Robot interaction method, interaction device and electronic equipment

Abstract

The invention provides an interaction method and device of a robot and electronic equipment. The robot comprises a head and a machine body. The head is rotationally connected with the fuselage; the robot controls the head to rotate in multiple directions to execute various anthropomorphic interaction actions; the robot is used for transporting the distribution goods to the distribution point location; the interaction method comprises the following steps: after a delivery point is reached, detecting a pick-and-place result of a delivered article and controlling a head to execute a personification interaction action corresponding to the pick-and-place result; and / or in the moving process, the surrounding environment is detected, and the head is controlled to execute anthropomorphic interaction actions corresponding to the surrounding environment. Therefore, the problem that the interaction intention of the robot is difficult to understand by the user in the prior art can be solved.

Description

Technical Field

[0001] The present application relates to the technical field of robots, and in particular, to an interaction method, an interaction device and an electronic device for a robot. Background Art

[0002] Nowadays, there are more and more robots used to deliver items in scenarios such as restaurants and hotels. Inevitably, robots need to interact with people during the process of delivering items. For example, users operate the robot to set delivery tasks, and pick up meals after the robot arrives at the delivery point.

[0003] Existing robots generally use screen display, voice broadcast, and light changes as interaction methods to provide information to users. For example, at nodes such as starting delivery and arriving at the target point, voice will be broadcast to the user and light prompts will be assisted. However, the inventor has found that the existing interaction methods are not intuitive enough, and users need to pre-understand the meaning of the function configuration of the robot to clarify the meaning of the interaction information. On the other hand, in scenarios with complex crowds and diverse language environments, there are certain interaction barriers in providing feedback information to users only through text and voice. These all lead to the interaction intentions of existing robots being difficult to be understood by users. Summary of the Invention

[0004] In view of this, the purpose of the present application is to provide an interaction method, an interaction device and an electronic device for a robot, which can solve the problem that the interaction intention of the robot in the prior art is difficult to be understood by users.

[0005] The embodiment of the present application provides an interaction method for a robot. The robot includes a head and a fuselage; the head is rotatably connected to the fuselage; the robot performs a variety of anthropomorphic interaction actions by controlling the head to rotate in multiple directions; the robot is used to transport delivery items to a delivery point; the interaction method includes:

[0006] After arriving at the delivery point, detecting the pick-up and put-down result of the delivery item and controlling the head to perform an anthropomorphic interaction action corresponding to the pick-up and put-down result; and / or,

[0007] During the movement, detecting the surrounding environment and controlling the head to perform an anthropomorphic interaction action corresponding to the surrounding environment.

[0008] The embodiment of the present application also provides an interaction device for a robot. The robot includes a head and a fuselage; the head is rotatably connected to the fuselage; the robot performs a variety of anthropomorphic interaction actions by controlling the head to rotate in multiple directions; the robot is used to transport delivery items to a delivery point; the interaction device includes:

[0009] The first interaction module is used to detect the pick-up and placement result of the delivered item after arriving at the delivery point and control the head to perform anthropomorphic interaction actions corresponding to the pick-up and placement result; and / or,

[0010] The second interaction module is used to detect the surrounding environment during the movement to or from the delivery point and control the head to perform anthropomorphic interaction actions corresponding to the surrounding environment.

[0011] An embodiment of the present application further provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of an interaction method of a robot as described above are executed.

[0012] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of an interaction method of a robot as described above are executed.

[0013] The embodiment of the present application has the following beneficial technical effects:

[0014] For the interaction method, interaction device, and electronic device of the robot provided by the embodiment of the present application, the robot can perform various anthropomorphic interaction actions by controlling the head to rotate in multiple directions, and the user can intuitively and clearly understand the information transmitted by the robot. Specifically, at the delivery point, the robot can more clearly and accurately indicate the pick-up and placement result to the user by performing anthropomorphic interaction actions corresponding to the pick-up and placement result of the delivered item, which helps the user correctly pick up the item and improves the accuracy and efficiency of delivery. During the movement, the robot can more clearly and accurately transmit the surrounding environment information of the robot body to the user by performing anthropomorphic interaction actions corresponding to the surrounding environment, reducing the user's understanding cost, eliminating the need to pre-understand the intention / function expression configuration of the robot, facilitating the user to understand the intention conveyed by the robot and make timely responses, improving the safety of the robot's movement, making the interaction performance of the robot more anthropomorphic, and making the human-computer interaction more friendly and vivid.

[0015] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specific preferred embodiments are given in conjunction with the accompanying drawings and are described in detail as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0017] Figure 1(a) shows a schematic structural diagram of a delivery robot provided by an embodiment of the present application;

[0018] Figure 1(b) shows a schematic diagram of the rotation of the robot head in the vertical direction provided by an embodiment of the present application;

[0019] Figure 2 Figure 10 shows one of the schematic diagrams of an interaction method of a robot during movement provided by an embodiment of the present application;

[0020] Figure 3 Figure 14 shows a schematic diagram of a travel route of a robot provided by an embodiment of the present application;

[0021] Figure 4 Figure 18 shows another schematic diagram of an interaction method of a robot during movement provided by an embodiment of the present application;

[0022] Figure 5 Figure 22 shows a schematic structural diagram of an interaction device of a robot provided by an embodiment of the present application;

[0023] Figure 6 Figure 26 shows a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Usually, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by those skilled in the art without creative efforts belongs to the scope of protection of the present application.

[0025] First, the applicable application scenarios of this application are introduced. This application is applied to the field of robots. Specifically, the robot in the embodiments of this application is a delivery robot used to transport delivery items to the delivery points. As an intelligent device that replaces manual delivery services, it can bring novel experiences to customers while reducing the intensity of manual labor and improving work efficiency. It has been increasingly applied in places such as canteens, restaurants, and hotels.

[0026] Exemplarily, please refer to FIG. 1(a). FIG. 1(a) is a schematic structural diagram of a delivery robot provided by an embodiment of this application. As shown in FIG. 1, the delivery robot includes: a head 10 and a fuselage 20; the head 10 is rotatably connected to the fuselage 20; the fuselage 20 includes a housing 21 for carrying items, a mobile chassis 22, a function controller for providing user operations (not shown in the figure), a low-level controller for map generation and path planning (not shown in the figure), and an element controller for controlling the mobile unit and the environment detection unit (not shown in the figure).

[0027] The housing 21 for carrying items includes a storage rack. The storage rack is fixed on the mobile chassis 22 of the delivery robot, and the storage rack has at least one storage layer 201. Each storage layer 201 can place delivery items. By setting a storage rack with multiple storage layers 201, the delivery robot can have the ability to store multiple items, enabling the delivery robot to deliver multiple items in one operation, thereby improving the delivery efficiency of the delivery robot.

[0028] The mobile chassis 22 is provided with at least two sets of drive wheels (not shown in the figure), and each set of drive wheels is located on one side of the mobile chassis 22; the element controller controls the traveling speed of the drive wheels. At least one turn signal unit is provided at the bottom of the mobile chassis 22, and each turn signal unit includes at least one turn signal (not shown in the figure); the mobile unit is provided with at least two sets of drive wheels, and each set of drive wheels is located on one side of the chassis 22; the element controller controls the traveling speed of the drive wheels; and controls the turn signals in the turn signal unit to be lit in a preset manner when the delivery robot turns.

[0029] Specifically, among the drive wheels provided by the mobile unit, at least one set of drive wheels serves as the left drive wheels, and at the same time, at least one set of drive wheels serves as the right drive wheels. The left drive wheels and the right drive wheels are located on opposite sides of the chassis 22. Optionally, the mobile unit may further include at least two sets of driven wheels, with one set of drive wheels corresponding to one set of driven wheels. Among them, at least one set of driven wheels serves as the left driven wheels, and at the same time, at least one set of driven wheels serves as the right driven wheels. The left driven wheels and the right driven wheels are used to assist the left drive wheels and the right drive wheels in driving the housing 21 and the chassis 22 of the delivery robot to move, reducing the load pressure on the drive wheels.

