Feedback method of robot and robot

Abstract

The embodiment of the application provides a feedback method of a robot and the robot, relates to the technical field of robots, and can improve the humanization degree of the robot. Wherein, the robot is provided with an IMU, and a plurality of first preset areas on the inner side of the shell of the robot are provided with touch sensors, the touch sensors are used for collecting operations acting on the robot, and the IMU is used for collecting the heading angle of the robot. The robot can receive a first operation acting on a first area, the first area being any area in the plurality of first preset areas. And the robot can obtain position information of the first area, an operation type of the first operation and a first offset, the first offset being used for reflecting the force of the first operation acting on the robot. Then, in response to the first operation, the robot can execute a first control event corresponding to the position information of the first area, the operation type of the first operation and the force of the first operation acting on the robot.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of robots, and in particular, to a feedback method of a robot. BACKGROUND

[0002] With the development of technology, the degree of personification of intelligent robots is getting higher and higher. A user can issue an instruction to an intelligent robot through voice, action (for example, tapping, continuous tapping, long pressing), and the like, so that the intelligent robot executes a control event corresponding to the instruction. For example, the user can input an operation (for example, long pressing) at any part (for example, a palm) of the intelligent robot. After receiving the long pressing operation input by the user at the palm part, the intelligent robot can execute an event of shaking hands with the user.

[0003] At present, the intelligent robot can receive and identify the operation input by the user through a touch sensor. For example, the intelligent robot can identify the operation input by the user as a long pressing operation through the touch sensor. For another example, the intelligent robot can identify the operation input by the user as a tapping operation through the touch sensor.

[0004] However, there are many external factors that affect the personification of intelligent robots. With the increasing requirement for the degree of personification of intelligent robots, the intelligent robot can no longer accurately make corresponding feedback by only identifying the operation type of the operation through the touch sensor. SUMMARY

[0005] The present application provides a feedback method of a robot, which can combine various external factors affecting the personification of the robot to accurately execute corresponding control events and improve the degree of personification of the robot.

[0006] In a first aspect, the present application provides a feedback method of a robot, which can be applied to a robot. The robot is installed with an inertial measurement unit (IMU). A plurality of first preset areas on the inner side of the shell of the robot are each provided with a touch sensor. The touch sensor is used to collect an operation acting on the robot. The IMU is used to collect a heading angle of the robot.

[0007] In the method, the robot can receive a first operation acting on a first area, the first area being any of the plurality of first preset areas. In addition, the robot can obtain position information of the first area, an operation type of the first operation, and a first offset. The first offset is used to indicate an offset of the heading angle of the robot after the robot receives the first operation. The first offset is used to reflect the force of the first operation acting on the robot.

[0008] Generally, when the force of the operation acting on the robot is too large, the robot can vibrate (or shake); when the force of the operation acting on the robot is small, the robot does not vibrate. When the robot vibrates, the heading angle of the robot changes. Therefore, the amount of deviation of the heading angle of the robot can reflect the force of the operation acting on the robot.

[0009] After receiving the first operation, the robot can perform a first control event corresponding to the position information of the first region, the operation type of the first operation, and the force of the first operation acting on the robot.

[0010] Based on the above scheme, after receiving the first operation acting on the robot, the robot can obtain the position information of the first region, the operation type of the first operation, and the amount of deviation of the heading angle of the robot after receiving the first operation (i.e., the first deviation). The first deviation can reflect the force of the first operation acting on the robot. In this way, the robot can execute a corresponding control event according to the position information of the first region, the operation type of the first operation, and the operation force of the first operation. Therefore, in the embodiments of the present application, the robot can combine various external factors (the region of the operation, the operation type of the operation, and the force of the operation) to accurately execute the corresponding control event, and improve the degree of humanization of the robot.

[0011] For example, the first operation received by the robot is a tapping operation, and the tapping operation acts on the head region of the robot. Moreover, the force of the tapping operation is large, causing the robot to vibrate. In response to the tapping operation, the robot can execute the operation of covering the head region with hands and emit the sound of “ouch!”.

