Rapid object-finding method and related device based on humanoid robot

Abstract

The present application provides a rapid object-finding method and related devices based on a humanoid robot, the method comprising: obtaining target feature information of a target object and historical object-finding data; determining the target object-finding data corresponding to the target feature information in the historical object-finding data; sorting historical locations from high to low according to historical frequency to obtain a first object-finding location list, and searching according to the first object-finding location list; obtaining a first image of the first object-finding location; if the target object does not exist in the first image, obtaining a blind spot of the first object-finding location, and controlling the humanoid robot to move to the blind spot; if the blind spot can be directly observed, obtaining a second image; if it cannot be directly observed, controlling the humanoid robot to execute a posture adjustment strategy, and obtaining a third image; if the target object does not exist in the second image or the third image, controlling the humanoid robot to move to the second object-finding location to continue searching for the target object.

Description

Technical Field

[0001] The present application relates to the technical field of humanoid robots, and in particular to a rapid object-finding method and related devices based on humanoid robots. Background Art

[0002] In daily life, finding forgotten or lost items is a common problem in people's daily life. Among them, the loss of personal items such as keys, mobile phones, glasses, etc. often causes people to spend a lot of time looking for them. However, this process is not only time-consuming and inefficient, but also more difficult for elderly people living alone to find items due to the decline in memory and physical strength, and may also cause safety hazards.

[0003] At present, although home robots can assist users in finding items to a certain extent, such as searching in a specific area and notifying users of found items through voice or display screens, this method is not efficient, especially when there are a large number of items or the search area is complex, and may not provide accurate results.

[0004] Therefore, how to help users quickly find forgotten items and improve the efficiency and accuracy of finding items needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present application provide a rapid object-finding method and related devices based on a humanoid robot, which can help users quickly find forgotten items and improve the efficiency and safety of object-finding.

[0006] In a first aspect, an embodiment of the present application provides a rapid object-finding method based on a humanoid robot, which is applied to an intelligent controller of the humanoid robot, wherein the humanoid robot includes a visual sensor and the intelligent controller, and the method includes:

[0007] Obtain target feature information of the target object and historical search data for a preset time period;

[0008] Determine the target object search data corresponding to the target characteristic information in the historical object search data; the target object search data includes at least one historical location and at least one historical frequency; each historical location corresponds to a historical frequency;

[0009] Sort the at least one historical location from high to low according to the at least one historical frequency to obtain a first list of locations to be searched for, and control the humanoid robot to search for objects according to the first list of locations to be searched for;

[0010] When the humanoid robot arrives at a first object-seeking location, a first image of the first object-seeking location is acquired through the visual sensor; the first object-seeking location is any one of the first object-seeking location list;

[0011] If the target object does not exist in the first image, obtaining a blind area of ​​the humanoid robot in the first object-hunting location, and controlling the humanoid robot to move to the blind area;

[0012] If the blind area of ​​the visual field can be directly observed, acquiring a second image of the blind area of ​​the visual field by using the visual sensor;

[0013] If the blind area of ​​the visual field cannot be directly observed, controlling the humanoid robot to execute a preset posture adjustment strategy, and acquiring a third image of the blind area of ​​the visual field through the visual sensor;

[0014] If the target object does not exist in the second image or the third image, determining that the target object does not exist in the first object-hunting location;

[0015] The humanoid robot is controlled to move to a second object-seeking location to continue searching for the target object; the second object-seeking location is the next object-seeking location of the first object-seeking location in the first object-seeking location list.

[0016] In a second aspect, an embodiment of the present application provides a rapid object-finding device based on a humanoid robot, which is applied to an intelligent controller of the humanoid robot. The humanoid robot includes a visual sensor and the intelligent controller. The device includes an acquisition module, a determination module, a sorting module, a control module, and an adjustment module, wherein:

[0017] The acquisition module is used to acquire target feature information of the target object and historical object-finding data for a preset time period;

[0018] The determination module is used to determine the target object search data corresponding to the target feature information in the historical object search data; the target object search data includes at least one historical location and at least one historical frequency; each historical location corresponds to a historical frequency;

[0019] The sorting module is used to sort the at least one historical location from high to low according to the at least one historical frequency to obtain a first list of locations for finding objects, and control the humanoid robot to search for objects according to the first list of locations for finding objects;

[0020] The acquisition module is further configured to acquire a first image of a first object-seeking location through the visual sensor when the humanoid robot arrives at the first object-seeking location; the first object-seeking location is any one of the first object-seeking location list;

[0021] The control module is configured to obtain a blind area of ​​the humanoid robot in the first object-hunting location if the target object does not exist in the first image, and control the humanoid robot to move to the blind area;

[0022] The acquisition module is further configured to acquire a second image of the blind area through the visual sensor if the blind area can be directly observed;

[0023] The adjustment module is used to control the humanoid robot to execute a preset posture adjustment strategy and obtain a third image of the blind area of ​​vision through the visual sensor if the blind area of ​​vision cannot be directly observed;

[0024] The determination module is further configured to determine that the target object does not exist in the first object-seeking location if the target object does not exist in the second image or the third image;

[0025] The control module is also used to control the humanoid robot to move to a second searching location to continue searching for the target object; the second searching location is the next searching location of the first searching location in the first searching location list.

[0026] In a third aspect, an embodiment of the present application provides an intelligent controller for a humanoid robot, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps of any method of the first aspect of the embodiment of the present application.

[0027] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in any method of the first aspect of the embodiment of the present application.

