Charging pile positioning method and device, robot and readable storage medium

Abstract

Embodiments of the present application provide a charging pile positioning method and device, a robot and a readable storage medium. The method comprises: in a moving process, real-time receiving, by an infrared receiver, signals emitted from an infrared emitter array in a charging pile; updating a pose and an occupancy probability of each particle in a particle group according to the real-time received signals, the particle group being used to represent a probability distribution of a position where the charging pile is located; updating the occupancy probability of each particle by using a radar point cloud to obtain a new occupancy probability of a corresponding particle; if there is no particle with a new occupancy probability greater than a preset threshold, performing particle resampling according to a distribution of all new occupancy probabilities, and returning to the step of real-time receiving signals until a particle with a new occupancy probability greater than the preset threshold is obtained to serve as a position of the charging pile. The method can realize accurate positioning of an indoor charging pile by a robot, and only a small number of observation times are required, thereby greatly improving positioning speed and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robots, and in particular to a charging pile positioning method and device, a robot, and a readable storage medium. BACKGROUND

[0002] With the development of smart homes, robots for replacing manual cleaning have been proposed. During cleaning, the robot will detect its power state in real time and prompt the user to charge when the power is insufficient. This scheme of prompting manual charging is cumbersome and requires user participation. Therefore, some people have proposed a scheme in which the robot positions the charging pile and automatically goes to charge. However, in existing schemes, there are often problems such as inaccurate positioning and low positioning efficiency. SUMMARY

[0003] Embodiments of the present application provide a charging pile positioning method, device, robot, and readable storage medium.

[0004] In a first aspect, embodiments of the present application provide a charging pile positioning method applied to a robot, comprising:

[0005] During movement, signals emitted by an infrared emitter array in the charging pile are received in real time by an infrared receiver;

[0006] According to the real-time received signals, the pose and occupancy probability of each particle in the particle group are updated, and the particle group is used to represent the probability distribution of the position of the charging pile;

[0007] The radar point cloud is obtained by real-time measurement by a laser radar, and the occupancy probability of each particle is updated using the radar point cloud to obtain a new occupancy probability of the corresponding particle;

[0008] If the new occupancy probability is not greater than a preset threshold, particle resampling is performed according to the distribution of all new occupancy probabilities, and the real-time signal receiving step is returned until a particle with a new occupancy probability greater than the preset threshold is obtained as the position of the charging pile.

[0009] In some embodiments, the updating of the pose and occupancy probability of each particle in the particle group according to the real-time received signals comprises:

[0010] The movement position and rotation angle of the robot at the current time are calculated according to the real-time received signals;

[0011] The pose of the particle at the current time is calculated according to the movement position and rotation angle and the pose of the particle at the previous time;

[0012] According to the real-time received signal, a field of view angle overlap region between the robot and the infrared emitter array at a current time is determined;

[0013] According to the field of view angle overlap region and a reverse measurement model of the infrared receiver, an occupancy probability of each particle after pose updating is adjusted.

[0014] In some embodiments, the construction of the reverse measurement model of the infrared receiver includes:

[0015] According to an observation range of the infrared receiver, a field of view angle of the infrared receiver is determined;

[0016] If a particle is located within the field of view angle range, a probability of the particle is set as a first occupancy probability value;

[0017] If a particle is located outside the field of view angle range, the probability of the particle is set as a first free probability value, the first occupancy probability value being greater than the first free probability value.

[0018] In some embodiments, the updating of the occupancy probability of each particle by using the radar point cloud includes:

[0019] According to the radar point cloud, a region where an obstacle is located is determined;

[0020] According to the region where the obstacle is located and a reverse measurement model of the lidar, an occupancy probability of each particle is adjusted.

[0021] In some embodiments, the construction of the reverse measurement model of the lidar includes:

[0022] The charging pile is divided into a base region and a head region;

[0023] If a particle is not located in the head region or the base region, a current occupancy probability of the particle is maintained;

[0024] If a particle is located in the head region, a probability of the particle is set as a second occupancy probability value;

[0025] If the particle is located in the base region, the probability of the particle is set as a second free probability value, the second occupancy probability value being greater than the second free probability value.