[0030] The delivery robot provided by the embodiment of the present application can control the turn signal to light up when the delivery robot turns, so as to remind pedestrians to pay attention.

[0031] On the basis of the above technical solution, optionally, when the speed difference between the driving wheels on both sides of the chassis 22 is greater than a preset value, the component controller controls the turn signals in the turn signal unit to light up in a preset manner. Optionally, the delivery robot further includes a voice module, and the voice module is electrically connected to the component controller; when the delivery robot turns, the component controller controls the voice module to send out a voice prompt message.

[0032] Further, the delivery robot further includes a lidar system. The lidar system can be arranged in the device of the delivery robot. The lidar system can rotate along a set plane, so that the photoelectric receiving array of the lidar system forms a scanning cylinder. The lidar system can also be arranged at the slit of the robot housing, so that it is easy to emit laser signals to detect surrounding objects. The above lidar system includes a photoelectric receiving array and a laser emitting unit array. When the lidar system rotates along the set plane, the photoelectric receiving array can form a scanning cylinder, thereby increasing the scanning area, facilitating obtaining details of the object shape, and avoiding the situation of the robot device bumping into obstacles. If the lidar system only includes a single photoelectric receiving unit and a single laser emitting unit, after the lidar system rotates along the set plane, it can only measure the object shape of one circumference and cannot obtain the shape of complex objects in time, which is easy to cause collisions and endanger personal and property safety. Optionally, the above set plane can be a horizontal plane, which is convenient for the robot device to detect objects during the traveling process. In addition, other set planes can also be selected according to user needs, such as a vertical plane, etc. This embodiment does not limit this.

[0033] In one embodiment, during the process of path planning of the delivery robot, the following steps are executed:

[0034] Step S101, determine the positioning map of the current working area, where the positioning map is the map formed by the robot's mapping of its surrounding environment.

[0035] Specifically, the robot is configured with a collection sensor and a modeling processor. The modeling processor constructs an environmental map by modeling the environmental data collected by the collection sensor. In this embodiment, the collection sensor includes a lidar, an ultrasonic sensor, and an infrared sensor. The lidar, ultrasonic sensor, and infrared sensor are used to collect data of the working area where the robot is located. The modeling processor uses the data collected by these sensors to create a map. During the process of creating the map, different map layers are generated by different sensors, such as a static layer, a dynamic obstacle layer, an ultrasonic layer, a visual layer, etc. By fusing these layers, a positioning map for positioning and navigating the robot is obtained.

[0036] Step S102, plan a path according to the positioning map.

[0037] Step S1021, determine the current position and the target position of the robot according to the positioning map.

[0038] Step S1022, determine the obstacle positions according to the positioning map.

[0039] Step S1023, plan a path according to the current position, the target position, and the obstacle positions.

[0040] Specifically, in step S1021, the target position is the position set by the user or the position that the robot's processing system determines to move to. Among them, the target position can be the position that needs to be moved to next determined during the movement process, or the position that the robot finally needs to reach. The current position is the real-time position information of the robot determined by the position sensor.

[0041] In step S1022, the positions of the obstacles on the positioning map are determined through the positioning map. Through this embodiment, the robot can determine the positions of the obstacles and plan a route without changing the navigation accuracy.

[0042] Step S103, move according to the path.

[0043] In another embodiment, during the delivery process, the delivery robot performs the following steps:

[0044] Step 201, the delivery robot moves to the target delivery point.

[0045] Among them, the delivery robot can perform delivery tasks to deliver items for users, such as the guest room delivery service in the hotel scenario and the meal delivery service in the restaurant scenario. The delivery task can be a task of providing a service of delivering goods for users. The delivery scenarios include warehouses, airports, hotels, restaurants, etc. The delivery point refers to a pre-designated position or area in the delivery scenario. The delivery robot can move to the delivery point, notify the user, and wait for the user to pick up the item. Exemplarily, the delivery point can be a specific location in the delivery scenario. For example, a certain building in a community or the entrance of a certain room in a hotel, or next to a certain table in a restaurant, etc. The target delivery point is the specific address required to be delivered by the target delivery task. For example, if the target delivery task is to provide a delivery service to Room B in Area A, the robot can move to the target delivery point, that is, the entrance of Room B in Area A, and call the landline in the room to notify the user to pick up the item at the door; another example is that if the target delivery task is to provide a meal delivery service to Door D of Hotel C, the robot can move to the target delivery point, that is, Door D of Hotel C, and call the phone inside the door to notify the user to pick up the meal at the door; or for example, if the target delivery task is to provide a meal delivery service to Table F in Restaurant E, the robot can move to the target delivery point, that is, Table F in Restaurant E, and control Table F to ring to notify the user to pick up the meal.

[0046] In a specific example, the delivery scenario is a hotel, and the delivery robot can be a delivery robot of the hotel. Each delivery robot has an identification information, for example, ID (Identity document, identity identification number), which is used to identify the identity of the delivery robot. The delivery points of the delivery robots in this hotel include the area at the entrance of the rooms inside the hotel. After the user checks into the hotel, the user can use the hotel's order placement system to order meals or daily necessities. Among them, the order placement system can be a phone order or a mobile APP (Application, application program) service system. For example, when ordering a meal, the user can reserve the meal in the order placement system and enter the room number where the user checks in. The order placement system sends the reserved meal information entered by the user to the hotel's platform system. The platform system can generate a target delivery task by combining the room number where the user checks in and the meal information reserved by the user, and send it to the delivery robot in the hotel. After the robot obtains the meal reserved by the user from the hotel staff, it moves to the target delivery point, and the target delivery point can be the area in front of the room where the user checks in.

[0047] In another specific example, the delivery scenario is a restaurant, and the delivery robot can be a delivery robot of the restaurant. The delivery points of the restaurant's delivery robot include dining locations inside the restaurant, such as the dining table area where the user is located. After the user selects a dining table, he can use the ordering system corresponding to the dining table to order, such as scanning the QR code on the dining table to place an order. When ordering, the user can manually enter the table number of the table or automatically enter the table number of the table. The ordering system sends the reserved dining information entered by the user to the restaurant's platform system. The platform system can generate a target delivery task based on the user's table number and the user's reserved dining information and send it to the delivery robot in the restaurant. After the robot obtains the user's reserved dining from the restaurant staff, it moves to the target delivery point, which can be the dining table area where the user is located. Here, the autonomous delivery of meals by the delivery robot greatly reduces the labor cost and improves the service quality.

[0048] Step 202: The robot triggers key generation, and the key is used to confirm the pickup, such as a pickup code.

[0049] Step 203: The robot prompts the user corresponding to the target delivery point to pick up the item through the communication connection.

[0050] The robot can transmit voice information to the user through the communication connection, prompting the user to move to the target delivery point to pick up the item. The user obtains the robot's pickup prompt information. The robot can inform the user of the delivered item information and the location of the target delivery point in the form of voice. After the user confirms that the item delivered by the robot is the item he or she has reserved, he or she arrives at the location of the target delivery point to obtain the item delivered by the robot.

[0051] For example, when the robot arrives at the dining location of the user, it can call the ringing phone on the dining table to remind the user to pick up the food. After the user confirms that the food delivered by the robot is the food he ordered, he can take the food delivered by the robot.

[0052] Furthermore, when using a delivery robot to deliver items, you need to first place the items to be delivered in the storage layer set in the robot, and then select the delivery location corresponding to the storage layer. Here, each storage layer needs to select its corresponding delivery location. After selecting the delivery location corresponding to each storage layer, click the "Go Now" button on the delivery robot, and the delivery robot can directly enter the delivery page and perform the delivery task.

[0053] However, research has found that robots inevitably need to interact with people during the delivery process. For example, users operate robots to set delivery tasks, and users pick up meals after arriving at the delivery point.