[0028] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in any method of the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0029] By implementing the embodiments of the present application, the location where the target object is most likely to appear can be determined based on the historical frequency corresponding to the historical location, so that the location can be searched first to improve the efficiency of finding objects, and the posture of the humanoid robot can be adjusted according to the posture adjustment strategy to facilitate a comprehensive search of blind spots in the field of vision, ensuring that the target object can be found even in areas that are difficult to observe directly, so as to improve the accuracy of finding objects and the probability of finding the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 This is a schematic diagram of a scenario of a rapid object-finding method based on a humanoid robot provided in an embodiment of the present application;

[0032] Figure 2 It is a structural schematic diagram of an intelligent controller of a humanoid robot provided in an embodiment of the present application;

[0033] Figure 3 It is a flowchart of a method for quickly finding objects based on a humanoid robot provided in an embodiment of the present application;

[0034] Figure 4 This is a block diagram of the functional modules of a rapid object-finding device based on a humanoid robot provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0037] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship. The "plurality" appearing in the embodiments of the present application refers to two or more.

[0038] In the embodiments of the present application, "at least one item" or similar expressions refer to any combination of these items, including any combination of single items or plural items, and refer to one or more, and multiple refers to two or more. For example, at least one item of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0039] The "connection" that appears in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not impose any limitations on this.

[0040] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0041] In daily life, finding forgotten or lost items is a common problem in people's daily life. Among them, the loss of personal items such as keys, mobile phones, glasses, etc. often causes people to spend a lot of time looking for them. However, this process is not only time-consuming and inefficient, but also more difficult for elderly people living alone to find items due to the decline in memory and physical strength, and may also cause safety hazards. At present, although home robots can assist users in finding items to a certain extent, such as searching in a specific area and notifying users of found items through voice or display screens. However, this method is not efficient, especially when there are a large number of items or the search area is complex, it may not provide accurate results for finding items. Therefore, how to help users quickly find forgotten items and improve the efficiency and accuracy of finding items needs to be solved urgently.

[0042] To solve the above problems, the embodiments of the present application provide a rapid object-finding method and related devices based on a humanoid robot, which are applied to an intelligent controller of the humanoid robot. The humanoid robot includes a visual sensor and the intelligent controller. First, the target feature information of the target object and the historical object-finding data of a preset time period can be obtained; the target object-finding data corresponding to the target feature information in the historical object-finding data can be determined; the target object-finding data includes at least one historical location and at least one historical frequency; each historical location corresponds to a historical frequency; then, the at least one historical location is sorted from high to low according to the at least one historical frequency to obtain a first object-finding location list, and the humanoid robot is controlled to search according to the first object-finding location list; when the humanoid robot arrives at the first object-finding location, a first image of the first object-finding location is obtained through the visual sensor; The first searching location is any one of the searching locations in the first searching location list; if the target object does not exist in the first image, the blind spot of the humanoid robot in the first searching location is obtained, and the humanoid robot is controlled to move to the blind spot; if the blind spot can be directly observed, a second image of the blind spot is obtained through the visual sensor; if the blind spot cannot be directly observed, the humanoid robot is controlled to execute a preset posture adjustment strategy, and a third image of the blind spot is obtained through the visual sensor; if the target object does not exist in the second image or the third image, it is determined that the target object does not exist in the first searching location; the humanoid robot is controlled to move to a second searching location to continue searching for the target object; the second searching location is the next searching location of the first searching location in the first searching location list.

[0043] It can be seen that the location where the target object is most likely to appear can be determined according to the historical frequency corresponding to the historical location, so as to prioritize the search of the location and improve the efficiency of finding objects. The posture of the humanoid robot is adjusted according to the posture adjustment strategy to facilitate a comprehensive search of the blind area of ​​the field of vision, ensuring that the target object can be found even in the area that is difficult to directly observe, thereby improving the accuracy of finding objects and the probability of finding the target object.

[0044] Combine the following Figure 1 An application scenario for executing a rapid object-finding method based on a humanoid robot in an embodiment of the present application is described. Figure 1 : This is a scene diagram of a method for quickly finding an object based on a humanoid robot provided in an embodiment of the present application. The scene includes a first location and a second location. The first location may be a living room and the second location may be a kitchen, which are not specifically limited here. The humanoid robot is located at the first location, and the target object is located on the dining table at the second location. The target object includes, but is not limited to, a water cup, a mobile phone, a key, a hat, and a backpack, which are not specifically limited here.

[0045] In one possible embodiment, the humanoid robot can be connected to the terminal device of the target user in communication, and the terminal device includes a mobile phone, a tablet, a smart watch and other devices, which are not specifically limited here. The target user can monitor the operation of the humanoid robot in real time through the terminal device, receive the progress information of the search, and remotely control the humanoid robot. Among them, when the target user remembers the location of the target object or finds the target object, a stop search instruction can be sent to the humanoid robot through the terminal device to stop searching for the target object. It can be seen that this instant feedback mechanism can effectively save the power resources of the humanoid robot, avoid unnecessary operations, and ensure that the humanoid robot has sufficient power to handle other tasks.

[0046] In a possible embodiment, the humanoid robot obtains a search instruction for the target object, and the search instruction can be a voice message of the target user or a text message from a terminal device, which is not specifically limited here. The humanoid robot parses the search instruction to obtain the characteristic information of the target object. The humanoid robot obtains the location information of the current position, determines that it is located at the first location according to the location information, and generates a list of search locations. Among them, the location information can be the image information of the current location, or it can be the location information corresponding to the pre-stored location information set, which is not specifically limited here. In the list of search locations, the locations are arranged according to the distance between each location and the humanoid robot, for example, the first location, the second location, and the third location, the first location is closest to the humanoid robot, the second location is closer to the humanoid robot, and the third location is farther from the humanoid robot. Then, the humanoid robot searches for each location according to the list of search locations. Among them, the humanoid robot first searches at the first location according to the characteristic information. If the target object is not found at the first location, it moves to the second location to continue searching. When the humanoid robot finds the target object on the dining table at the second location, it can send a voice prompt message to the target user or send a prompt message to the terminal device to prompt the user that the target object has been found and stop searching for the target object.