[0026] In some embodiments, the particle resampling according to the distribution of all new occupancy probabilities includes:

[0027] According to the new occupancy probability of a corresponding particle, a weight of the corresponding particle is determined, and the weights of all particles are normalized to obtain a normalized weight distribution of each particle;

[0028] According to the normalized weight distribution, a number of particles are selected from the particle set and the weight of each selected particle is equalized to obtain a new particle set.

[0029] In a second aspect, the embodiments of the present application provide a charging pile positioning device applied to a robot, comprising:

[0030] An infrared receiving module is configured to receive, in the moving process, signals emitted by an infrared emitter array in the charging pile in real time through an infrared receiver;

[0031] A first updating module is configured to update the pose and the occupancy probability of each particle in a particle swarm according to the real-time received signals, the particle swarm being used to represent a probability distribution of a position of the charging pile;

[0032] A point cloud obtaining module is configured to obtain a radar point cloud by real-time measurement through a laser radar;

[0033] A second updating module is configured to update the occupancy probability of each particle using the radar point cloud to obtain a new occupancy probability of the corresponding particle;

[0034] A resampling module is configured to, if there is no particle whose new occupancy probability exceeds a preset threshold, perform particle resampling according to the distribution of all new occupancy probabilities, and return to the infrared receiving module to perform the step of real-time signal receiving until a particle whose new occupancy probability is greater than the preset threshold is obtained as the position of the charging pile.

[0035] In a third aspect, the embodiments of the present application provide a robot, comprising an infrared receiver, a laser radar, a processor and a memory, wherein the infrared receiver is configured to receive infrared signals, the laser radar is configured to emit and receive laser, the memory stores a computer program, and the processor is configured to execute the computer program to implement the charging pile positioning method described above.

[0036] In some embodiments, the infrared receiver comprises five infrared receivers, two of which are arranged on the front side of the robot, two of which are arranged on the rear side of the robot, and one of which is arranged on the right side of the robot, wherein the intersection of the field of view of each infrared receiver is empty.

[0037] In a fourth aspect, the embodiments of the present application provide a readable storage medium storing a computer program, which, when executed on a processor, implements the charging pile positioning method described above.

[0038] The embodiments of the present application have the following beneficial effects:

[0039] The charging pile positioning method of the embodiment of the application updates the pose and occupation probability of each particle in the particle group by using the infrared receiver to receive the signals emitted by the infrared emitter array in the charging pile in real time during the movement of the robot, and also updates the occupation probability of each particle by using the radar point cloud to obtain the new occupation probability of the corresponding particle; the particle is resampled according to the distribution of all new occupation probabilities, and the above signal receiving step is returned until the particle with a new occupation probability greater than a preset threshold is obtained to serve as the position of the charging pile. The method uses the infrared sensors used in cooperation with the charging pile and the robot, and the laser radar of the robot itself to jointly realize the positioning of the charging pile. By applying the particle filtering technology to the positioning of the charging pile by the robot, the charging pile can be positioned with high accuracy in a small number of observation times, and the positioning efficiency is greatly improved. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the application, and therefore should not be regarded as a limitation on the scope. Other related drawings can also be obtained by those skilled in the art without creative labor.

[0041] Figure 1 An application schematic diagram of the charging pile positioning method of the embodiment of the application is shown;

[0042] Figure 2 A first flowchart of the charging pile positioning method of the embodiment of the application is shown;

[0043] Figure 3a And Figure 3b Schematic diagrams of the setting positions of the infrared receiver in the robot and the infrared emitter in the charging pile of the embodiment of the application are shown respectively;

[0044] Figure 4 A second flowchart of the charging pile positioning method of the embodiment of the application is shown;

[0045] Figure 5 A schematic diagram of the reverse measurement model of the infrared receiver of the embodiment of the application is shown;

[0046] Figure 6 A schematic diagram of the reverse measurement model of the laser radar of the embodiment of the application is shown;

[0047] Figure 7 A structural schematic diagram of the charging pile positioning device of the embodiment of the application is shown. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application.