[0012] In combination with the first aspect, in a possible design manner, the method further includes that the robot can obtain a first heading angle and a first initial heading angle. The first heading angle is the heading angle of the robot after receiving the first operation, and the first initial heading angle is the heading angle of the robot before receiving the first operation. Then, the robot can calculate the difference between the first heading angle and the first initial heading angle to obtain the first deviation.

[0013] For example, the heading angle of the robot (i.e., the first initial heading angle) before the robot receives the first operation (e.g., a tapping operation) is A. After the robot receives the tapping operation, the heading angle of the robot (i.e., the first heading angle) is B. Then, the first deviation is B-A.

[0014] It should be noted that if the first offset is 0, it indicates that the first heading angle of the robot is the same as the first initial heading angle, that is, the heading angle of the robot does not change. In this way, it can be determined that the robot does not vibrate, and the operation degree of the operation is small. If the first offset is not 0, it indicates that the first heading angle of the robot is different from the first initial heading angle, that is, the heading angle of the robot changes. In this way, it can be determined that the robot vibrates, and the operation degree of the operation is large.

[0015] In this way, in the method provided in the application, the robot can execute the corresponding control event according to the operation degree, thereby improving the humanization degree of the robot.

[0016] In combination with the first aspect, in another possible design, the head of the robot and / or the chest of the robot is installed with an IMU.

[0017] It should be noted that when the robot vibrates, the center of gravity of the robot will certainly vibrate with the robot. Therefore, the change amount of the heading angle of the center of gravity of the robot is the change amount of the heading angle of the robot. Generally, the position of the center of gravity of the robot is usually the head of the robot and / or the chest of the robot. Therefore, the head of the robot and / or the chest of the robot can be installed with an IMU. In this way, when the robot receives an operation with too large a degree, the center of gravity (for example, the head and / or the chest) of the robot will vibrate, and the IMU installed on the head and / or the chest can obtain the change amount of the heading angle of the center of gravity of the robot, that is, the change amount of the heading angle of the robot.

[0018] In combination with the first aspect, in another possible design, if the first offset is greater than a preset offset threshold, the first operation is a heavy operation; if the first offset is less than the preset offset threshold, the first operation is a light operation; the degree corresponding to the heavy operation is greater than the degree corresponding to the light operation.

[0019] For example, assuming that the preset offset threshold is 0. The robot is in a static state when it does not receive the first operation, and the robot can collect an initial heading angle a through the IMU; after the robot receives the first operation, the robot can collect a first heading angle b through the IMU. Wherein, if a and b are not the same (that is, the first initial heading angle is not the same as the first heading angle), the robot can determine that the first operation is a heavy operation. If a and b are the same (that is, the first initial heading angle is equal to the first heading angle), the robot can determine that the first operation is a light operation.

[0020] In this way, the robot can execute the corresponding control event according to the operation with different degrees (heavy operation or light operation), thereby improving the humanization degree of the robot.

[0021] With reference to the first aspect, in a possible design, the plurality of first preset areas inside the shell of the robot correspond to the plurality of second preset areas on the surface of the shell of the robot one by one. The plurality of second preset areas are areas on the surface of the shell of the robot that are operated by the user more frequently than a preset frequency threshold.

[0022] That is, the area where the touch sensor is arranged can be an area corresponding to an area on the surface of the shell of the robot that is operated by the user more frequently. In this way, arranging the touch sensor only in the first preset area corresponding to the second preset area can reduce the number of touch sensors arranged on the robot. In this way, the cost can be reduced while ensuring the user experience of interacting with the robot.

[0023] With reference to the first aspect, in a possible design, the robot further includes a camera configured to capture images. The method further includes: in response to the first operation, if the robot captures portrait information, the robot determines that the first control event is a control event triggered by a human.