[0047] It can be seen that the humanoid robot analyzes the characteristic information of the target object, generates a list of locations to be found according to distance sorting, and then searches sequentially according to the characteristic information and the list of locations to improve the speed and efficiency of the search process and ensure the efficient completion of the search task.

[0048] Combine the following Figure 2 The intelligent controller of the humanoid robot in the embodiment of the present application is described. Figure 2 A schematic diagram of the structure of an intelligent controller of a humanoid robot provided in an embodiment of the present application is shown in FIG. Figure 2As shown, the intelligent controller of the humanoid robot includes one or more processors, a memory, a communication interface and one or more programs, and the processor is communicatively connected with the memory and the communication interface via an internal communication bus.

[0049] Among them, the processor is mainly used for:

[0050] Obtain target feature information of the target object and historical search data for a preset time period;

[0051] Determine the target object-seeking data corresponding to the target characteristic information in the historical object-seeking data; the target object-seeking data includes at least one historical location and at least one historical frequency; each historical location corresponds to a historical frequency;

[0052] Sort at least one historical location from high to low according to at least one historical frequency to obtain a first list of locations to be searched, and control the humanoid robot to search for objects according to the first list of locations to be searched;

[0053] When the humanoid robot arrives at the first object-seeking location, the humanoid robot obtains a first image of the first object-seeking location through the visual sensor; the first object-seeking location is any object-seeking location in the first object-seeking location list;

[0054] If the target object does not exist in the first image, obtaining a blind area of ​​the humanoid robot in the first object-seeking location, and controlling the humanoid robot to move to the blind area;

[0055] If the blind area of ​​the visual field can be directly observed, a second image of the blind area of ​​the visual field is obtained by a visual sensor;

[0056] If the blind area of ​​the visual field cannot be directly observed, the humanoid robot is controlled to execute a preset posture adjustment strategy, and a third image of the blind area of ​​the visual field is obtained through a visual sensor;

[0057] If the target object does not exist in the second image or the third image, it is determined that the target object does not exist in the first search location;

[0058] The humanoid robot is controlled to move to a second searching location to continue searching for the target object; the second searching location is the next searching location of the first searching location in the first searching location list.

[0059] The one or more programs are stored in the above-mentioned memory and are configured to be executed by the above-mentioned processor, and the one or more programs include instructions for executing any step in the above-mentioned method embodiment.

[0060] Among them, the processor can be, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, units and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of DSP and microprocessors, and the like. The communication unit can be a communication interface, a transceiver, a transceiver circuit, and the like, and the storage unit can be a memory.

[0061] The memory may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM).

[0062] It is understandable that the intelligent controller of the humanoid robot may include more or fewer structural elements than those in the above structural block diagram, for example, including a power module, a physical button, a Wi-Fi module, a speaker, a Bluetooth module, a sensor, a display module, etc., which are not limited here. It is understandable that the intelligent controller of the humanoid robot can be applied in Figure 1 The described scenario.

[0063] After understanding the software and hardware architecture of this application, Figure 3 A method for quickly finding objects based on a humanoid robot in an embodiment of the present application is described. Figure 3 A flowchart of a rapid object-finding method based on a humanoid robot provided in an embodiment of the present application is applied to an intelligent controller of a humanoid robot, wherein the humanoid robot includes a visual sensor and the intelligent controller, and specifically includes the following steps:

[0064] Step S301, obtaining target feature information of the target object and historical found object data of a preset time period.

[0065] The step of obtaining target feature information of the target object specifically includes:

[0066] Acquire a search instruction for the target item; determine reference feature information of the target item according to the search instruction; generate at least one feature item to be determined according to the reference feature information; generate an inquiry statement according to the at least one feature item to be determined, and issue the inquiry statement to a target user; acquire answer information for the inquiry statement, and adjust the at least one feature item to be determined according to the answer information to obtain at least one determined feature item; determine the target feature information according to the at least one determined feature item.

[0067] Specifically, a search instruction from a target user is received, and the search instruction can be input by voice or text, which is not specifically limited here. Then, the reference feature information of the target item is determined according to the search instruction. For example, when the target user inputs a search instruction by voice, and the search instruction is "find my red backpack", the search instruction is identified and analyzed and the corresponding reference feature information, i.e., "red backpack", is extracted. Then, at least one feature item to be determined is generated according to the reference feature information, and the at least one feature item to be determined is "red" and "backpack". Then, an inquiry statement is generated according to the at least one feature item to be determined, and an inquiry statement is issued to the target user, for example, "Are you looking for a red backpack?" and "What shape is the backpack you are looking for?" When the target user's answer information is "Yes, red backpack" and "square", the feature item to be determined can be adjusted according to the answer information to obtain the determined feature item, i.e., "red", "backpack", and "square". Finally, the target feature information, i.e., "red square backpack", is determined according to the determined feature item.

[0068] Among them, the local database of the humanoid robot can be used to store historical found object data, and then the historical found object data of a preset time period can be obtained in the local database. The preset time period includes but is not limited to one day, one week, one month, and one year, which are not specifically limited here.

[0069] Step S302, determining the target object search data corresponding to the target feature information in the historical object search data.

[0070] The target object search data includes at least one historical location and at least one historical frequency; each historical location corresponds to a historical frequency.

[0071] Specifically, the historical found object data includes at least one item feature record, and each item feature record corresponds to one found object data. The item feature record matching the target feature information is screened out from the historical found object data, and the target found object data corresponding to the item feature record is obtained. The target found object data includes at least one historical location and at least one historical frequency, wherein the historical location is a location where the target item has appeared, and the historical frequency is the frequency of the target item appearing at the location within a preset time period.