[0049] The components of the embodiments of the present application generally described and shown in the accompanying drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0050] Hereinafter, the terms "include", "have", and their conjugates used in various embodiments of the present application merely mean that specific features, numbers, steps, operations, elements, components, or combinations thereof are present and not to preclude the presence or addition of one or more other features, numbers, steps, operations, elements, components, or combinations thereof.

[0051] In addition, the terms "first", "second", "third", and the like are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0052] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present application belong. The terms (such as those defined in commonly used dictionaries) will be interpreted as having a meaning that is the same as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized or overly formal meaning, unless clearly defined in various embodiments of the present application.

[0053] Embodiment 1

[0054] Please refer to Figure 1 The present embodiment proposes a charging pile positioning method for realizing position recognition of a charging pile by a robot. In the present embodiment, the position of the charging pile is fixed, and the robot can move anywhere. When the robot leaves the charging area and needs to return to the charging pile for charging, the position of the charging pile needs to be recognized so as to go to the position for charging. For example, the robot can be a robot with a floor cleaning function, but is not limited thereto. It is worth noting that the robot in the present embodiment does not have a visual recognition function, but includes some sensors for signal acquisition, such as a laser radar, a temperature sensor, etc.

[0055] Exemplarily, as Figure 2 shown in the charging pile positioning method includes:

[0056] Step S110, during the movement, the signals emitted from the infrared emitter array in the charging pile are received in real time by the infrared receiver.

[0057] In this embodiment, the charging pile is provided with an infrared emitter for emitting infrared signals outward. In an implementation, a plurality of infrared emitters arranged according to certain rules can be provided to form an infrared emitter array, so as to be able to provide comprehensive coverage of the two-dimensional space in front of the base. For example, as Figure 3a shown, the charging pile can be provided with five infrared emitters, wherein each infrared emitter has a respective signal emission range, and by reasonably arranging these infrared emitters, comprehensive coverage in front of the base can be achieved.

[0058] Correspondingly, a plurality of infrared receivers are provided on the robot for receiving the infrared band signals emitted from the infrared emitters, and then the signals are analyzed to achieve the positioning of the charging pile. For example, in an implementation, the number of infrared receivers is equal to the number of infrared emitters, and of course it can also be unequal, which is not limited here.

[0059] Taking the charging pile shown in the above Figure 3a as an example, the infrared receivers on the robot can be provided as five, which are respectively arranged at different positions. Specifically, two can be arranged on the front side of the robot, two on the rear side of the robot, and the other on the right side of the robot, as Figure 3b shown. Among them, the intersection of the field of view (FOV) of each infrared receiver is empty, that is, there is no overlap between the FOVs of the infrared receivers, so as to achieve the maximum degree of signal reception. It can be understood that the number of infrared emitters and infrared receivers and their respective arrangement positions in this embodiment are not limited, and can be selected according to actual needs.

[0060] Step S120, according to the real-time received signals, updating the pose and occupancy probability of each particle in the particle group. Wherein, the particle group is used to represent the probability distribution of the real charging pile position.

[0061] Since the existing laser radar-based positioning scheme has the problem of low positioning accuracy, it is difficult to meet the positioning needs of the robot to the charging pile in this application. Therefore, this embodiment proposes to use infrared sensing devices and laser radars and with the help of particle filtering principle to realize accurate and rapid positioning of the robot to the charging pile.

[0062] Exemplarily, a preset number of particles are randomly generated in the space where the robot is located, wherein each particle is provided with an initial pose including the position of the particle and the angle between the particle and the robot. It can be understood that the particle group constructed by the particles is used to represent the probability distribution of the position of the charging pile. Further, by controlling the robot to move constantly while updating the occupation probability of the particles, a unique particle whose occupation probability meets the preset requirement is found, and the particle is taken as the final position of the charging pile.

[0063] In an embodiment, as shown in Figure 4 The step S120 includes:

[0064] In the sub-step S210, the moving position and the rotation angle of the robot at the current time are calculated according to the signals received in real time.

[0065] In the sub-step S220, the pose of the particle at the current time is calculated according to the moving position and the rotation angle and the pose of the particle at the last time.