[0024] With reference to the first aspect, in a possible design, the portrait information includes a face image and a portrait distance, where the portrait distance is used to indicate the distance between the robot and the user. The method that "if the robot captures portrait information, the robot determines that the first control event is a control event triggered by a human" includes: if the robot captures portrait information and the portrait distance is less than a preset distance threshold, the robot determines that the first control event is a control event triggered by a human.

[0025] For example, assuming that the preset distance threshold is 1 meter. In response to a knocking operation, the robot can capture a face image. If the portrait distance is 0.5 meters, the robot can determine that the knocking operation is a human knocking operation.

[0026] Based on the above technical solution, the robot can further determine whether the first control event is a control event triggered by a human according to the distance between the robot and the user. In this way, the accuracy of the robot in executing the corresponding control event can be further improved, and the humanization of the robot is improved.

[0027] With reference to the first aspect, in a possible design, the method further includes: if the robot captures portrait information but the portrait distance is greater than the preset distance threshold, the robot determines that the first control event is a control event not triggered by a human; or if the robot does not capture portrait information, the robot determines that the first control event is a control event not triggered by a human.

[0028] For example, assuming that the preset distance threshold is 1 meter. If the portrait distance is 3 meters, the robot can determine that the knocking operation is an accidental hitting event, for example, the robot is hit by an object (for example, a stone), the robot collides with an object, and the like.

[0029] With reference to the first aspect, in another possible design, the method further includes: if the robot receives a second operation acting on a second region after a preset time length after receiving the first operation, the second region being any region in the plurality of first preset regions. Then, the robot can obtain position information of the second region, an operation type of the second operation, and a second offset; the second offset being a difference between a second heading angle of the robot and a second initial heading angle of the robot, the second heading angle being a heading angle of the robot after the robot receives the second operation, the second initial heading angle being a heading angle of the robot before the robot receives the second operation, and the second offset being used to reflect a force of the second operation acting on the robot. In response to the second operation, the robot can perform a second control event corresponding to the position information of the second region, the operation type of the second operation, and the force of the second operation acting on the robot.

[0030] It can be understood that when the interval time length of the first operation and the second operation is greater than the preset time length, the robot can divide the first operation and the second operation into two touch events, and perform different control events. In this way, the robot can perform more control events, and the robot's humanization degree is improved.

[0031] With reference to the first aspect, in another possible design, the method further includes: if the robot receives a second operation acting on a second region within a preset time length after receiving the first operation. Then, the robot can obtain position information of the second region, an operation type of the second operation, and a second offset. In response to the first operation and the second operation, the robot can perform a third control event corresponding to the position information of the first region, the operation type of the first operation, and the force of the first operation acting on the robot, the position information of the second region, the operation type of the second operation, and the force of the second operation acting on the robot.

[0032] That is, in response to the first operation and the second operation, the robot can perform one control event (i.e., the third control event). In this way, the robot can feed back a control event for a combination of multiple operations, and the robot's humanization degree is improved.

[0033] With reference to the first aspect, in another possible design, the touch sensor includes a copper sheet.

[0034] It can be understood that the copper sheet is relatively soft, and the shell of the robot is curved. Therefore, the touch sensor can be well attached to the inner side of the shell of the robot. In this way, the touch sensitivity of the robot can be increased, and the humanization degree of the robot can be improved. Moreover, the cost can be reduced.

[0035] In a second aspect, the present application provides a robot, comprising: an inertial measurement unit (IMU), a memory and one or more processors, a plurality of first preset areas on the inner side of the shell of the robot are each provided with a touch sensor, the IMU, the touch sensor, the memory and the processor are coupled; the touch sensor is configured to collect an operation acting on the robot, and the IMU is configured to collect a heading angle of the robot; the memory is configured to store computer program code, the computer program code comprising computer instructions; when the computer instructions are executed by the processor, the robot performs the method according to the first aspect and any possible design manner thereof.