[0072] Step S303, sorting the at least one historical location from high to low according to the at least one historical frequency to obtain a first list of locations to be searched, and controlling the humanoid robot to search for objects according to the first list of locations to be searched.

[0073] Specifically, the historical locations are sorted according to their corresponding historical frequencies to obtain a first list of locations to be found. In the first list of locations to be found, the higher the historical frequency corresponding to the historical location, the more likely it is that the target item will appear at the historical location again, and the higher the ranking of the historical location in the first list of locations to be found. Then, the humanoid robot is controlled to search according to the first list of locations to be found, that is, the locations where the target item appears with high frequency are searched first, thereby improving the efficiency and success rate of the humanoid robot in finding items.

[0074] It can be seen that sorting historical locations according to the frequency of occurrence of items can help prioritize the search for locations where the target items are most likely to appear, improve search efficiency and success rate, and reduce random and repeated searches, thereby saving time and cost.

[0075] In a possible embodiment, if the target object finding data corresponding to the target feature information does not exist in the historical object finding data, the target object type of the target object is obtained; based on the mapping relationship between the preset object type and the probability level of the reference location, the probability levels of multiple reference locations corresponding to the target object type are determined to obtain multiple reference probability levels; each reference location corresponds to a reference probability level; the multiple reference locations are sorted from high to low according to the multiple reference probability levels to obtain a second object finding location list, and the humanoid robot is controlled to search according to the second object finding location list.

[0076] It can be seen that the probability level of the item appearing in each reference location is determined according to the type of the item, and locations with high probability levels are searched first to improve the speed and efficiency of finding the item.

[0077] It should be noted that the target item types include but are not limited to personal items, stationery items, household items, and clothing accessories, among which personal items may be keys, wallets, glasses, etc., stationery items may be pens, notebooks, folders, etc., household items may be remote controls, chargers, books, etc., and clothing accessories may be hats, scarves, gloves, etc. When the target item is a hat, the target item type of the target item is a clothing accessory, and according to the mapping relationship between the preset item type and the probability level of the reference location, the probability levels of multiple reference locations corresponding to the target item type are determined to obtain multiple reference probability levels. For example, the probability level of the cloakroom is high, the probability level of the bedroom is relatively high, the probability level of the living room is medium, the probability level of the study is relatively low, and the probability level of the kitchen is low.

[0078] Step S304: When the humanoid robot arrives at a first object-seeking location, the visual sensor is used to obtain a first image of the first object-seeking location.

[0079] The first lost object location is any lost object location in the first lost object location list.

[0080] Specifically, a visual sensor is installed on the head of the humanoid robot, and the visual sensor is used to capture images or video streams of the surrounding environment and perform recognition and analysis on the images. When the humanoid robot moves to the first search location, the visual sensor can obtain a first image of the first search location and perform recognition and analysis on the first image to determine whether the target object exists in the first image.

[0081] In a possible embodiment, if the target object exists in the first image, the first position of the target object and the second position of the humanoid robot are obtained; the shortest path is planned according to the first position and the second position, and the humanoid robot is controlled to move along the shortest path to reach the first position; during the movement of the humanoid robot, dynamic obstacles on the shortest path are obtained through the visual sensor; the dynamic obstacles are objects that can move autonomously; the motion trajectory of the dynamic obstacles is determined; and the shortest path is adjusted according to the motion trajectory to avoid the dynamic obstacles.

[0082] Specifically, if there is a target object in the first image, the first position of the target object is determined according to the first image, and the second position of the humanoid robot at the current moment is determined. Then, path planning is performed according to the first position and the second position, and the shortest path is calculated. A movement instruction is generated according to the shortest path, and the humanoid robot is controlled to move along the shortest path according to the movement instruction to reach the first position. The movement instruction includes forward, turn, and backward. In the process of the movement of the humanoid robot, dynamic obstacles on the shortest path can be obtained by a visual sensor. The dynamic obstacles are objects that can move autonomously, including but not limited to sweeping robots, humans, and animals, which are not specifically limited here. The motion parameters of the dynamic obstacles can be recorded, and the motion parameters include but are not limited to position, speed, and direction, and the motion trajectory of the dynamic obstacle is determined according to the motion parameters. It is determined whether the motion trajectory conflicts with the current shortest path, that is, intersects or overlaps. If it is determined that the motion trajectory conflicts with the current shortest path, the shortest path is adjusted according to the intersection or overlap point of the motion trajectory and the shortest path to avoid the dynamic obstacles. For example, turning and re-planning the route before an intersection or coincidence point.

[0083] It can be seen that by detecting dynamic obstacles in real time and recording their motion trajectories, the path planning can be dynamically adjusted to ensure that the humanoid robot always chooses the optimal path to avoid obstacles, thereby improving the efficiency and accuracy of path planning.

[0084] In a possible embodiment, the humanoid robot includes a first manipulator and a second manipulator, and obtains the target volume of the target object through the visual sensor; if the target volume is less than or equal to a preset volume threshold, the distances between the first position and the first manipulator and the second manipulator are obtained respectively to obtain a first distance and a second distance; if the first distance is less than or equal to the second distance, the first manipulator is controlled to pick up the target object; if the first distance is greater than the second distance, the second manipulator is controlled to pick up the target object; if the target volume is greater than the volume threshold, the first manipulator and the second manipulator are controlled to pick up the target object; when the humanoid robot gets the target object, it sends a prompt message to the target user or moves to the position of the target user.

