflects the degree of dispersion of the data. The probability density function formula using the Gaussian distribution is Calculate the probability density value corresponding to each discrete coordinate point, combine the discrete coordinate points and their corresponding probability density values ​​to form the initial probability distribution of the charging pile.

[0081] In this embodiment, by discretizing the charging pile position, the originally complex continuous space positioning problem is simplified to a problem of selecting from a limited number of grids, reducing the complexity and difficulty of positioning. By using the method of recording the probability of grid position, the observation information provided by the infrared signal can be fully utilized, and the real position of the charging pile can be gradually approached through multiple observations and probability updates. Compared with the traditional positioning method based on fuzzy area information, it can significantly improve the accuracy and stability of positioning.

[0082] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 , step S200 may include steps S210 to S230:

[0083] Step S210: after detecting the signal sent by the charging pile, traverse the second position.

[0084] In this embodiment, when the infrared receiving device provided on the robot receives the infrared signal emitted by the charging pile, it indicates that there is a charging pile nearby, and the robot can be controlled to move to the charging pile and charge the pile. After observing the existence of the charging pile, all possible second positions p(x, y) of the charging pile in the preset initial probability distribution are obtained.

[0085] Step S220, obtaining a position vector between the second position and the position of the signal receiving device, and an angle between the position vector and the central axis vector of the signal receiving device.

[0086] Step S230: determining the update probability according to the angle.

[0087] In this embodiment, the signal receiving device r is obtained. i The position of the signal receiving device is represented by i, where i represents the index of the signal receiving device. To transfer the position of the signal receiving device from the map coordinate system to the charging pile coordinate system, a rotation operation is first performed. The coordinates of the signal receiving device are rotated by the rotation matrix so that their direction is consistent with that of the charging pile coordinate system. Then a translation operation is performed. On the basis of the rotation, a translation vector is added to move the coordinates to the correct position in the charging pile coordinate system. The position of the signal receiving device after the conversion is T C i , and its corresponding rotation matrix and translation matrix are Rotation Matrix It is a 3×3 matrix used to describe the rotation of the signal receiving device in three-dimensional space, and uses trigonometric functions to represent the rotation angle of the coordinate axis. is a 3×1 column vector used to describe the translation of the signal receiving device in three-dimensional space.

[0088] In this embodiment, first, obtain the current location of the robot Location of the signal receiving device Among them, m represents the map coordinate system, b represents the robot, and r i represents the receiving device, and i represents the index of the receiving device. Figure 5 , AC represents the central axis of the signal receiving device, and the vector represented by AC is V AC , AB and AD represent the FOV (Field of View) of the signal receiving device, respectively. Secondly, obtain the possible position p(x, y) of the charging pile in the preset initial probability distribution. Finally, determine the update probability based on the difference between the actual distance between the possible position of the charging pile and the signal receiving device.

[0089] In this embodiment, the update probability is determined according to the angle between the second position and the central axis, and the distance deviation between the second position and the signal receiving device. The possible positions p of the charging pile in the initial probability distribution are traversed in sequence, p = [x, y]. Calculate the vector V Ap , vector V Ap With V AC The angle β between them, and the distance deviation r δ . Vector V Ap Represents the vector pointing from the position of the signal receiving device to the possible position of the charging pile. The angle β is used to measure the degree of deviation of the possible position of the charging pile relative to the central axis of the receiving sensor. Distance deviation r δ represents the distance difference between the actual location of the charging station and the estimated location. δ The smaller the value of is, the closer the actual location of the charging pile is to the estimated location. δ If the value of is large, the actual location of the charging pile is far away from the estimated location.

[0090] Vector V Ap The calculation formula is:

[0091] The calculation formula of angle β is β=atan2(v Ap [1], v Ap [0])-atan2(v AC [1], v AC [0]).

[0092] Among them, atan2(V Ap [1], V Ap [0]) represents the vector V Ap The angle with the positive direction of the x-axis, atan2(V AC [1], V AC[0]) represents the vector V AC The angle with the positive direction of the x-axis, subtracting the two angles to get the vector V Ap With V AC The angle β between them.