[0036] In a third aspect, the present application provides a chip system applied to a robot. The chip system comprises one or more interface circuits and one or more processors. The interface circuit and the processor are interconnected through a circuit. The interface circuit is configured to receive a signal from a memory of the robot and send the signal to the processor, the signal comprising computer instructions stored in the memory. When the processor executes the computer instructions, the robot performs the method according to the first aspect and any possible design manner thereof.

[0037] In a fourth aspect, the present application provides a computer storage medium comprising computer instructions, when the computer instructions are run on a robot, the robot performs the method according to the first aspect and any possible design manner thereof.

[0038] In a fifth aspect, the present application provides a computer program product, when the computer program product is run on a computer, the computer performs the method according to the first aspect and any possible design manner thereof.

[0039] It can be understood that the robot according to the second aspect and any possible design manner thereof, the chip system according to the third aspect, the computer storage medium according to the fourth aspect, and the computer program product according to the fifth aspect can achieve the beneficial effects as described in the first aspect and any possible design manner thereof, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1A A structural schematic diagram of a touch sensor provided by an embodiment of the present application;

[0041] Figure 1BAnother structural diagram of a touch sensor provided by the embodiment of the present application;

[0042] Figure 2A A structural diagram of a system architecture applied by a feedback method of a robot provided by the embodiment of the present application;

[0043] Figure 2B Another structural diagram of a touch sensor provided by the embodiment of the present application;

[0044] Figure 2C An example diagram of a geographic coordinate system provided by the embodiment of the present application;

[0045] Figure 2D A state diagram of a robot provided by the embodiment of the present application;

[0046] Figure 2E A heading angle diagram of a robot provided by the embodiment of the present application;

[0047] Figure 3A A software structural diagram of a robot provided by the embodiment of the present application;

[0048] Figure 3B An example diagram of a robot sensing method provided by the embodiment of the present application;

[0049] Figure 4 An example diagram of a robot provided by the embodiment of the present application;

[0050] Figure 5 A feedback method flowchart of a robot provided by the embodiment of the present application;

[0051] Figure 6A Another feedback method flowchart of a robot provided by the embodiment of the present application;

[0052] Figure 6B A diagram of a robot detecting a touch event provided by the embodiment of the present application;

[0053] Figure 7 An example diagram of a robot detecting an event provided by the embodiment of the present application;

[0054] Figure 8 A structural diagram of a chip system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0055] With reference to the drawings and the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of the present application.

[0056] In the present application, the character " / " generally represents that the associated objects before and after the " / " are in an "or" relationship. For example, A / B can be understood as A or B.

[0057] The terms "first", "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the embodiments, unless otherwise specified, the meaning of "multiple" is two or more.

[0058] In addition, the terms "include" and "have" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but can optionally include other steps or modules that are not listed, or can optionally include other steps or modules inherent to the process, method, product or device.

[0059] In addition, in the embodiments of the present application, the words "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or advantageous than other embodiments or designs. In fact, the use of the words "exemplary" or "for example" is intended to present concepts in a particular manner.

[0060] With the development of technology, robots have become more and more popular in daily life. Robots can be installed with various sensors, such as visual sensors, auditory sensors and tactile sensors, to realize the humanization of robots. At present, the humanization of robots in vision and hearing has been relatively mature. However, the humanization of robots in touch is difficult to meet the requirements due to the inability of touch sensors to detect the force information of the operation. For example, when a user uses different forces to perform the same operation on an intelligent robot (e.g., the user lightly taps the robot and the user heavily taps the robot), the robot cannot obtain the force acting on the robot through the touch sensor, so that the robot cannot make different control events for light tapping and heavy tapping.