[0085] Specifically, after the humanoid robot reaches the first position of the target object, the target volume of the target object can be obtained through the visual sensor. If the target volume is less than or equal to the preset volume threshold, the distance between the first position and the first manipulator and the second manipulator is obtained to obtain the first distance and the second distance. If the first distance is less than or equal to the second distance, the first manipulator is controlled to pick up the target object. If the first distance is greater than the second distance, the second manipulator is controlled to pick up the target object to ensure that the manipulator closer to the target object is used to pick up the object, thereby improving the work efficiency of picking up the object. It should be noted that the volume threshold can be set according to the preset picking capacity of the manipulator, and the picking capacity is the maximum object volume that a single manipulator can pick up. For example, when the target volume is less than or equal to the volume threshold, the target object can be picked up by a single manipulator, that is, the first manipulator or the second manipulator, but when the target volume is greater than the volume threshold, the target object needs to be picked up by two manipulators working together. Therefore, if the target volume is greater than the volume threshold, the first manipulator and the second manipulator are controlled to pick up the target object. When the humanoid robot gets the target object, it can send a prompt message to the target user or move to the position of the target user. The prompt information may be broadcasted via voice or sent to a terminal device of the target user, which is not specifically limited here.

[0086] It can be seen that by selecting a manipulator that is closer to the object, the operation time and error can be reduced, the efficiency and accuracy of the humanoid robot in picking up objects can be improved, and the use of a single manipulator or a double manipulator can be automatically adjusted according to the volume of the object to improve the flexibility and stability of picking up objects.

[0087] Step S305: If the target object does not exist in the first image, a blind spot of the humanoid robot in the first object-hunting location is obtained, and the humanoid robot is controlled to move to the blind spot.

[0088] Specifically, if it is determined that the target object does not exist in the first image, the first image is further analyzed to determine the area in the first location that may be blocked or uncovered, which is the blind area. The blind area is usually an area that cannot be covered by the current viewing angle of the humanoid robot, including but not limited to the area behind the door, the area behind the sofa, the area under the table, and the area under the bed. Then, the humanoid robot is controlled to move to the position of the blind area to further observe whether there is a target object in the blind area.

[0089] It can be seen that by ensuring that the humanoid robot searches for the target object within all possible fields of view, omissions can be avoided and the probability of finding the target object can be increased.

[0090] Step S306: If the blind area can be directly observed, a second image of the blind area is acquired through the visual sensor.

[0091] Specifically, if the blind spot can be directly observed, for example, the area behind a door or behind a sofa, etc., a second image of the blind spot is obtained through the visual sensor of the humanoid robot, and it is determined whether there is a target object in the second image.

[0092] Step S307: If the blind area cannot be directly observed, the humanoid robot is controlled to execute a preset posture adjustment strategy, and a third image of the blind area is acquired through the visual sensor.

[0093] Among them, if the blind spot of the field of vision cannot be directly observed, for example, the area under the table, the area under the bed and other areas that cannot be directly observed, the humanoid robot can be controlled to execute a preset posture adjustment strategy and adjust the posture of the humanoid robot to change the position of its visual sensor, so as to obtain a third image of the blind spot of the field of vision through different perspectives and determine whether there is a target object in the third image.

[0094] The humanoid robot includes a waist joint and a leg joint, and the controlling the humanoid robot to execute a preset posture adjustment strategy and obtaining a third image of the blind area of ​​the visual field through the visual sensor includes:

[0095] Obtain the vertical height between the blind spot and the visual sensor; when the vertical height is less than or equal to a preset first height threshold, determine a first adjustment parameter corresponding to the vertical height; adjust the waist joint according to the first adjustment parameter to obtain a first posture; when the vertical height is greater than the first height threshold, determine a second adjustment parameter corresponding to the vertical height; adjust the waist joint and / or the leg joint according to the second adjustment parameter to obtain a second posture; control the humanoid robot to maintain the first posture or the second posture, and obtain the third image through the visual sensor.

[0096] Specifically, first determine the viewing angle position where the blind spot can be observed. For example, the viewing angle position corresponding to the area under the table can be the edge position of the table. When the visual sensor is at the edge position, the entire image of the area under the table can be captured. Then calculate the vertical height between the viewing angle position of the blind spot and the current position of the visual sensor. When the vertical height is less than or equal to the preset first height threshold, determine the first adjustment parameter corresponding to the vertical height. Among them, the first height threshold can be set according to the height of the humanoid robot and the degree of bendability of its waist joint to ensure that when the vertical height is less than or equal to the first height threshold, the entire image of the blind spot can be obtained only by adjusting the waist joint. For example, the first height threshold is pre-set to 0.4 meters and the vertical height is 0.2 meters. According to the mapping relationship between the preset vertical height and the adjustment parameter, the first adjustment parameter corresponding to the vertical height is determined, that is, the waist joint is bent by 15 degrees. Then adjust the waist joint according to the first adjustment parameter to obtain the first posture, that is, the waist joint of the humanoid robot is bent by 15 degrees. It should be noted that when the waist joint of the humanoid robot is bent 15 degrees, the visual sensor on its head can be offset downward by 0.2 meters to obtain the entire image of the blind spot. When the vertical height is greater than the first height threshold, the second adjustment parameter corresponding to the vertical height is determined. For example, the second adjustment parameter can be a 15-degree bending of the waist joint and / or a 10-degree bending of the leg joint, which is not specifically limited here. The waist joint and / or leg joint are adjusted according to the second adjustment parameter to obtain a second posture. Finally, the humanoid robot is controlled to maintain the first posture or the second posture, and a third image of the blind spot is obtained through the visual sensor.