[0054] Existing robots generally use screen display, voice broadcast, and light changes as interaction methods to provide information to users. For example, at nodes such as the start of delivery and arrival at the target point, voice will be broadcast to the user and accompanied by light prompts. When the robot turns during movement, there will be corresponding turn signal prompts, etc. However, the inventor found that the existing interaction methods are not intuitive enough, and users need to pre-understand the meaning of the robot's function configuration to clarify the meaning of the interaction information. On the other hand, in scenarios with complex crowds and diverse language environments, there are certain interaction barriers in providing feedback information to users only through text and voice. These all lead to the difficulty for users to understand the interaction intentions of existing robots.

[0055] Based on this, the embodiments of the present application provide an interaction method, an interaction device, and an electronic device for a robot, which can solve the problem that the interaction intention of the robot in the prior art is difficult to be understood by users.

[0056] The interaction method of the embodiments of the present application can be executed by the interaction device of the robot provided by the embodiments of the present application. The device can be implemented in software and / or hardware and can be integrated into the robot. When implemented in software, the device can be realized through the interaction APP integrated in the robot. The interaction APP summarizes the various states of the robot and controls the robot's head to perform anthropomorphic interaction actions according to the changes in the robot's state and the detection results of pick-and-place results, the surrounding environment, etc.

[0057] Please refer to FIG. 1(b). FIG. 1(b) is a schematic diagram of the rotation of the head of a robot in the vertical direction provided by the embodiments of the present application. In the embodiments of the present application, the head of the robot is rotatably connected to the fuselage, and the head can rotate in multiple directions, such as the horizontal direction, the vertical direction, and the inclined direction, etc. As shown in FIG. 1, the robot can control the head to rotate up and down in the vertical direction at multiple angles.

[0058] And the robot can perform various anthropomorphic interaction actions by controlling the head to rotate in multiple directions. Exemplarily, by controlling the head to rotate left and right in the horizontal direction, an anthropomorphic interaction action representing negation can be performed, simulating the human shaking head action; by controlling the head to rotate up and down in the vertical direction, an anthropomorphic interaction action representing affirmation can be performed, simulating the human nodding action; by alternately performing the actions of controlling the head to rotate left and right in the horizontal direction and up and down in the vertical direction, an anthropomorphic interaction action representing help-seeking can be performed, simulating the action when a human looks around for help; by controlling the bending direction of the head to a curved route, an anthropomorphic interaction action representing observation can be performed, simulating the observation direction action when a human turns, etc.

[0059] Embodiment 1:

[0060] The interaction method of the delivery robot provided by the embodiments of the present application includes:

[0061] S301. After arriving at the delivery point, detect the pick-up and placement result of the delivery item and control the head to perform anthropomorphic interaction actions corresponding to the pick-up and placement result.

[0062] In this step, after the robot arrives at the delivery point, the user can pick up and put back the delivery items carried on the storage layer of the robot. During this process, the user's independent pick-up and put-back operations may be incorrect, that is, incorrect operations are performed, such as incorrectly picking up delivery items that do not belong to this delivery point, or stopping the pick-up operation before all the delivery items belonging to this delivery point are picked up.

[0063] To ensure that the user at the delivery point can correctly pick up all the delivery items, the robot continuously detects the pick-up and placement result of the delivery items; for example, compares the currently picked-up items with the items belonging to the delivery point set in the delivery task; if they are consistent, the pick-up and placement result is determined to be correct; if not, the pick-up and placement result is determined to be incorrect. After the determination, the robot controls the head to perform anthropomorphic interaction actions corresponding to the pick-up and placement result to feedback the determination result to the user, facilitating the user to understand the intention conveyed by the robot and make timely responses, making the interaction performance of the robot more anthropomorphic and the human-machine interaction more friendly and vivid.

[0064] In a possible example, step S301 may include: after arriving at the delivery point, when it is detected that a delivery item that does not belong to the delivery point is picked up by a person, control the head to rotate left and right in the horizontal direction to perform anthropomorphic interaction actions representing negation; and / or,

[0065] When it is detected that a delivery item belonging to the delivery point is picked up by a person, control the head to rotate up and down in the vertical direction to perform anthropomorphic interaction actions representing affirmation (actions similar to a human nodding).

[0066] Among them, the angle of the head rotating left and right in the horizontal direction is within the first preset angle range; the angle of the head rotating up and down in the vertical direction is within the second preset angle range. The specific values of the first preset angle range and the second preset angle range can be set comprehensively according to the mechanical structure of the robot, and this application does not make any limitations here. For example, the first preset angle range is from 0 to 25°; the second preset angle range is from 0 to 45°. Correspondingly, the angle of the head rotating left and right in the horizontal direction can be a range of 0 to 25° for each left and right rotation, such as from 15 degrees or 25 degrees on the left side to 15 degrees or 25 degrees on the right side; 0° can represent that the head is in the middle state in the horizontal direction. The angle of the head rotating up and down in the vertical direction can be a range of 0 to 45° for each up and down rotation (pitch), such as from tilting the head up 25 degrees or 45 degrees to tilting the head down 25 degrees or 45 degrees; 0° can represent that the head is in the horizontal plane in the vertical direction.

[0067] In this way, through anthropomorphic interaction actions, the robot can clearly feedback to the user whether the pick-up and placement results are correct, reducing the user's understanding cost and eliminating the need to pre-understand the robot's intention / function expression configuration. This enables the user to clearly understand the intention conveyed by the robot and respond in a timely manner, such as putting back the wrongly picked item or continuing to pick up items, which helps the user pick up items correctly, improves the accuracy and efficiency of delivery, makes the robot's interaction performance more anthropomorphic, and makes the human-robot interaction more friendly and vivid.

[0068] Furthermore, the fuselage includes at least one storage layer for carrying delivery items. When it is detected that a delivery item not belonging to the delivery point is taken away, the head is controlled to turn left and right horizontally to perform an anthropomorphic interaction action representing negation (a movement similar to a human shaking the head), including:

[0069] After arriving at the delivery point, a cyclic judgment of the delivery items in each storage layer of the fuselage is started.

[0070] Here, after the robot arrives at the corresponding delivery point according to the delivery task, it can determine the delivery items belonging to the delivery point according to the delivery task and perform a cyclic judgment on the pick-up and placement of the delivery items in each storage layer of the fuselage. The starting time of this cyclic judgment can be when arriving at the delivery point, or when responding to the signal of the user opening the storage layer hatch of the robot, or when detecting a signal that a delivery item has been moved, etc.

[0071] During any round of judgment: a corresponding item label can be attached to the delivery item itself or the container carrying the delivery item. The robot can continuously detect the currently picked-up and placed delivery item by detecting the item label through a sensor, etc. Then, by comparing the currently picked-up and placed delivery item with the delivery items belonging to the delivery point, it can be determined whether the delivery item currently taken away by the user is the delivery item belonging to the delivery point, that is, whether the user has correctly taken away their own item.

[0072] On the one hand, if it is detected that a delivery item not belonging to the delivery point in each storage layer of the fuselage is taken away, and the situation where a delivery item not belonging to the delivery point is taken away appears for the first time during this round of cyclic judgment, the head is controlled to perform the anthropomorphic interaction action representing negation once.

[0073] Here, the robot continuously detects the delivery items placed in each storage layer of the fuselage. If it is detected that a delivery item not belonging to the current delivery point in each storage layer of the fuselage is taken away, and the situation where a delivery item not belonging to the current delivery point is taken away appears for the first time during this round of cyclic judgment, the head is controlled to turn left and right horizontally once.

[0074] Therefore, even if the user makes consecutive incorrect taking operations, the anthropomorphic interaction action representing negation will only be executed once during one round of cyclic judgment in the embodiments of the present application. This is because through practical research, it is found that the user's taking operations may occur multiple times within a short period, so the incorrect taking operations may also occur multiple times within a short period. However, the actions of the robot are relatively more lagging than those of humans. If the robot has to execute the anthropomorphic interaction action representing negation for each incorrect taking operation, it will not only consume the robot's power, accelerate the wear of the rotating components, but also easily cause the user's misunderstanding, thereby inducing new incorrect taking operations. Therefore, only executing the anthropomorphic interaction action representing negation once during one round of cyclic judgment can save the robot's power, extend the robot's lifespan, and more clearly convey the information of the taking and placing results.