[0061] In the current conventional technology, a robot can recognize a touch operation through a capacitive touch sensor. The capacitive touch sensor is composed of a plurality of sensor units in series. Each sensor unit includes four multifunctional layers arranged in pairs. As shown in Figure 1A FIG. 1, the sensor unit includes four multifunctional layers, i.e., multifunctional layer 101, multifunctional layer 102, multifunctional layer 103, and multifunctional layer 104. Multifunctional layer 101 and multifunctional layer 103 form a capacitor C1, and multifunctional layer 102 and multifunctional layer 104 form a capacitor C2. For example, Figure 1A The curve between multifunctional layer 101 and multifunctional layer 103 represents the electric field distribution of capacitor C1, and the curve between multifunctional layer 102 and multifunctional layer 104 represents the electric field distribution of capacitor C2. When an external object 105 enters the electric field line distribution area of C1 and C2, the sensor can obtain the speed and acceleration of the external object 105 approaching the sensor unit according to the relationship between the change amount and the change time of C1 and C2. Then, the robot can determine the force exerted by the external object 105 on the robot according to the speed and acceleration of the external object 105 approaching the sensor unit. That is, according to the above conventional technology, the greater the speed and acceleration of the external object 105 approaching the sensor unit, the greater the force exerted by the external object 105 on the robot; the smaller the speed and acceleration of the external object 105 approaching the sensor unit, the smaller the force exerted by the external object 105 on the robot.

[0062] However, in the above conventional technology, the speed and acceleration of the object approaching the sensor unit are used to detect the force exerted by the external object on the robot, which is not accurate. In addition, in the conventional technology, the plurality of capacitive touch sensors installed in the robot are in series (for example Figure 1B As shown in FIG. 1, capacitive touch sensor 106, capacitive touch sensor 107, and capacitive touch sensor 108 are in series), which cannot simultaneously feedback multiple operations.

[0063] Therefore, an embodiment of the present application provides a feedback method of a robot. In the method, the robot can receive an operation of a user, and then execute a control event corresponding to the operation. A touch sensor and an IMU are arranged on the inner side of the shell of the robot. The touch sensor is used to collect the operation acting on the robot, and the IMU is used to collect the heading angle of the robot. Generally, when the force of the operation acting on the robot is too large, the robot may vibrate (or shake); when the force of the operation acting on the robot is small, the robot does not vibrate. When the robot vibrates, the heading angle of the robot changes. Therefore, the force of the operation acting on the robot can be reflected according to the offset of the heading angle of the robot.

[0064] In the embodiments of the present application, the user can input operations of different operation types to the robot, such as tapping operations, continuous tapping operations, long pressing operations, and the like. The above operations can act on different regions of the robot, such as a head region, an abdomen region, a hand region, and the like.

[0065] It can be understood that after the robot receives the operation acting on the robot, the robot can obtain position information of the region of the operation, the operation type of the operation, and an offset of a heading angle of the robot when the robot receives the operation. In this way, the robot can execute a control event corresponding to the above position information, the operation type of the operation, and the force of the operation in response to the operation. Therefore, in the embodiments of the present application, the robot can accurately execute corresponding control events in combination with various external factors (the region of the operation, the operation type of the operation, and the force of the operation), so that the degree of humanization of the robot is increasingly high.

[0066] Please refer to Figure 2A , a system architecture diagram to which the method provided in the embodiments of the present application is applied. As shown in the figure, Figure 2A , the system architecture includes a user 201, a robot 202, and a server 203.

[0067] The user 201 can input an operation to the robot 202. The operation can be different types of operations input by the user 201 to the robot, for example, the operation can be tapping, long pressing, continuous tapping, and the like. For another example, the operation can also be an operation input by the user 201 to the robot with different forces, for example, the above tapping operation can be light tapping and heavy tapping.

[0068] It should be noted that the above tapping can be a finger of the user 201 touching the robot, or a palm of the user 201 touching the robot (i.e., slapping), which is not limited in the embodiments of the present application.

[0069] The robot 202 can receive an operation acting on the robot 202. Moreover, the robot 202 can identify a touch event corresponding to the operation input by the user 201 according to an identification strategy, and execute a control event corresponding to the touch event according to a feedback strategy. The identification strategy is used to reflect a corresponding relationship between operation information generated by the operation received by the robot 202 and the touch event, and the feedback strategy is used to reflect a corresponding relationship between the touch event and the control event.