[0097] It can be seen that adjusting the posture of the humanoid robot according to the position height of the blind spot can ensure that the visual sensor can capture the entire image of the blind spot and avoid information omission. At the same time, determining the corresponding adjustment parameters according to different heights allows the humanoid robot to make the best posture adjustment in a limited space, thereby improving the flexibility and adaptability of the humanoid robot in complex environments.

[0098] In a possible embodiment, the clarity of the third image can be obtained; if the clarity is less than a preset clarity threshold, the light intensity of the blind spot is obtained; the target adjustment factor corresponding to the light intensity is determined; the initial sensitivity of the visual sensor is adjusted according to the target adjustment factor to obtain the target sensitivity; wherein, the higher the sensitivity, the brighter the captured image; the shooting distance between the blind spot and the visual sensor is obtained; the initial focal length of the visual sensor is adjusted according to the shooting distance to obtain the target focal length; the visual sensor is set according to the target sensitivity and the target focal length, and a fourth image of the blind spot is obtained through the visual sensor.

[0099] It can be seen that the sensitivity of the visual sensor is dynamically adjusted according to the light intensity of the blind spot to adapt to different lighting conditions, ensuring that the image can be clearly seen in various environments, and adjusting the focal length according to the shooting distance to ensure that the visual sensor can focus clearly at different distances to avoid image blur. Therefore, by adjusting the clarity of the image, the accuracy and success rate of the humanoid robot in finding objects in complex environments are improved.

[0100] Step S308: If the target object does not exist in the second image or the third image, it is determined that the target object does not exist in the first search location.

[0101] Specifically, if the target object does not exist in the second image or the third image, it means that the first search location has been fully searched and it is determined that the target object does not exist in the first search location.

[0102] Step S309, controlling the humanoid robot to move to a second object-seeking location to continue searching for the target object; the second object-seeking location is the next object-seeking location of the first object-seeking location in the first object-seeking location list.

[0103] Specifically, if the first search location list is a cloakroom, a bedroom, and a study, the first search location is the cloakroom, the second search location is the bedroom, and the third search location is the study. If the target object is not found at the first search location, the target object can be moved to the second search location to continue searching for the target object.

[0104] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the intelligent controller of the humanoid robot includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0105] The embodiment of the present application can divide the intelligent controller of the humanoid robot into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0106] In the case of dividing each functional module into corresponding functional modules, Figure 4 A functional module composition block diagram of a humanoid robot-based rapid object-finding device provided in an embodiment of the present application is applied to an intelligent controller of a humanoid robot. The humanoid robot includes a visual sensor and the intelligent controller. The rapid object-finding device 400 based on a humanoid robot includes an acquisition module 410, a determination module 420, a sorting module 430, a control module 440, and an adjustment module 450, wherein:

[0107] The acquisition module 410 is used to acquire target feature information of the target object and historical object-finding data for a preset time period;

[0108] The determination module 420 is used to determine the target object search data corresponding to the target feature information in the historical object search data; the target object search data includes at least one historical location and at least one historical frequency; each historical location corresponds to a historical frequency;

[0109] The sorting module 430 is used to sort the at least one historical location from high to low according to the at least one historical frequency to obtain a first list of locations for searching, and control the humanoid robot to search for objects according to the first list of locations for searching;

[0110] The acquisition module 410 is further configured to acquire a first image of a first object-seeking location through the visual sensor when the humanoid robot arrives at the first object-seeking location; the first object-seeking location is any one of the first object-seeking location list;

[0111] The control module 440 is configured to obtain a blind area of ​​the humanoid robot in the first object-hunting location if the target object does not exist in the first image, and control the humanoid robot to move to the blind area;

[0112] The acquisition module 410 is further configured to acquire a second image of the blind area through the visual sensor if the blind area can be directly observed;

[0113] The adjustment module 450 is used to control the humanoid robot to execute a preset posture adjustment strategy and obtain a third image of the blind area of ​​vision through the visual sensor if the blind area of ​​vision cannot be directly observed;

[0114] The determination module 420 is further configured to determine that the target object does not exist in the first object-seeking location if the target object does not exist in the second image or the third image;

[0115] The control module 440 is further used to control the humanoid robot to move to a second searching location to continue searching for the target object; the second searching location is the next searching location of the first searching location in the first searching location list.

[0116] Optionally, in the aspect of acquiring target feature information of the target object, the acquisition module 410 is specifically used for:

[0117] Obtaining a search instruction for the target object;

[0118] Determine reference feature information of the target object according to the object-finding instruction;

[0119] generating at least one feature item to be determined according to the reference feature information;

[0120] generating a query statement according to the at least one feature item to be determined, and sending the query statement to the target user;

[0121] Acquire answer information for the query statement, and adjust the at least one feature item to be determined according to the answer information to obtain at least one determined feature item;

[0122] The target feature information is determined according to the at least one determined feature item.

[0123] Optionally, the control module 440 is specifically used for:

[0124] If the target object exists in the first image, obtaining a first position of the target object and a second position of the humanoid robot;

[0125] planning a shortest path according to the first position and the second position, and controlling the humanoid robot to move along the shortest path to reach the first position;

[0126] During the movement of the humanoid robot, the dynamic obstacles on the shortest path are acquired by the visual sensor; the dynamic obstacles are objects that can move autonomously;

[0127] Determining the motion trajectory of the dynamic obstacle;

[0128] The shortest path is adjusted according to the motion trajectory to avoid the dynamic obstacle.

[0129] Optionally, the humanoid robot includes a first manipulator and a second manipulator, and the control module 440 is further specifically used for:

[0130] Acquiring the target volume of the target object by using the visual sensor;

[0131] If the target volume is less than or equal to a preset volume threshold, obtaining the distances between the first position and the first manipulator and the second manipulator, respectively, to obtain a first distance and a second distance;

[0132] If the first distance is less than or equal to the second distance, controlling the first manipulator to pick up the target object;

[0133] If the first distance is greater than the second distance, controlling the second manipulator to pick up the target object;

[0134] If the target volume is greater than the volume threshold, controlling the first manipulator and the second manipulator to pick up the target object;

[0135] When the humanoid robot gets the target object, it sends a prompt message to the target user or moves to the location of the target user.