[0075] On the other hand, if it is detected that the delivered items taken from each storage layer of the fuselage and not belonging to the delivery point are placed back into the storage layer where they originally belonged, this round of judgment is ended and the next round of judgment is started until it is determined that all the delivered items belonging to the delivery point have been taken away and all the delivered items not belonging to the delivery point are still all located in the storage layer, and then the cyclic judgment is ended.

[0076] Here, if it is detected that the delivered items taken from each storage layer of the fuselage and not belonging to the delivery point, that is, the delivered items that were previously taken away by the user incorrectly are placed back into the storage layer where they originally belonged, this round of judgment can be ended. At this time, the anthropomorphic interaction action representing affirmation can also be executed to give timely feedback to the user. Then the next round of judgment is started, that is, when a new incorrect taking operation occurs later, the robot can continue to execute the anthropomorphic interaction action representing negation.

[0077] Until the robot determines that all the delivered items belonging to the delivery point have been taken away and all the delivered items not belonging to the delivery point are still all located in the storage layer, that is, the user has correctly taken away all the delivered items belonging to the current delivery point and has not taken away any delivered items from other delivery points by mistake. At this time, the robot can determine that the delivery task at this delivery point can be ended and the cyclic judgment is ended. At this time, the anthropomorphic interaction action representing affirmation can also be executed once, or supplemented with voice prompts and screen animations. Then the robot can go from the current delivery point to the next delivery point, or go to other positions within the delivery area, such as the charging point or the item taking point, etc.

[0078] In this way, at the delivery point, by executing the anthropomorphic interaction actions corresponding to whether the taking and placing results of the delivered items are correct or incorrect, the robot can more clearly and accurately indicate to the user the feedback information on whether the items are correctly taken away and whether they are correctly placed back, facilitating the user to operate correctly and quickly according to the feedback information, improving the accuracy and efficiency of the delivery, making the interaction performance of the robot more anthropomorphic, and making the human-machine interaction more friendly and vivid.

[0079] Example 2:

[0080] The interaction method of the delivery robot provided in the embodiment of the present application includes:

[0081] S401. During the movement process, detect the surrounding environment and control the head to perform anthropomorphic interaction actions corresponding to the surrounding environment.

[0082] Here, the movement process includes the whole process of all autonomous movement behaviors of the robot in the working environment. For example, the movement process of the robot towards the delivery point, the movement process of the robot leaving the delivery point and moving to other positions, the movement process of the robot from the charging point to the item pickup point, etc.

[0083] In this step, during the movement process, the robot can detect the surrounding environment through its own sensors or by communicating with other robots, cloud platforms and other systems, and then control the head to perform anthropomorphic interaction actions corresponding to the detected surrounding environment. During the movement process, the detection of the surrounding environment may include: detecting the shape of the upcoming travel route, detecting whether the travel route is blocked by obstacles, and detecting whether it meets other robots, etc.

[0084] In this way, during the movement process, by performing anthropomorphic interaction actions corresponding to the surrounding environment, the robot can more clearly and accurately convey the information of the surrounding environment of the robot body to the user, reduce the user's understanding cost, eliminate the need to pre-understand the intention / function expression configuration of the robot, facilitate the user to understand the intention conveyed by the robot and make timely responses, improve the safety of the robot movement, make the interaction performance of the robot more anthropomorphic, and make the human-computer interaction more friendly and vivid.

[0085] Method 1: Please refer to Figure 2 , Figure 2 which is one of the schematic diagrams of an interaction method of a robot during the movement process provided in the embodiment of the present application. As shown in Figure 2 , the interaction method S401 provided in the embodiment of the present application may include:

[0086] S501. If it is detected that the upcoming travel route of the robot is curved, identify the degree of curvature of the travel route.

[0087] Here, the robot has pre-collected the data of the working area where the robot is located based on the acquisition sensors (such as lidar, ultrasonic sensors and infrared sensors) and planned a global route. The robot can plan a travel route from the global route according to the target position and the current position; the target position can be the delivery point or item pickup point set by the delivery task, or any position in the working area. Then, the robot will move towards the target position according to the travel route.

[0088] After planning the travel route, during the movement, the robot can compare the travel route in real time according to the detected current position of itself, and determine the upcoming travel route. For example, according to the current position of itself and the travel route, the route with a preset length that has not been moved from the current position can be determined as the upcoming travel route; or the route that will be moved within a preset time period in the future starting from the current moment can be determined as the upcoming travel route, etc., and then the shape of the upcoming travel route can be determined.

[0089] If it is detected that the upcoming travel route of the robot is curved, the degree of curvature of the travel route is recognized.

[0090] S502. If it is recognized that the degree of curvature of the travel route exceeds a preset threshold, control the head to horizontally turn to the curved direction of the curved shape to represent the anthropomorphic interaction action that the robot is about to turn.

[0091] If the robot recognizes that the degree of curvature of the travel route exceeds a preset threshold, it means that the degree of curvature of the route is large. At this time, control the head to horizontally turn to the curved direction of the curved shape, and after turning once, control the head to face the travel route again to represent the anthropomorphic interaction action that the robot is about to turn.

[0092] Among them, the angle of horizontal turning of the head can be a preset angle. The specific value of the preset angle here can be set comprehensively according to the mechanical structure of the robot. For example, the preset angle is within the angle range of 0 to 25°. Then, by way of example, the angle of horizontal turning of the head can be 15° or 25° to the left horizontally and 15° or 25° to the right horizontally. This application does not make any limitation here.

[0093] Alternatively, the angle of horizontal turning of the head can also be positively correlated with the degree of curvature of the travel route, such as setting the angle range of horizontal turning of the head. When the degree of curvature of the travel route is greater, the angle of horizontal turning of the head is greater and closer to the upper limit of the angle range. For example, the angle range is set from 0° to 25°. The greater the degree of curvature of the travel route, the closer the angle of horizontal turning of the head is to 25°, and the maximum is 25°; when the degree of curvature of the travel route is relatively small, the angle of horizontal turning of the head is closer to 0°.

[0094] At the same time, while controlling the head to horizontally turn to the curved direction of the curved shape, the fuselage can also be controlled to rotate synchronously with the head to make the steering visual effect of the robot more coordinated; and on the non-curved travel route, the fuselage of the robot can be kept consistent with the direction of the road section to make the visual effect of the straight-line movement of the robot more coordinated.

[0095] In a possible implementation, the travel route can be represented as coordinate data, and the degree of curvature can be expressed as the route curvature. During the process of the robot moving along the travel route, it continuously calculates the route curvature of the upcoming section. If the route curvature exceeds the preset threshold, it indicates that the route is highly curved and the forward direction of the section may change, such as a large S-shaped curve or a right-angle turn. At this time, the robot will control the head to horizontally turn in the bending direction of the curved shape to represent the anthropomorphic interaction action of the robot about to turn. In this way, nearby users can clearly understand the information that the robot is about to turn in a timely manner, clarify the turning intention of the robot, and thus make an avoidance in time to avoid colliding with the robot, improve the safety of the robot's movement, make the interaction performance of the robot more anthropomorphic, and make the human-robot interaction more friendly and vivid.

[0096] If the route curvature does not exceed the preset threshold, it indicates that the route is not highly curved and the forward direction of the section has not undergone an essential change that is considered by the general human vision, for example, it is considered to be a roughly straight-ahead direction. Such a curved shape may be a slightly winding section. On such a curved section, the robot will not control the head to turn horizontally to be consistent with the general direction of the section, while reducing unnecessary robot actions, saving power, and avoiding providing redundant interaction information to the user.