[0066] Exemplarily, during the movement of the robot, the robot moves according to the planned path, wherein the speed and the distance of each movement can be set by the robot itself or measured by the corresponding sensor. It can be understood that when the position of the robot changes, the relative position and direction between the particles and the robot also often change. In this regard, based on the pose of the particle at the last time, the moving position and the rotation angle at the current time are added to calculate the position and attitude of the particle at the current time, i.e., the above-mentioned pose.

[0067] In the sub-step S230, the FOV overlap region between the robot and the infrared emitter array at the current time is determined according to the signals received in real time.

[0068] When the infrared receiver of the robot can receive the corresponding infrared signal, it means that the direction and position of the charging pile at this time enter the signal detection area of the robot. Since the infrared receiver and the infrared emitter on the robot have their own FOV, the use manual of the device can be consulted to obtain the FOV. Therefore, the robot can calculate the FOV overlap region between the corresponding infrared receiver and the infrared emitter array according to the information such as whether the signal is received at the current time.

[0069] Then, the robot updates the occupancy probabilities of these pose-updated particles based on the pre-built inverse sensor model of the infrared receiver and the overlapping region. The particle's occupancy probability is also denoted as a confidence level, representing how confident the particle's pose is as a charging station location. Correspondingly, there is also a particle's free probability, which represents the probability that the particle is not occupied. It can be understood that this mainly combines the principles of occupancy grid maps to solve for the occupancy probability of each particle as a charging station.

[0070] In one implementation, the construction of the reverse measurement model of the infrared receiver includes:

[0071] The field of view of the infrared receiver is determined based on its observation range, such as... Figure 5 As shown. If a particle is located within this field of view, meaning it can be observed within the observation range, then a first occupancy probability value, denoted as P, is returned for that particle. occ Conversely, if the particle is outside the field of view, it returns a first free probability value, denoted as P. free Among them, the preset first occupancy probability value P occ Greater than the first free probability value P free And the sum of the two is 1. For example, the occupancy probability Pocc ranges from 0.6 to 0.9, while the free probability ranges from 0.1 to 0.4.

[0072] Sub-step S240: Based on the overlapping area of ​​the field of view and the reverse measurement model of the infrared receiver, adjust the occupancy probability of each particle after pose update.

[0073] As an example, based on the aforementioned inverse measurement model, for particles located within the overlapping region of the field of view, their confidence level can be increased by increasing the occupancy probability. Alternatively, for particles located outside the overlapping region of the field of view, their confidence level can be decreased by adjusting the free probability, and so on.

[0074] For example, expressing probability in logarithmic form, i.e., logarithmic probability l(x) = log(p(x) / (1-p(x))), shows that the probability p(x) can be expressed as: p(x) = 1 - (1 / (1+expl(x))). It can be understood that using logarithmic ratios to represent probability avoids probability instability around 0 or 1. Furthermore, it can improve the system's computational speed and accuracy.

[0075] Therefore, the update of the occupancy probability of the aforementioned particles can be expressed as:

[0076] l(t,i)=inv_sensor_model(m ix t z t )+l(t-1,i)-l0;

[0077] wherein, l(t,i) and l(t-1,i) represent the state of the i-th particle at t time and t-1 time respectively; l0 represents the prior attitude; and inv_sensor_model(m t z t ) represents the constructed inverse measurement model. Wherein, m i represents the estimated i-th posterior map, x t represents the attitude of the robot at t time, z t represents the measurement value of the robot, through which the inverse measurement model can be used to calculate the posterior probability according to the known attitude through the occupancy grid map method, and then the updated state of each particle can be obtained.

[0078] For the above inverse measurement model, in step S240, in the embodiment, for the existing particle i, if it is located in the overlapping field of view angle range, the above inverse measurement model of the infrared receiver can be represented as:

[0079] inv_sensor_model(m i x t z t ) IR = log(P occ / (1-P occ ));

[0080] wherein, Pocc represents the occupancy probability, which can be 0.6-0.9, etc.

[0081] For the existing particle i, if it is not in the overlapping field of view angle range, the above inverse measurement model of the infrared receiver can be represented as:

[0082] inv_sensor_model(m i x t z t ) IR = log(P free / (1-P free ));

[0083] wherein, P free represents the free probability, which can be 0.1-0.4, etc.