[0136] Optionally, the humanoid robot includes a waist joint and a leg joint. In controlling the humanoid robot to execute a preset posture adjustment strategy and acquiring the third image of the blind spot of the visual field through the visual sensor, the adjustment module 450 is specifically used to:

[0137] Obtaining the vertical height between the blind area of ​​the visual field and the visual sensor;

[0138] When the vertical height is less than or equal to a preset first height threshold, determining a first adjustment parameter corresponding to the vertical height;

[0139] Adjusting the waist joint according to the first adjustment parameter to obtain a first posture;

[0140] When the vertical height is greater than the first height threshold, determining a second adjustment parameter corresponding to the vertical height;

[0141] Adjusting the waist joint and / or the leg joint according to a second adjustment parameter to obtain a second posture;

[0142] The humanoid robot is controlled to maintain the first posture or the second posture, and the third image is acquired through the visual sensor.

[0143] Optionally, the control module 440 is further specifically configured to:

[0144] Acquiring the clarity of the third image;

[0145] If the clarity is less than a preset clarity threshold, obtaining the light intensity of the blind area of ​​the field of view;

[0146] Determining a target adjustment factor corresponding to the light intensity;

[0147] Adjusting the initial sensitivity of the visual sensor according to the target adjustment factor to obtain a target sensitivity; wherein the higher the sensitivity, the brighter the captured image;

[0148] Obtaining a shooting distance between the blind area of ​​the visual field and the visual sensor;

[0149] Adjusting the initial focal length of the visual sensor according to the shooting distance to obtain a target focal length;

[0150] The visual sensor is set according to the target sensitivity and the target focal length, and a fourth image of the blind area of ​​the field of view is acquired through the visual sensor.

[0151] Optionally, the control module 440 is further specifically configured to:

[0152] If the target object search data corresponding to the target characteristic information does not exist in the historical object search data, obtaining the target object type of the target object;

[0153] According to the mapping relationship between the preset item type and the probability level of the reference location, the probability levels of multiple reference locations corresponding to the target item type are determined to obtain multiple reference probability levels; each reference location corresponds to a reference probability level;

[0154] The multiple reference locations are sorted from high to low according to the multiple reference probability levels to obtain a second list of locations to be searched for, and the humanoid robot is controlled to search for objects according to the second list of locations to be searched for.

[0155] It can be seen that the location where the target object is most likely to appear can be determined according to the historical frequency corresponding to the historical location, so as to prioritize the search of the location and improve the efficiency of finding objects. The posture of the humanoid robot is adjusted according to the posture adjustment strategy to facilitate a comprehensive search of the blind area of ​​the field of vision, ensuring that the target object can be found even in the area that is difficult to directly observe, thereby improving the accuracy of finding objects and the probability of finding the target object.

[0156] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above. The rapid object-finding device 400 based on the humanoid robot can be used to execute the above method embodiment of the present application, which will not be described in detail.

[0157] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes an intelligent controller of a humanoid robot.

[0158] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an intelligent controller of a humanoid robot.

[0159] It should be noted that, for the above-mentioned various embodiments, for the sake of simple description, they are all expressed as a series of action combinations. Those skilled in the art should be aware that the present application is not limited by the described order of actions, because some steps in the embodiments of the present application can be performed in other orders or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions, steps, modules or units involved are not necessarily required by the embodiments of the present application.

[0160] In the above embodiments, the embodiments of the present application have different focuses on the description of each embodiment. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0161] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0162] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by executing software instructions by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, read-only compact disks (CD-ROMs) or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also exist in a terminal device or a management device as discrete components.

[0163] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0164] The modules / units included in the devices and products described in the above embodiments may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units. For example, for the devices and products applied to or integrated in the chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for the devices and products applied to or integrated in the chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as chip, circuit module, etc.) or different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. It is implemented in the form of a software program that runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal equipment, or at least some of the modules / units can be implemented in the form of a software program that runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.

[0165] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not intended to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A rapid object-finding method based on a humanoid robot, characterized in that: An intelligent controller applied to a humanoid robot, the humanoid robot comprising a visual sensor and the intelligent controller, the method comprising: Obtain target feature information of the target object and historical search data for a preset time period; Determine the target object search data corresponding to the target characteristic information in the historical object search data; the target object search data includes at least one historical location and at least one historical frequency; each historical location corresponds to a historical frequency; Sort the at least one historical location from high to low according to the at least one historical frequency to obtain a first list of locations to be searched for, and control the humanoid robot to search for objects according to the first list of locations to be searched for; When the humanoid robot arrives at a first object-seeking location, a first image of the first object-seeking location is acquired through the visual sensor; the first object-seeking location is any one of the first object-seeking location list; If the target object does not exist in the first image, obtaining a blind area of ​​the humanoid robot in the first object-hunting location, and controlling the humanoid robot to move to the blind area; If the blind area of ​​the visual field can be directly observed, acquiring a second image of the blind area of ​​the visual field by using the visual sensor; If the blind area of ​​the visual field cannot be directly observed, controlling the humanoid robot to execute a preset posture adjustment strategy, and acquiring a third image of the blind area of ​​the visual field through the visual sensor; If the target object does not exist in the second image or the third image, determining that the target object does not exist in the first object-hunting location; The humanoid robot is controlled to move to a second object-seeking location to continue searching for the target object; the second object-seeking location is the next object-seeking location of the first object-seeking location in the first object-seeking location list.