[0093] Distance deviation r δ The calculation formula is:

[0094] Among them, ||V Ap ||2 represents the distance between the possible location of the charging pile and the signal receiving device, It is the distance between the actual location of the charging pile and the signal receiving device.

[0095] In this embodiment, after the angle β is obtained, the angle β is compared with the field of view of the signal receiving device. When β>α / 2, it means that the second position exceeds the field of view corresponding to the signal receiving device, and the signal received by the signal receiving device may be inaccurate or very weak, and cannot be effectively used to determine the position of the charging pile. The update probability corresponding to the position outside this range is set to 0 to avoid the interference of unreliable positions on the overall position estimation and save computing resources. When β≤α / 2, the charging pile may be located in Figure 5 For the position of the shaded area, the update probability is determined according to the distance deviation and the angle between the second position and the signal receiving device, taking into account the deviation degree and the distance difference of the second position relative to the direction of the charging contact piece.

[0096] The calculation formula for the update probability is:

[0097] Among them, L represents the update weight, Represents the distribution discreteness of the update probability. For example, L = 0.1, σ 2 =0.2.

[0098] Based on the first embodiment of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 6 , step S400 may include steps S500 to S700:

[0099] Step S500: determining whether the robot needs to spin according to the orientation of the robot and the orientation of the target position.

[0100] Step S600: if necessary, obtain and adjust the orientation of the robot according to the spin angle, and control the robot to move in an arc to the target position.

[0101] Step S700: If not necessary, skip the spinning step and control the robot to move in an arc to the target position.

[0102] In this embodiment, after determining the direction θ3 of the target position p2 of the charging pile, the vector V3 corresponding to θ3, the current position p1 = [x1, y1] of the robot, the direction θ1, and the vector V1 corresponding to θ1, the vector V pointing to the target position of the charging pile is calculated. p1p2 , vector V p1p2 The corresponding angle is θ4. Among them, V p1p2 =p2-p1,θ4=atan2(V p1p2 [1], V p1p2 [0]), θ4 is the angle between the vector from the robot position p1 to the target position p2 and the positive direction of the X-axis. The robot's motion trajectory to the charging pile is determined based on the direction and vector corresponding to the target position and the robot's current position. The robot's motion trajectory can be in a variety of ways. The robot's motion trajectory can be to first rotate and adjust the robot and the charging pile target position to the same direction. Then drive in a straight line to the target position. The robot's motion trajectory can also be to first rotate and then drive to the target position in an arc.

[0103] In this embodiment, the movement process towards the charging pile is transformed into a combination of spinning in place and arc driving. Figure 7 , the starting position is p1, and the end position is p2. First, based on the angle difference between the target position of the charging pile and the position orientation of the robot, determine whether to control the robot to spin in place. The angle difference θ diff The calculation formula is: diff =θ1-(2(θ4-θ3). If the angle difference is greater than the preset threshold, it means that the current direction of the robot is quite different from the direction it needs to face the charging pile. The robot cannot reach the charging pile accurately by driving in an arc, and needs to spin first to adjust the direction. If the angle difference is less than or equal to the preset threshold, it means that the robot can reach the charging pile directly at a suitable angle by driving in an arc, without the need to spin in place, and directly control the robot to reach the target position of the charging pile by driving in an arc. Exemplarily, the preset threshold is 0.1.

[0104] When controlling the robot to spin, adjust the robot's direction from V1 to V2, where the angle between V1 and V2 is θ diff In determining the direction of the spin, in θ diff >0, clockwise rotation is adopted; when θ diff<0, counterclockwise rotation is adopted. When controlling the robot to reach the target position of the charging pile by arc driving, firstly, the straight-line distance l between the current position of the robot and the target position, the curvature C of the arc motion, and the angular velocity W of the arc motion are determined. Then, the robot is controlled from p1 to p2 by the angular velocity W, the curvature C and the set angular velocity V.