[0084] For a new particle i, the above inverse measurement model of the infrared receiver can be represented as:

[0085] inv_sensor_model(m ix t z t ) IR = log(P prior / (1-P prior ));

[0086] wherein P prior represents a prior probability, which can be selected as 0.5, etc.

[0087] It can be understood that for each particle, the corresponding inverse measurement model inv_sensor_model(m i x t z t ) IR is substituted into the above formula to calculate the updated state.

[0088] In step S130, real-time measurement is performed by the laser radar to obtain a radar point cloud, and the radar point cloud is used to update the occupancy probability of each particle to obtain a new occupancy probability of the corresponding particle.

[0089] Exemplarily, during movement, the robot also performs real-time detection of obstacles by the laser radar to obtain corresponding laser point cloud data. Then, the laser point cloud data and the inverse measurement model of the laser radar are used to further update the occupancy probability of the particles. Specifically, the region where the obstacle is located can be determined according to the obtained radar point cloud, and then the occupancy probability of each particle is adjusted according to the region where the obstacle is located and the inverse measurement model of the laser radar.

[0090] In an embodiment, the construction of the inverse measurement model of the laser radar includes:

[0091] The charging pile is divided into a pad region and a head region, wherein the head region is associated with the occupancy probability, and the pad region is associated with the free probability, as shown in Figure 6 If the particle is not located in the head region or the pad region, the particle is not updated, i.e., the current occupancy probability of the particle is maintained; if the particle is located in the head region, the probability of the particle is set to a second occupancy probability value; if the particle is located in the pad region, the probability of the particle is set to a second free probability value, wherein the second occupancy probability value is greater than the second free probability value. For example, in an embodiment, the inverse measurement model of the laser radar is represented as:

[0092] inv_sensor_model(mi,x t z t ) Lidar = log(p / (1-p));

[0093] wherein p = 0.7 * p h+ 0.3 * p b ;

[0094] In the formula, p h represents the occupancy probability of the head of the charging pile being regarded as an obstacle by the laser radar; p b represents the freedom probability of the base of the charging pile being selected by the laser radar.

[0095] It can be understood that, based on the above-mentioned inverse measurement model of the laser radar, it can be substituted into the above-mentioned expression of the update of the occupancy probability of the particle to serve as the constructed inverse measurement model, so as to update the occupancy probability of each particle.

[0096] In step S140, if there is no particle with a new occupancy probability greater than the preset threshold, the particles are resampled according to the distribution of all the new occupancy probabilities, and the above-mentioned real-time receiving signal step is returned until a particle with a new occupancy probability greater than the preset threshold is obtained to serve as the position of the charging pile.

[0097] Demonstratively, after the update of the occupancy probability of each particle based on the laser radar is obtained, it can be judged whether the updated new occupancy probability is greater than the preset threshold, so as to determine whether the confidence of the particle meets the requirement, if the confidence meets the requirement, the pose of the particle is taken as the final position of the charging pile. Conversely, if there is no particle with a new occupancy probability greater than the preset threshold, the particles need to be resampled to obtain a new particle set, and then the above-mentioned steps S110-S140 are repeated until a particle with a confidence meeting the requirement is obtained.

[0098] Among them, performing one resampling includes: determining the weight of the corresponding particle according to the new occupancy probability of the corresponding particle, and normalizing the weights of all particles to obtain the normalized weight distribution of each particle; then, according to the distribution of the normalized weight, a plurality of particles with unchanged quantity are selected from the particle set and the weight of each selected particle is equalized to obtain a new particle set.

[0099] It can be understood that the weight of the particle is related to the occupancy probability, and by resampling according to the weight distribution, particles with large weights may be repeatedly drawn and repeatedly appear in the new particle group, and particles with small weights may be discarded in the new particle group. With continuous resampling, the particles with large occupancy probabilities are finally retained, and thus the position of the charging pile can be obtained.

[0100] The charging pile positioning method of the embodiment utilizes the infrared sensor used in cooperation with the charging pile and the laser radar of the robot itself, and combines the particle filtering technology to jointly realize the positioning of the charging pile. The charging pile can be positioned with high accuracy in a small number of observation times, and the positioning efficiency is greatly improved.