[0097] Please refer to Figure 3 , Figure 3 which is a schematic diagram of a travel route of a robot provided by an embodiment of the present application. As Figure 3 shown, although section a on the travel route shows a certain degree of curvature, the curvature of section a does not exceed the preset threshold and belongs to a slightly winding section, still belonging to a roughly straight-ahead direction. Therefore, on section a, the robot will not control the head to turn horizontally, and the robot is consistent with the general direction of the section; while for section b on the travel route, it is a right-angle turn, and its curvature exceeds the preset threshold, indicating that the forward direction of the route has changed. Therefore, on section b, the robot will control the head to turn horizontally in the bending direction of section b to express the turning intention of the robot.

[0098] In one example, the travel route that the robot is about to move forward can be detected to be curved in the following way:

[0099] Based on the real-time position of the robot and the coordinates of the curved area on the pre-calibrated travel route, it is determined that the travel route that the robot is about to move forward is curved.

[0100] In this step, the coordinates of the curved area are calibrated in the pre-planned global route; therefore, the coordinates of the curved area are also calibrated on the travel route planned based on the global route. The robot performs real-time self-positioning during operation. By comparing the positioning coordinates with the coordinates of the curved area calibrated on the travel route, it can be determined that the travel route that the robot is about to move forward is curved.

[0101] Among them, the curved region is pre-calibrated in the following manner:

[0102] Step 1: Plan a global route according to the global map of the delivery area and the fixed obstacles in the delivery area.

[0103] Specifically, the robot can be configured with a collection sensor and a modeling processor. The modeling processor builds a global map by modeling the environmental data collected by the collection sensor. In this embodiment, the collection sensor includes a lidar, an ultrasonic sensor, and an infrared sensor. The data of the working area where the robot is located is collected by the lidar, the ultrasonic sensor, and the infrared sensor. The modeling processor uses the data collected by these sensors to create a map. During the process of creating the map, different map layers are generated by different sensors, such as a static layer, a dynamic obstacle layer, an ultrasonic layer map, a vision layer, etc. By fusing these layers, a global map for positioning and navigating the robot is obtained. Then, according to the global map, the fixed obstacles in the delivery area can be determined, the area where the fixed obstacles are located is set as a no-go area, and a global route is planned; in this way, without the participation of dynamic obstacles in the planning, the interference of dynamic obstacles to the route can be excluded, which helps to filter out the real curved region, is not affected by local planning and replanning, and makes the route more stable.

[0104] Step 2: Determine the initial straight-line region and the initial turning region on the global route according to the coordinates of each position point on the global route.

[0105] In this step, the global route is sampled at a certain resolution to obtain the coordinates of each position point on the global route; then, according to the coordinate relationship between each position point, the initial straight-line region and the initial turning region on the global route are preliminarily determined. Further, the method of sampling at intervals in the grid can be used to determine the horizontal and vertical coordinates of each point. For example, if there are 10,000 points on the global route according to the grid, sampling can be performed at intervals, and 100 points in a certain grid are used as a position point. The horizontal and vertical coordinates of the position point are determined by methods such as taking the average value and selecting the center point. This sampling method at intervals can improve the robustness of the solution because if sampling is not performed at intervals, the route direction angles of adjacent position points are unstable.

[0106] In an example, Step 2 may include:

[0107] The first step: For each position point on the global route, select multiple adjacent position points of this position point from the global route.

[0108] In this step, a certain length range or quantity can be preset, and other position points within a certain length range of a certain position point on the global route are determined as the adjacent position points of this position point; or a certain number of other position points are selected from around this position point on the global route and determined as the adjacent position points of this position point.

[0109] Second step: According to the coordinates of this position point and multiple adjacent position points, determine the route direction angle corresponding to this position point.

[0110] Here, the route direction angle refers to the azimuth angle determined by using a certain coordinate axis direction as the standard direction, that is, the angle between the line connecting two position points and the coordinate axis. The setting of the coordinate axis in the embodiments of the present application is not restricted, because the embodiments of the present application focus on the change situation of the route direction angle, rather than the specific numerical value of a single direction angle.

[0111] In specific implementation, this position point and multiple adjacent position points are grouped into a set of position points according to their positions. According to the coordinates of the position points in the group, determine the route direction angle between every two position points; determine the average value of multiple route direction angles as the route direction angle corresponding to this position point. Preferably, the adjacent position points can include the position points in the two directions before and after this position point on the global route, so that the calculated route direction angle is more accurate; or, the adjacent position points can include more position points after this position point on the global route to achieve early identification of the turning area.

[0112] Third step: According to the route direction angles corresponding to multiple position points within each fixed length on the global route, screen out the initial straight area and the initial turning area.

[0113] In the embodiments of the present application, the route direction angle is an index of the change in the route orientation; according to the route direction angles corresponding to multiple position points, the average value and variance of the route direction angles can be determined. The coordinates, the average value of the route direction angles, and the variance can be used as labels of the position points for the data processing process of screening the initial straight area and the initial turning area. Exemplarily, the data information of a certain position point can be expressed as: position point A(x, y) - average value of the route direction angle - variance of the route direction angle.

[0114] In specific implementation, the global route is divided into multiple routes of a fixed length; according to the route direction angles corresponding to multiple position points within each fixed length, the variance of the route direction angle can be determined; then, the position points with a route direction angle variance greater than a certain threshold are screened out. A variance greater than a certain threshold indicates that the degree of dispersion of the average route direction angle of the position points in this area is very high, which can be regarded as a turn of the route on the route, so it can be identified as an initial turning area; if the variance is less than the threshold, it means that the degree of dispersion of the average route direction angle of the position points in this area is relatively low, which can be regarded as no turn of the route on the route, so it can be identified as an initial straight area.

[0115] Through the above method, the route direction angle of any position point is determined based on multiple adjacent position points of the position point, and then the straight area and the turning area are screened out through the route direction angles corresponding to multiple position points within each fixed length, which can improve the accuracy of screening the straight area and the turning area and avoid misjudging the type of the area due to errors in the coordinate detection of a certain position point.

[0116] Step 3: Filter the initial straight area and the initial turning area, and merge two areas of the same type and the connected connected area of another type between the two areas of the same type into one area of the same type to obtain the curved area on the global route.

[0117] Here, when a connected area of another type is connected between two areas of the same type and the length of the connected area is small, area merging can be performed to obtain one area of the same type. For example, the initial straight area, a small initial turning area, and the initial straight area are merged into a large straight area, or the initial turning area, a small initial straight area, and the initial turning area are merged into a large turning area. Furthermore, the curved area and the straight area on the global route are obtained. In the motion control of the robot, the curved area and the straight area are different. The differential control algorithm can be used for the robot in the curved area, and the servo steering can be used for the robot to avoid obstacles in the straight area. Therefore, through merging, it is possible to prevent the robot from frequently switching the motion mode and the planning algorithm during movement, and improve the stability of the robot's movement.

[0118] In this way, by detecting the shape of the route during movement and controlling the horizontal turning of the head in the direction of the curve of the route when it is judged that the degree of route curvature is large, an anthropomorphic interaction action indicating that the robot is about to turn is characterized, so that the user can clearly understand the information that the robot is about to turn in a timely manner, reducing the user's understanding cost, eliminating the need to pre-understand the robot's intention / function expression configuration, and thus making a timely avoidance to prevent collision with the robot, improving the safety of the robot's movement, making the interaction performance of the robot more anthropomorphic, and making the human-computer interaction more friendly and vivid.

[0119] Method 2: Please refer to Figure 4 , Figure 4 which is the second schematic diagram of an interaction method for a robot during movement provided by an embodiment of the present application. As Figure 3 shown, the interaction method S401 provided by an embodiment of the present application may include:

[0120] S601. If it is detected that the travel route of the robot is blocked by an obstacle, identify whether the obstacle is a human body.