[0070] For example, if the operation information that the pressing robot 202 hand for 2 seconds corresponds to a touch event of a handshake event in the feedback strategy, the control event that the robot 202 should perform corresponding to the handshake event in the feedback strategy is a handshake event. The robot 202 receives the operation information that the user 201 presses the robot 202 hand for 2 seconds, can identify that the control event corresponding to the operation information is a handshake event, and perform the control event of shaking hands with the user 201. The robot 202 can also record the operation information generated by the received operation and the touch event corresponding to the operation information. For example, the robot 202 receives the operation information that the user 201 presses the robot 202 hand for 2 seconds, and the touch event corresponding to the operation information is a handshake event. For another example, the robot 202 receives the operation information that the user 201 presses the robot 202 hand for 2.5 seconds, and the touch event corresponding to the operation information is also a handshake event.

[0071] In addition, the robot 202 can communicate with the server 203 wirelessly to complete the interaction of data. The robot 202 can transmit the historical data of the robot 202 to the server 203, which includes the position information of the robot 202, the attitude information of the robot 202, and the operation information generated by the user operation received by the robot 202. The robot 202 can also receive the updated identification strategy and the updated feedback strategy from the server 203.

[0072] The server 203 can provide the robot 202 with control strategies (such as identification strategies and feedback strategies, etc.). Specifically, the server 203 can send the identification strategy and the feedback strategy to the robot 202. In addition, the server 203 can receive the historical data from the robot 202. For example, the server 203 can receive the operation information recorded by the robot 202 and the touch event corresponding to the operation information. In addition, the server 203 can update the identification strategy and the feedback strategy according to the above historical data, and send the updated identification strategy and the updated feedback strategy to the robot 202. For example, before the robot 202 receives the updated feedback strategy from the server 203, the robot 202 can perform a handshake event in response to the user's long-pressing operation of the hand for 2 seconds. After the robot 202 receives the updated feedback strategy from the server 203, the robot 202 can perform a handshake event in response to the user's long-pressing operation of the hand for 1 second.

[0073] It should be noted that the type of robot and the use of the robot in the embodiments of the present application are not specially limited. For example, the robot in the embodiments of the present application can be an industrial robot, an agricultural robot, a household robot, a medical robot, a service robot, a space robot, an underwater robot, a military robot, a disaster rescue robot, an education and teaching robot, an entertainment robot, etc.

[0074] The robot feedback method provided in this application can be executed by a robot feedback device, which can be a robot (such as the robot 202 described above). The execution device can also be the robot's central processing unit (CPU) or a control module within the robot used to control the robot. This application uses the example of a robot executing the robot feedback method to illustrate the robot feedback method provided in this application embodiment.

[0075] The hardware structure of the robot in this embodiment is described below. The robot is equipped with input components such as a touch sensor, IMU, camera, receiver, and microphone, as well as output components such as a display, speaker, and servo motors. Optionally, the robot may be equipped with only one or more of the aforementioned input or output components. Furthermore, the robot also possesses a processor, interface, and artificial intelligence (AI) capabilities.

[0076] The touch sensor is used to collect operations performed on the robot. For example, the touch sensor can collect the type of operation received by the robot (e.g., tapping, continuous tapping, long press). The touch sensor can also collect location information of the area of ​​the robot being operated by the user (e.g., the robot's head, hands, and chest). Optionally, the touch sensor is set at a preset position on the robot's body, and the area of ​​the robot being operated can be determined through the preset location information. In this embodiment, the robot includes multiple touch sensors, and optionally, each touch sensor is located inside the robot's shell. Optionally, the multiple touch sensors are arranged in parallel inside the robot's shell.