[0101] Embodiment 2

[0102] Please refer to Figure 7 Based on the method of Embodiment 1, this embodiment proposes a charging pile positioning device 100 applied to a robot, which exemplarily comprises:

[0103] An infrared receiving module 110 is configured to receive, in real time, signals emitted from an infrared emitter array in a charging pile through an infrared receiver during movement.

[0104] A first updating module 120 is configured to update the pose and occupancy probability of each particle in a particle swarm according to the real-time received signals, the particle swarm being used to represent the probability distribution of the position of the charging pile.

[0105] A point cloud obtaining module 130 is configured to obtain a radar point cloud by real-time measurement through a laser radar.

[0106] A second updating module 140 is configured to update the occupancy probability of each particle using the radar point cloud to obtain a new occupancy probability of the corresponding particle.

[0107] A resampling module 150 is configured to, if there is no particle whose new occupancy probability exceeds a preset threshold, resample the particles according to the distribution of all new occupancy probabilities, and return the infrared receiving module 110 to perform the step of real-time signal receiving until a particle whose new occupancy probability is greater than the preset threshold is obtained as the position of the charging pile.

[0108] It can be understood that the device of this embodiment corresponds to the method of Embodiment 1 described above, and the optional items in Embodiment 1 described above are also applicable to this embodiment, so they will not be described again here.

[0109] The present application also provides a robot, for example, the robot can be constituted by rotating wheels, which exemplarily comprises a laser radar, at least one infrared receiver, a processor and a memory, wherein the infrared receiver is configured to receive infrared signals, the laser radar is configured to emit and receive laser, the memory stores a computer program, and the processor runs the computer program, so that the robot performs the functions of each module in the charging pile positioning method or the charging pile positioning device described above.

[0110] In an embodiment, the infrared receiver of the robot can be provided with five, as described above Figure 3bTwo of the infrared receivers are disposed on the front side of the robot, two of the infrared receivers are disposed on the rear side of the robot, and one of the infrared receivers is disposed on the right side or the left side of the robot, wherein the intersection of the field of view of each infrared receiver is empty. It can be understood that the number and the position of the infrared receivers in the robot are not limited to the above, for example, the number of the infrared receivers can also be four, such as two on the front side and two on the rear side, and the like; or the number of the infrared receivers can also be three, such as one on the front side, one on the rear side, one on the left side, or one on the right side, and the like.

[0111] The application further provides a readable storage medium for storing the computer program used in the robot.

[0112] In several embodiments provided in the application, it should be understood that the disclosed apparatus and method can also be implemented by other means. The apparatus embodiments described above are only illustrative, for example, the flowcharts and structural diagrams in the drawings show the possible implementation architecture, function and operation of the apparatus, method and computer program product according to the embodiments of the application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in alternative implementation manners, the functions annotated in the blocks can also occur in an order different from that annotated in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can also be executed in reverse order, depending on the functions involved. It should also be noted that each block in the structural diagram and / or flowchart, and the combination of blocks in the structural diagram and / or flowchart, can be implemented by a dedicated hardware-based system for executing the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0113] In addition, each functional module or unit in each embodiment of the application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0114] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0115] 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 can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method of positioning a charging station, characterized by, The application is applied to a robot, comprising: During the movement of the robot, signals emitted from an infrared emitter array in a charging pile are received in real time by an infrared receiver arranged on the robot; According to the real-time received signals, the pose and occupancy probability of each particle in a particle group are updated based on the principle of an occupancy grid map, the particle group being used to represent the probability distribution of the position of the charging pile; Obstacles are detected in real time by a laser radar arranged on the robot to obtain a radar point cloud, and the occupancy probability of each particle is updated using the radar point cloud to obtain a new occupancy probability of the corresponding particle; If there is no particle with a new occupancy probability greater than a preset threshold, particle resampling is performed according to the distribution of all new occupancy probabilities, and the above real-time signal receiving step is returned until a particle with a new occupancy probability greater than the preset threshold is obtained, so that the pose of the particle with the new occupancy probability greater than the preset threshold is taken as the position of the charging pile.