[0121] During the movement of the robot, an obstacle may appear on the original travel route, blocking the original travel route, and the robot cannot bypass the obstacle. At this time, the robot enters a blocked state. Then, when the robot detects that the travel route is blocked by an obstacle, it identifies whether the obstacle is a human body. For example, the robot can read the video RGB stream through the image acquisition device installed on it and call the human body detection algorithm to identify whether the obstacle is a human body. Here, the human body detection algorithm can output a credibility value indicating that the obstacle is a human body; if this credibility value is greater than the preset human body detection threshold, it is determined that the obstacle is a human body; if this credibility value is less than the preset non-human body detection threshold, it is determined that the obstacle is not a human body; when this credibility value is between the preset human body detection threshold and the preset non-human body detection threshold, it is impossible to identify whether the obstacle is a human body.

[0122] S602. When it is identified that the obstacle is a human body, or when it is impossible to identify whether the obstacle is a human body, control the head to alternately perform actions of turning left and right in the horizontal direction and turning up and down in the vertical direction until the blocked state ends or the duration of the blocked state reaches a predetermined time length.

[0123] Among them, the angle of the head turning left and right in the horizontal direction is within a first preset angle range; the angle of the head turning up and down in the vertical direction is within a second preset angle range. The specific values of the first preset angle range and the second preset angle range can be set comprehensively according to the mechanical structure of the robot, and the present application does not make any limitation here. For example, the first preset angle range is from 0 to 25°; the second preset angle range is from 0 to 45°. Accordingly, the angle of the head turning left and right in the horizontal direction can be a range of turning left and right by 0 to 25° each, for example, turning from 15 degrees or 25 degrees on the left side to 15 degrees or 25 degrees on the right side; 0° can represent that the head is in the middle state in the horizontal direction. The angle of the head turning up and down in the vertical direction can be a range of turning up and down (pitching) by 0 to 45° each, for example, turning from tilting the head up by 25 degrees or 45 degrees to tilting the head down by 25 degrees or 45 degrees; 0° can represent that the head is in the horizontal plane in the vertical direction.

[0124] In one example, when the obstacle is recognized as a human body, first, the robot controls the head to turn 20 degrees to the left from the horizontal direction of 0 degrees, then turn 20 degrees to the right, and finally return to the horizontal direction of 0 degrees, completing a left - right rotation along the horizontal direction (i.e., turning the head left and right once, similar to a human looking around left and right once); second, the robot controls the head to turn up 30 degrees from the vertical direction of 0 degrees, then turn down 30 degrees, and finally return to the vertical direction of 0 degrees, completing an up - down rotation along the vertical direction (i.e., pitching the head up and down once, similar to a human looking up and down once); after that, the robot controls the head to alternately perform left - right rotation along the horizontal direction and up - down rotation along the vertical direction in the same way.

[0125] Here, when the obstacle is recognized as a human body or it is impossible to recognize whether the obstacle is a human body, controlling the head to alternately perform left - right rotation along the horizontal direction and up - down rotation along the vertical direction can execute anthropomorphic interaction actions for seeking help, simulating the actions of a human looking around for help, so as to remind the user to pay attention to avoiding when the obstacle is a person or may be a person. The robot will continue this action for a certain period of time. If within the predetermined time period, the state of the robot being blocked by the obstacle ends, the robot can stop this action and continue to drive along the original travel route; if the duration of the state of being blocked by the obstacle reaches the predetermined time period and it is determined that the obstacle cannot be moved, the robot can also stop this action and re - plan the route.

[0126] Furthermore, the interaction method further includes:

[0127] S603. When it is recognized that the obstacle is not a human body, control the head to turn left and right along the horizontal direction, and determine whether there is anyone around the body of the robot. If it is determined that there is someone around the body of the robot, control the head to turn towards the direction where the person is located to execute anthropomorphic interaction actions for seeking help.

[0128] Here, if it is recognized that the obstacle is not a human body, control the head to turn left and right along the horizontal direction, and the presence of people around the body of the robot can be determined through the image data collected during the rotation process; if it is determined that there is someone around the body of the robot, control the head to turn towards the direction where the person is located to execute anthropomorphic interaction actions for seeking help, such as controlling the head to turn slightly left and right along the horizontal direction and turn slightly up and down along the vertical direction, etc., and voice, text, and anthropomorphic expression prompts can be coordinated.

[0129] In this way, when the moving route of the robot is blocked by an obstacle, if the obstacle is recognized as a human body or may be a human body, the anthropomorphic interaction actions can prompt the user to avoid in time; if the obstacle is recognized as not a human body, the anthropomorphic interaction actions can seek help from other users around, so that the users can help to move the obstacle away. Such anthropomorphic interaction actions can reduce the user's understanding cost, eliminate the need to pre-understand the intention / function expression configuration of the robot, facilitate the user to understand the intention conveyed by the robot, enable the user to make a timely response, improve the efficiency and safety of the robot's movement, make the interaction performance of the robot more anthropomorphic, and make the human-computer interaction more friendly and vivid.

[0130] Method 3: The interaction method S401 of the robot during movement provided by the embodiment of the present application may further include:

[0131] If it is detected that the robot meets another robot, control the rotation angle of the head in the horizontal direction to track the direction where the other robot is located; when it is detected that the heads of the two robots are facing each other, control the head to rotate up and down in the vertical direction.

[0132] In this step, when it is detected that the robot meets another robot, control the head to rotate in the horizontal direction, and the rotation angle is adjusted in real time according to the real-time positions of the two robots that meet, so as to achieve the effect of tracking the direction where the other robot is located; when it is detected that the heads of the two robots are facing each other, control the head to rotate up and down in the vertical direction, which can simulate the actions when humans meet and greet, and enhance the perception of the robot's natural and vivid interaction.

[0133] It should be noted that during the movement of the robot, the above three interaction methods can be used separately or in combination with each other.

[0134] Embodiment 3:

[0135] Furthermore, an operation screen is also installed on the head of the robot; the rotation of the head drives the operation screen to rotate together, and the operation screen is similar to the face of the robot; the operation screen can provide a human-computer interaction interface for the user to interact with the robot; the user can issue commands to the robot by triggering the controls displayed on the operation screen, and the robot can display content to the user through the operation screen.

[0136] On this basis, the interaction method of the delivery robot provided by the embodiment of the present application further includes:

[0137] When the user interacts with the operation screen or in the welcome state, control the rotation angle of the head in the vertical direction according to the detected height of the user to adjust the tilt angle of the operation screen; after receiving the start instruction of the delivery task triggered by the user through the operation screen, control the head to rotate in the vertical direction to adjust the operation screen to a first preset angle in the vertical direction, and control the operation screen to display the display content related to the delivery task.

[0138] Here, in the welcome state, the robot can actively conduct welcome inquiries according to the recognized human body, adjust the welcome route and follow the human body. Default operation angles in the operation state and welcome state can be preset for the robot according to usage requirements (such as looking up at 0°, looking straight ahead at 15°, and the default at 45°); when the robot detects that the user is interacting with the operation screen or the robot is in the welcome state, it can control the rotation angle of the head in the vertical direction according to the detected height of the user to adjust the tilt angle of the operation screen, ensuring that users of different heights can conveniently interact with the operation screen, thereby improving the interaction convenience for users of different heights. In addition, during the interaction between the user and the operation screen, the robot can also recognize the face and track the direction of the face, so that the operation screen is always facing the face directly, facilitating the user's operation.

[0139] After receiving the start instruction of the delivery task triggered by the user through the operation screen, the robot switches from the operation state to the moving state and will move to the target point. At this time, the control head rotates in the vertical direction to adjust the operation screen to the first preset angle in the vertical direction; at the same time, the operation screen can also be controlled to display the display content related to the delivery task, including at least one of the following items: delivery task status, delivered items, delivery points, and anthropomorphic dynamic expressions. Here, the first preset angle can be the angle that makes the operation screen change from the tilted state to a state closer to the vertical state compared with when interacting with the user or in the welcome state; that is, after receiving the start instruction of the delivery task, the robot can control the head to rotate in the vertical direction, so as to adjust the operation screen to be closer to the vertical direction, or can also be directly adjusted to the vertical direction. This is because after receiving the start instruction, the robot should start moving to transport the delivered items to the delivery point. In this way, adjusting the operation screen can show the state of the robot walking upright, and at the same time, displaying the display content related to the delivery task can prompt the robot to execute the delivery task and move soon, enabling the surrounding users to perceive the moving intention of the robot in time and avoid it, improving the safety of the robot's movement and the delivery efficiency; and during the execution of the delivery task, the robot controls the operation screen to maintain the first preset angle, so as to facilitate seeing the state of the robot clearly at medium and long distances in the delivery scenario, helping users to perceive and avoid in time. Among them, the specific value of the first preset angle can be set according to the delivery scenario. For example, the first preset angle is within the angle range of 0 to 15°, and can be 0°, 5°, 10°, 15°, etc. The present application does not make any limitation here.