[0105] The calculation formula of the straight-line distance l is: The calculation formula for the curvature C of arc motion is: C=2*sin(θ4-θ1) / l, and the angular velocity W=V*C.

[0106] Based on the first embodiment of the present application, in the fifth embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. On this basis, the following steps can be included after step S100:

[0107] When the charging pile is not detected at the first observation angle, the first observation angle is adjusted.

[0108] Charging pile detection is performed based on the adjusted first observation angle.

[0109] If the charging pile is still not detected, the steps of angle adjustment and charging pile detection are repeated until a preset detection time threshold is reached.

[0110] In this embodiment, the charging pile detection is performed according to the first observation angle of the signal receiving device. Exemplarily, the first observation angle range of the signal receiving device is from θ start1 to θ start2 . Within this angle range, detect whether there is a signal from the charging pile. If a charging pile signal is detected, stop the detection process and record the relevant information of the charging pile (such as direction, position, etc.). If the charging pile is not detected at the initial first observation angle, the observation angle needs to be adjusted. The angle increment for each adjustment is △θ, and the angle is adjusted in the counterclockwise direction or clockwise direction.

[0111] In this embodiment, the charging pile detection is performed again based on the adjusted observation angle. If the charging pile signal is detected, the detection process is stopped and the relevant information is recorded. If the charging pile is still not detected at the adjusted angle, the angle adjustment and charging pile detection steps are repeated until the preset detection time threshold is reached. After reaching the preset time threshold, the robot has not found the charging pile after a long search at the current position and within a certain angle range around it. At this time, the position of the robot is adjusted. When the robot moves to the new position, the charging pile detection is performed again according to the above method.

[0112] In this embodiment, by continuously adjusting the observation angle, the search range can be expanded, thereby increasing the probability of detecting the charging pile. Setting the detection time threshold can avoid indefinite angle adjustment and detection operations, thereby improving work efficiency.

[0113] Based on the first embodiment of the present application, in the sixth embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 8 The above-mentioned robot pile alignment method comprises the following steps:

[0114] First, the possible locations of charging piles are discretized, and the continuous space where charging piles may appear is divided into discrete location units for subsequent probability calculation and location judgment. Secondly, the signal receiving device on the robot is used to detect at the current location to determine whether the charging pile can be observed. If the charging pile is observed, the probability distribution of the previously discretized charging pile position is updated based on information such as the angle at which the charging pile is currently observed. The probability of the charging pile appearing at each location is adjusted according to the observation results, which can more accurately reflect the possible location of the charging pile. Finally, the position with the largest probability in the updated probability distribution is used as the moving target, and the robot is moved towards the position of the moving target to achieve the pile alignment.

[0115] By discretizing the charging pile position and using discrete grid positions to record the probability of the possible location of the charging pile, the observation information provided by the signal can be fully utilized. Through multiple observations and probability updates, the accuracy of the determined true location of the charging pile is improved, and the computational complexity and implementation difficulty of positioning are reduced.

[0116] The present application provides a robot, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the robot pairing method in the above-mentioned embodiment one.

[0117] Reference below Fig. 9, which shows a schematic diagram of the structure of a robot suitable for implementing an embodiment of the present application. The above-mentioned robot may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the robot are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the robot to communicate with other devices wirelessly or by wire to exchange data. Although the control device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0118] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0119] The robot provided by the present application adopts the robot-to-pile method in the above embodiment, which can solve the technical problem of how to improve the accuracy of charging pile position estimation. Compared with the prior art, the beneficial effects of the robot provided by the present application are the same as the beneficial effects of the robot-to-pile method provided by the above embodiment, and the other technical features of the robot are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0120] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0121] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0122] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the robot pile-matching method in the above-mentioned embodiment.