2. The method according to claim 1, characterized in that The step of obtaining target feature information of the target object includes: Obtaining a search instruction for the target object; Determine reference feature information of the target object according to the object-finding instruction; generating at least one feature item to be determined according to the reference feature information; generating a query statement according to the at least one feature item to be determined, and sending the query statement to the target user; Acquire answer information for the query statement, and adjust the at least one feature item to be determined according to the answer information to obtain at least one determined feature item; The target feature information is determined according to the at least one determined feature item.

3. The method according to claim 2, characterized in that After acquiring the first image of the first object-seeking location by the visual sensor, the method further includes: If the target object exists in the first image, obtaining a first position of the target object and a second position of the humanoid robot; planning a shortest path according to the first position and the second position, and controlling the humanoid robot to move along the shortest path to reach the first position; During the movement of the humanoid robot, the dynamic obstacles on the shortest path are acquired by the visual sensor; the dynamic obstacles are objects that can move autonomously; Determining the motion trajectory of the dynamic obstacle; The shortest path is adjusted according to the motion trajectory to avoid the dynamic obstacle.

4. The method according to claim 3, characterized in that The humanoid robot comprises a first manipulator and a second manipulator, and the method further comprises: Acquiring the target volume of the target object by using the visual sensor; If the target volume is less than or equal to a preset volume threshold, obtaining the distances between the first position and the first manipulator and the second manipulator, respectively, to obtain a first distance and a second distance; If the first distance is less than or equal to the second distance, controlling the first manipulator to pick up the target object; If the first distance is greater than the second distance, controlling the second manipulator to pick up the target object; If the target volume is greater than the volume threshold, controlling the first manipulator and the second manipulator to pick up the target object; When the humanoid robot gets the target object, it sends a prompt message to the target user or moves to the location of the target user.

5. The method according to any one of claims 1 to 4, characterized in that: The humanoid robot includes a waist joint and a leg joint, and the controlling the humanoid robot to execute a preset posture adjustment strategy and obtaining a third image of the blind area of ​​the visual field through the visual sensor includes: Obtaining the vertical height between the blind area of ​​the visual field and the visual sensor; When the vertical height is less than or equal to a preset first height threshold, determining a first adjustment parameter corresponding to the vertical height; Adjusting the waist joint according to the first adjustment parameter to obtain a first posture; When the vertical height is greater than the first height threshold, determining a second adjustment parameter corresponding to the vertical height; Adjusting the waist joint and / or the leg joint according to a second adjustment parameter to obtain a second posture; The humanoid robot is controlled to maintain the first posture or the second posture, and the third image is acquired through the visual sensor.

6. The method according to claim 5, characterized in that After acquiring the third image by the visual sensor, the method further includes: Acquiring the clarity of the third image; If the clarity is less than a preset clarity threshold, obtaining the light intensity of the blind area of ​​the field of view; Determining a target adjustment factor corresponding to the light intensity; Adjusting the initial sensitivity of the visual sensor according to the target adjustment factor to obtain a target sensitivity; wherein the higher the sensitivity, the brighter the captured image; Obtaining a shooting distance between the blind area of ​​the visual field and the visual sensor; Adjusting the initial focal length of the visual sensor according to the shooting distance to obtain a target focal length; The visual sensor is set according to the target sensitivity and the target focal length, and a fourth image of the blind area of ​​the field of view is acquired through the visual sensor.

7. The method according to claim 1, characterized in that The method further comprises: If the target object search data corresponding to the target characteristic information does not exist in the historical object search data, obtaining the target object type of the target object; According to the mapping relationship between the preset item type and the probability level of the reference location, the probability levels of multiple reference locations corresponding to the target item type are determined to obtain multiple reference probability levels; each reference location corresponds to a reference probability level; The multiple reference locations are sorted from high to low according to the multiple reference probability levels to obtain a second list of locations to be searched for, and the humanoid robot is controlled to search for objects according to the second list of locations to be searched for.

8. A rapid object-finding device based on a humanoid robot, characterized in that: An intelligent controller applied to a humanoid robot, the humanoid robot comprising a visual sensor, the intelligent controller, the device comprising an acquisition module, a determination module, a sorting module, a control module and an adjustment module, wherein: The acquisition module is used to acquire target feature information of the target object and historical object-finding data for a preset time period; The determination module is used to determine the target object search data corresponding to the target feature information in the historical object search data; the target object search data includes at least one historical location and at least one historical frequency; each historical location corresponds to a historical frequency; The sorting module is used to sort the at least one historical location from high to low according to the at least one historical frequency to obtain a first list of locations for finding objects, and control the humanoid robot to search for objects according to the first list of locations for finding objects; The acquisition module is further configured to acquire a first image of a first object-seeking location through the visual sensor when the humanoid robot arrives at the first object-seeking location; the first object-seeking location is any one of the first object-seeking location list; The control module is configured to obtain a blind area of ​​the humanoid robot in the first object-hunting location if the target object does not exist in the first image, and control the humanoid robot to move to the blind area; The acquisition module is further configured to acquire a second image of the blind area through the visual sensor if the blind area can be directly observed; The adjustment module is used to control the humanoid robot to execute a preset posture adjustment strategy and obtain a third image of the blind area of ​​vision through the visual sensor if the blind area of ​​vision cannot be directly observed; The determination module is further configured to determine that the target object does not exist in the first object-seeking location if the target object does not exist in the second image or the third image; The control module is also used to control the humanoid robot to move to a second searching location to continue searching for the target object; the second searching location is the next searching location of the first searching location in the first searching location list.

9. An intelligent controller for a humanoid robot, characterized in that: include: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs comprising instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images