[0140] Furthermore, the interaction method of the delivery robot provided by the embodiments of the present application further includes:

[0141] When the running state of the robot is the standby state, control the head to rotate in the vertical direction to adjust the operation screen to the second preset angle in the vertical direction; when the robot reaches the delivery point, control the head to rotate in the vertical direction to adjust the operation screen to the third preset angle in the vertical direction; wherein, the first preset angle is less than the second preset angle and greater than the third preset angle.

[0142] Here, when the robot is not set to a specific working state (such as the greeting state), and there is no user interacting with the robot's operation screen, or the robot is waiting for a delivery task, or the robot has just completed a delivery task and returned to the set position and has not received a new delivery task, etc., the robot can be in a standby state to save power. When the running state of the robot is the standby state, the head of the robot control rotates along the vertical direction to adjust the operation screen to a second preset angle in the vertical direction; the second preset angle can be a default convenient operation angle. For example, the second preset angle can be 20° with respect to the vertical direction, which can facilitate the user to interact with the operation screen at any time. The specific value of the second preset angle can be set according to the delivery scenario. For example, the second preset angle is within the angle range of 0 to 20°, and can be 0°, 15°, 20°, etc. This application does not make any limitation here.

[0143] After that, the robot receives a start instruction for a delivery task triggered by the user through the operation screen and starts to execute the delivery task. As described above, at this time, the robot can control the head to rotate along the vertical direction to adjust the operation screen to a first preset angle in the vertical direction, so as to adjust the operation screen to be closer to the vertical direction, or directly adjust it to the vertical direction, to show the state of the robot walking upright. That is, the first preset angle should be less than the second preset angle.

[0144] After that, the robot responds to the start instruction and starts to execute the delivery task. During the movement of executing the delivery task, the operation screen of the robot is controlled to remain unchanged at the first preset angle in the vertical direction until the robot reaches the delivery point. During the movement, the surrounding environment can be detected according to the description in the second embodiment above and the head is controlled to perform anthropomorphic interaction actions corresponding to the surrounding environment, and after the execution is completed, the operation screen of the robot is re-controlled to remain unchanged at the first preset angle in the vertical direction.

[0145] When reaching the delivery point, the robot can control the head to rotate along the vertical direction to adjust the operation screen to a third preset angle in the vertical direction, that is, compared with the movement process of executing the delivery task, the operation screen is adjusted to be closer to the vertical direction, that is, the first preset angle should be greater than the third preset angle. The specific value of the third preset angle can be set according to the delivery scenario. For example, the third preset angle is within the angle range of 0 to 5°, and can be 0°, 1°, 3°, 5°, etc. This application does not make any limitation here.

[0146] In this way, when the robot arrives at the delivery point, it controls its head to rotate vertically, showing an action similar to a human nodding, which can better attract the user's attention and more clearly convey the intention of prompting the user to pick up the item. On the other hand, the present application finds that in some specific delivery scenarios, such as in a restaurant, where the delivery point is next to a certain table in the restaurant and the user is generally sitting on a chair waiting for the delivered item. The robot may be provided with multiple layers of storage layers to improve the delivery efficiency, making the height of the robot higher relative to the sitting user. Therefore, by controlling the head to rotate vertically, the operation screen is adjusted to a third preset angle closer to the vertical in the vertical direction, so that the sitting user can more clearly observe the information displayed on the operation screen and more conveniently interact with the operation screen.

[0147] Further, the interaction method of the delivery robot provided in the embodiments of the present application further includes:

[0148] When the current user is having a voice interaction with the operation screen, it is detected that there is a voice inquiry message sent by another user within a predetermined space range; after completing the voice interaction with the current user, the head is controlled to turn to the direction where the other user is located and continue the voice interaction with the other user.

[0149] Here, there are occasions where the robot interacts with multiple users simultaneously. For example, when the current user is having a voice interaction with the operation screen, the robot detects that there is a voice inquiry message sent by another user within a predetermined space range (such as within 360° and 1 meter), and the orientation of the other user can be determined based on the voice inquiry message; at this time, the robot will first complete the voice interaction with the current user, and then control the head to turn to the direction where the other user is located and continue the voice interaction with the other user. After turning, the robot can also readjust the angle of the operation screen according to the height of the other user with whom it is interacting.

[0150] In this way, in the scenario of multi-user interaction, the robot can ensure the integrity of the interaction with the current user and take into account the interaction needs of more users.

[0151] It should be noted that in the interaction method of the robot provided in the embodiments of the present application, the above embodiments can be used separately or in combination with each other.

[0152] An interaction method for a robot provided by an embodiment of the present application. The robot includes a head and a fuselage; the head is rotatably connected to the fuselage; the robot performs various anthropomorphic interaction actions by controlling the head to rotate in multiple directions; the robot is used to transport delivery items to a delivery point. The interaction method includes: after arriving at the delivery point, detecting the pick-up and placement result of the delivery item and controlling the head to perform an anthropomorphic interaction action corresponding to the pick-up and placement result; and / or, during the movement process, detecting the surrounding environment and controlling the head to perform an anthropomorphic interaction action corresponding to the surrounding environment.

[0153] In this way, it can solve the problem that the interaction intention of the robot in the prior art is difficult to be understood by the user, achieve more clearly and accurately conveying information to the user, reduce the user's understanding cost, eliminate the need to pre-understand the intention / function expression configuration of the robot, facilitate the user to understand the intention conveyed by the robot and make a timely response, thereby improving the accuracy and efficiency of delivery and the safety of the robot's movement, making the interaction performance of the robot more anthropomorphic and the human-computer interaction more friendly and vivid.

[0154] Based on the same inventive concept, an interaction device for a robot is also provided in an embodiment of the present application. Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of an interaction device for a robot provided by an embodiment of the present application. The robot includes a head and a fuselage; the head is rotatably connected to the fuselage; the robot performs various anthropomorphic interaction actions by controlling the head to rotate in multiple directions; the robot is used to transport delivery items to a delivery point. As shown in Figure 5 , the interaction device 400 includes:

[0155] A first interaction module 410, configured to detect the pick-up and placement result of the delivery item after arriving at the delivery point and control the head to perform an anthropomorphic interaction action corresponding to the pick-up and placement result; and / or,

[0156] A second interaction module 420, configured to detect the surrounding environment during the movement to or from the delivery point and control the head to perform an anthropomorphic interaction action corresponding to the surrounding environment.

[0157] It should be noted that the specific implementation manner of the device can be referred to the method embodiment. Since the principle of solving problems by the interaction device in the embodiment of the present application is similar to the above interaction method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0158] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As shown in Figure 6As shown in the figure, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.

[0159] The memory 520 stores machine-readable instructions executable by the processor 510. When the electronic device 500 runs, the processor 510 communicates with the memory 520 via the bus 530. When the machine-readable instructions are executed by the processor 510, they can perform the steps of an interaction method of a robot as described in the above Figure 2 and Figure 4 shown method embodiments. For the specific implementation manners, reference may be made to the method embodiments and will not be elaborated herein.

[0160] The embodiments of the present application further provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, it can perform the steps of an interaction method of a robot as described in the above Figure 2 and Figure 4 shown method embodiments. For the specific implementation manners, reference may be made to the method embodiments and will not be elaborated herein.