2. The charging pile positioning method according to claim 1, characterized in that, The updating of the pose and occupancy probability of each particle in the particle group based on the principle of the occupancy grid map according to the real-time received signals comprises: The movement position and rotation angle of the robot at the current time are calculated according to the real-time received signals; The pose of the particle at the current time is calculated according to the movement position and rotation angle and the pose of the particle at the previous time; The field of view angle overlap region between the robot at the current time and the infrared emitter array is determined according to the real-time received signals; The occupancy probability of each particle after the pose update is adjusted based on the principle of the occupancy grid map according to the field of view angle overlap region and the reverse measurement model of the infrared receiver.

3. The charging pile positioning method according to claim 2, characterized in that, The construction of the reverse measurement model of the infrared receiver comprises: The field of view angle of the infrared receiver is determined according to the observation range of the infrared receiver; If the particle is located within the field of view angle range, the probability of the particle is set as a first occupancy probability value; If the particle is located outside the field of view angle range, the probability of the particle is set as a first free probability value, the first occupancy probability value being greater than the first free probability value.

4. The charging station positioning method of claim 1, wherein, The updating of the occupancy probability of each particle using the radar point cloud comprises: The region where the obstacle is located is determined according to the radar point cloud; The occupancy probability of each particle is adjusted according to the region where the obstacle is located and the reverse measurement model of the laser radar.

5. The charging pile positioning method according to claim 4, characterized in that, The construction of the reverse measurement model of the laser radar comprises: The charging pile is divided into a base region and a head region; If the particle is not located in the head region or the base region, the current occupancy probability of the particle is maintained; If the particle is located in the head region, the probability of the particle is set as a second occupancy probability value; If the particle is located in the base region, the probability of the particle is set as a second free probability value, the second occupancy probability value being greater than the second free probability value.

6. The charging station positioning method of claim 1, wherein, The particle resampling according to the distribution of all new occupancy probabilities comprises: The weight of the corresponding particle is determined according to the new occupancy probability of the corresponding particle, and the weights of all particles are normalized to obtain a normalized weight distribution of each particle; According to the normalized weight distribution, a number of particles are selected from the particle swarm and the weight of each selected particle is equalized to obtain a new particle swarm.

7. A charging station positioning device, characterized by, The application is applied to a robot, comprising: An infrared receiving module is configured to receive, in real time, signals emitted by an infrared emitter array in a charging pile via infrared receivers arranged on the robot during movement of the robot. A first updating module is configured to update the pose and occupancy probability of each particle in a particle swarm based on an occupancy grid map principle according to the real-time received signals, the particle swarm being used to represent a probability distribution of a position of the charging pile. A point cloud acquisition module is configured to perform real-time obstacle detection via a laser radar arranged on the robot to obtain a radar point cloud. A second updating module is configured to update the occupancy probability of each particle using the radar point cloud to obtain a new occupancy probability of the corresponding particle. A resampling module is configured to perform particle resampling according to a distribution of all new occupancy probabilities if there is no new occupancy probability exceeding a preset threshold, and return the infrared receiving module to perform the step of real-time signal receiving until a particle with a new occupancy probability greater than the preset threshold is obtained, so as to take the pose of the particle with the new occupancy probability greater than the preset threshold as the position of the charging pile.

8. A robot, characterized in that The robot comprises infrared receivers, a laser radar, a processor and a memory, wherein the infrared receivers are configured to receive infrared signals, the laser radar is configured to emit and receive laser, the memory stores a computer program, and the processor is configured to execute the computer program to implement the charging pile positioning method according to any one of claims 1-6.

9. The robot of claim 8, wherein, The infrared receivers comprise five, two arranged on the front side of the robot, two arranged on the rear side of the robot, and one arranged on the right side of the robot, wherein the intersection of the field of view angle of each infrared receiver is empty.

10. A readable storage medium, characterized by, The memory stores a computer program, and the computer program is executed on the processor to implement the charging pile positioning method according to any one of claims 1-6. The memory stores a computer program, and the computer program is executed on the processor to implement the charging pile positioning method according to any one of claims 1-6.

Images