[0123] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0124] The computer-readable storage medium may be included in the robot; or it may exist independently without being assembled into the robot. The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the robot, the robot: performs charging pile detection based on the first observation angle of the signal receiving device; after detecting the charging pile, determines the update probability according to the position of the signal receiving device and the second position in the initial probability distribution of the charging pile; updates the initial probability distribution of the charging pile position according to the updated probability to obtain the target probability distribution of the charging pile position; determines the maximum probability in the target probability distribution, and determines the charging pile position corresponding to the maximum probability as the target position of the charging pile.

[0125] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0128] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned robot-to-pile method, and can solve the technical problem of how to improve the accuracy of charging pile position estimation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the robot-to-pile method provided in the above-mentioned embodiment, and will not be repeated here.

[0129] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A robot pile method, characterized in that: Applied to a robot control system, the robot is provided with at least one signal receiving device, and the method described includes: Performing charging pile detection based on the first observation angle of the signal receiving device; After detecting the charging pile, determining an update probability according to the position of the signal receiving device and the second position in the initial probability distribution of the charging pile; The initial probability distribution of the charging pile position is updated according to the updated probability to obtain the target probability distribution of the charging pile position; The maximum probability in the target probability distribution is determined, and the charging pile position corresponding to the maximum probability is determined as the target position of the charging pile.

2. The robot pile alignment method according to claim 1, characterized in that: Before the step of detecting the charging pile based on the first observation angle, the method includes: Acquire first position information of the charging pile, and determine a discretization range according to the first position information; Discretize the coordinates within the discretization range to obtain discretized coordinate points; The discretized coordinate points are input into a preset probability distribution model to obtain the initial probability distribution.

3. The robot pile alignment method according to claim 1, characterized in that: After the charging pile is detected, the step of determining the update probability according to the position of the signal receiving device and the second position in the initial probability distribution of the charging pile comprises: After detecting the signal sent by the charging pile, traversing the second position; Acquire a position vector between the second position and the position of the signal receiving device, and an angle between the position vector and the axis vector of the signal receiving device; The update probability is determined according to the angle.

4. The robot pile alignment method according to claim 3, characterized in that: The step of determining the update probability according to the angle comprises: Determining whether the second position is within the field of view angle of the signal receiving device according to the included angle; If it is within the field of view angle range, determining the update probability according to the distance deviation between the second position and the signal receiving device, and the angle; If it is not within the field of view angle range, the update probability is zero.

5. The robot pile alignment method according to claim 1, characterized in that: The step of updating the initial probability distribution of the charging pile position according to the updated probability to obtain the target probability distribution of the charging pile position includes: determining an amount of confidence decay; The initial probability distribution is updated according to the confidence attenuation and the update probability to obtain the target probability distribution.

6. The robot pile alignment method according to claim 1, characterized in that: After the step of determining the maximum probability in the target probability distribution and determining the charging pile position corresponding to the maximum probability as the target position of the charging pile, the following steps are included: Determining whether the robot needs to spin according to the robot orientation and the target position orientation; If necessary, obtaining and adjusting the orientation of the robot according to the spin angle, and controlling the robot to move to the target position in an arc; If not necessary, the spinning step is skipped and the robot is controlled to travel to the target position in an arc.

7. The robot pile alignment method according to claim 6, characterized in that: The step of determining whether the robot needs to spin according to the robot orientation and the target position orientation comprises: Obtaining an angle difference between the orientation of the target position and the direction in which the robot points to the target position, to obtain the target orientation of the robot; If the target orientation is greater than a preset threshold, it is determined that the robot needs to be controlled to spin.

8. The robot pile alignment method according to claim 1, characterized in that: After the step of performing charging pile detection based on the first observation angle of the signal receiving device, the step further includes: When the charging pile is not detected at the first observation angle, adjusting the first observation angle; Perform charging pile detection based on the adjusted first observation angle; If the charging pile is still not detected, the steps of angle adjustment and charging pile detection are repeated until a preset detection time threshold is reached.

9. A robot, characterized in that: The robot comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the robot pile alignment method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the robot pile alignment method according to any one of claims 1 to 8 are implemented.

Images