[0161] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0162] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division manners in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed with each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0163] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0165] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0166] Finally, it should be noted that the above-mentioned embodiments are only specific implementation manners of this application, used to illustrate the technical solutions of this application, rather than limiting them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed in this application can still modify the technical solutions recorded in the foregoing embodiments or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An interaction method for a robot, characterized in that, the robot includes a head and a fuselage; the head is rotatably connected to the fuselage; the robot performs various anthropomorphic interaction actions by controlling the head to rotate in multiple directions; the robot is used to transport delivery items to a delivery point; the interaction method includes: after arriving at the delivery point, detecting the pick-up and drop-off result of the delivery item and controlling the head to perform an anthropomorphic interaction action corresponding to the pick-up and drop-off result; and / or, during the movement, detecting the surrounding environment and controlling the head to perform an anthropomorphic interaction action corresponding to the surrounding environment.

2. The interaction method according to claim 1, characterized in that, the step of, after arriving at the delivery point, detecting the pick-up and drop-off result of the delivery item and controlling the head to perform an anthropomorphic interaction action corresponding to the pick-up and drop-off result, includes: after arriving at the delivery point, when it is detected that a delivery item that does not belong to the delivery point is taken away by a person, controlling the head to rotate left and right in the horizontal direction to perform an anthropomorphic interaction action representing negation; and / or, when it is detected that a delivery item that belongs to the delivery point is taken away by a person, controlling the head to rotate up and down in the vertical direction to perform an anthropomorphic interaction action representing affirmation; wherein, the angle of the head rotating left and right in the horizontal direction is within a first preset angle range; the angle of the head rotating up and down in the vertical direction is within a second preset angle range; the first preset angle range is from 0 to 25°; the second preset angle range is from 0 to 45°.

3. The interaction method according to claim 2, characterized in that, the fuselage includes at least one storage layer for carrying delivery items; the step of, when it is detected that a delivery item that does not belong to the delivery point is taken away, controlling the head to rotate left and right in the horizontal direction to perform an anthropomorphic interaction action representing negation, includes: after arriving at the delivery point, starting a cyclic judgment on the delivery items in each storage layer of the fuselage; during any round of judgment, if it is detected that a delivery item that does not belong to the delivery point in each storage layer of the fuselage is taken away, and the situation of the delivery item that does not belong to the delivery point being taken away appears for the first time during this round of cyclic judgment, controlling the head to perform the anthropomorphic interaction action representing negation once; if it is detected that the taken-away delivery item that does not belong to the delivery point in each storage layer of the fuselage is put back into the original storage layer to which it belongs, ending this round of judgment and starting the next round of judgment until it is determined that all the delivery items belonging to the delivery point are taken away and all the delivery items that do not belong to the delivery point are still located in the storage layer, ending the cyclic judgment.

4. The interaction method according to claim 1, characterized in that, the step of, during the movement, detecting the surrounding environment and controlling the head to perform an anthropomorphic interaction action corresponding to the surrounding environment, includes: if it is detected that the travel route that the robot is about to move forward is curved, identifying the degree of curvature of the travel route; If it is recognized that the degree of curvature of the traveling route exceeds a preset threshold, then control the head to horizontally turn towards the bending direction of the curved shape to represent an anthropomorphic interaction action that the robot is about to turn; wherein, the angle of the horizontal turn of the head is a preset angle or is positively correlated with the degree of curvature of the traveling route; the preset angle is within the angular range of 0 to 25°.

5. The interaction method according to claim 4, wherein, the curved shape of the traveling route that the robot is about to move forward is detected in the following manner: Determine that the traveling route that is about to move forward is curved according to the real-time position of the robot and the coordinates of the curved area on the pre-calibrated traveling route; wherein, the curved area is pre-calibrated in the following manner: Plan a global route according to the global map of the delivery area and the fixed obstacles in the delivery area; Determine the initial straight area and the initial turning area on the global route according to the coordinates of each position point on the global route; Filter the initial straight area and the initial turning area, and merge two areas of the same type and a connected area of another type between two areas of the same type into one area of the same type to obtain the curved area on the global route.

6. The interaction method according to claim 5, wherein, the determining the initial straight area and the initial turning area on the global route according to the coordinates of each position point on the global route includes: For each position point on the global route, select multiple adjacent position points of this position point from the global route; Determine the route direction angle corresponding to this position point according to the coordinates of this position point and multiple adjacent position points; Filter out the initial straight area and the initial turning area according to the route direction angles corresponding to multiple position points within each fixed length on the global route.

7. The interaction method according to claim 1, wherein, the detecting the surrounding environment during movement and controlling the head to perform anthropomorphic interaction actions corresponding to the surrounding environment includes: If it is detected that the traveling route of the robot is blocked by an obstacle, then identify whether the obstacle is a human body; When it is recognized that the obstacle is a human body, or when it is impossible to identify whether the obstacle is a human body, control the head to alternately perform actions of turning left and right in the horizontal direction and turning up and down in the vertical direction until the state of being blocked by the obstacle ends or the duration of the state of being blocked by the obstacle reaches a preset time length; wherein, the angle of the head turning left and right in the horizontal direction is within a first preset angle range; the angle of the head turning up and down in the vertical direction is within a second preset angle range; the first preset angle range is 0 to 25°; the second preset angle range is 0 to 45°.

8. The interaction method according to claim 7, wherein, the detecting the surrounding environment during movement and controlling the head to perform anthropomorphic interaction actions corresponding to the surrounding environment further includes: When it is recognized that the obstacle is not a human body, control the head to turn left and right in the horizontal direction, and determine whether there is anyone around the body of the robot; If it is determined that there is someone around the body of the robot, control the head to turn towards the direction where the person is located to perform anthropomorphic interaction actions for soliciting help.

9. The interaction method according to claim 1, characterized in that, an operation screen is installed on the head; the interaction method further includes: When the user interacts with the operation screen or in the welcome state, control the rotation angle of the head in the vertical direction according to the detected height of the user to adjust the tilt angle of the operation screen; After receiving the start instruction of the delivery task triggered by the user through the operation screen, control the head to rotate in the vertical direction to adjust the operation screen to a first preset angle in the vertical direction, and control the operation screen to display display content related to the delivery task; the display content includes at least one of the following: delivery task status, delivery items, delivery points, and anthropomorphic dynamic expressions.

10. The interaction method according to claim 9, the interaction method further includes: When the running state of the robot is the standby state, control the head to rotate in the vertical direction to adjust the operation screen to a second preset angle in the vertical direction; When the robot arrives at the delivery point, control the head to rotate in the vertical direction to adjust the operation screen to a third preset angle in the vertical direction; wherein, the first preset angle is less than the second preset angle and greater than the third preset angle; the first preset angle is within the angular range of 0 to 15°; the second preset angle is within the angular range of 0 to 20°; the third preset angle is within the angular range of 0 to 5°.

11. The interaction method according to claim 9, characterized in that, the interaction method further includes: When the current user is having a voice interaction with the operation screen, it is detected that there is a voice inquiry message sent by another user within a predetermined space range; After completing the voice interaction with the current user, control the head to turn towards the direction where the other user is located and continue the voice interaction with the other user.

12. An interaction device of a robot, characterized in that, the robot includes a head and a body; the head is rotationally connected to the body; the robot performs various anthropomorphic interaction actions by controlling the head to rotate in multiple directions; the robot is used to transport delivery items to the delivery point; the interaction device includes: A first interaction module, configured to detect the pick-up and placement result of the delivery item after arriving at the delivery point and control the head to perform anthropomorphic interaction actions corresponding to the pick-up and placement result; and / or, A second interaction module, configured to detect the surrounding environment during the movement to or from the delivery point and control the head to perform anthropomorphic interaction actions corresponding to the surrounding environment.

13. An electronic device, characterized in that, includes: A processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device operates, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of an interaction method of a robot as described in any one of claims 1 to 11 are performed.

Images