[0077] Please refer to Figure 2B This is a schematic diagram of the structure of the touch sensor provided in an embodiment of this application. Figure 2B As shown, the touch sensor 204 includes a capacitive sensing button 204a (such as 204a-1 and 204a-2) and a capacitance detector 204b. The capacitance detector 204b can be connected to the capacitive sensing button. Optionally, the capacitive sensing button 204a consists of two copper plates (such as a first copper plate 204a1 and a second copper plate 204a2), with the first copper plate 204a1 grounded and the second copper plate 204a2 laid inside the outer shell of the robot 202. The capacitive sensing button 204a (such as 204a-1 and 204a-2) is used to sense operations applied to the robot, and the capacitance detector 204b is used to detect changes in capacitance of the capacitive sensing button 204a.

[0078] It should be noted that due to the existence of the human body electric field, the capacitive sensing button (for example, the second copper sheet 204a-2) in the touch point and the touch area of the touch sensor can form a small coupling capacitor. Moreover, high-frequency current can flow through the small capacitor more easily, but will be shunted by the small capacitor. In this way, the touch sensor can obtain the position of the touch point in the touch sensor according to the amount of current flowing into the four electrodes symmetrical to the second copper sheet 204a-2 and the distance between the touch point and the four corners of the second copper sheet 204a-2. For example, the position of the touch point can be represented by two-dimensional coordinates of the touch point in the coordinate system of the copper sheet. For example, the origin of the coordinate system in the copper sheet can be any one corner (for example, the upper left corner and the lower left corner) in the copper sheet, and the x-axis and the y-axis can be two adjacent sides adjacent to the point. The position of the touch point can be represented as (a1, a2).

[0079] It can be understood that the copper sheet is relatively soft, and the shell of the robot is curved. Therefore, the touch sensor 204 can be well fitted on the inner side of the shell of the robot. In this way, the touch sensitivity of the robot can be increased, and the degree of humanization of the robot can be improved.

[0080] It should be noted that the above-mentioned capacitive sensing button 204a (such as 204a-1 and 204a-2) can also be composed of a thin sheet of other metal materials with relatively soft material, such as iron sheet, aluminum sheet, etc. Optionally, in order to reduce the cost, the above-mentioned capacitive sensing button 204a is usually composed of a copper sheet.

[0081] The IMU can include one or more acceleration sensors and / or gyroscope sensors. Optionally, the IMU can include 3 acceleration sensors and 3 gyroscope sensors. The above-mentioned 3 acceleration sensors and the above-mentioned 3 gyroscope sensors can form a 6-axis IMU. Alternatively, the IMU can include 3 acceleration sensors, 3 gyroscope sensors, and 3 magnetometers. The above-mentioned 3 acceleration sensors, 3 gyroscope sensors, and 3 magnetometers can form a 9-axis IMU. The IMU can collect the heading angle of the robot. The heading angle includes the azimuth angle, the pitch angle, and the roll angle. In the following, the embodiments of the present application combine the description of the heading angle of the robot. Figure 2C and Figure 2D The heading angle of the robot is described.

[0082] Wherein, the IMU collects the heading angle of the robot based on the geographic coordinate system. For example, Figure 2CAs shown, the origin O of the geographic coordinate system is located at the carrier (i.e. the point where the device containing the IMU, such as a robot, is located); the x-axis points east (E) along the local meridian; the y-axis points north (N) along the local prime vertical; and the z-axis points upward along the local geographic vertical, and forms a right-handed orthogonal coordinate system with the x-axis and the y-axis. Among them, the plane formed by the x-axis and the y-axis is the local horizontal plane, and the plane formed by the y-axis and the z-axis is the local prime vertical plane. Therefore, it can be understood that the coordinate system of the IMU is: taking the IMU as the origin O, the x-axis points east along the local meridian, the y-axis points north along the local prime vertical, and the z-axis points upward (i.e. the opposite direction of the geographic vertical).

[0083] For example, it is assumed that the robot is in the state shown in FIG. 1B, which is parallel to the horizontal plane of the ground. Figure 2D As shown in FIG. 1C, the a edge of the robot (i.e. any edge of the robot in the front view which is parallel to the ground) is parallel to the x-axis of the geographic coordinate system, the b edge of the robot (i.e. any edge of the robot in the side view which is parallel to the ground) is parallel to the y-axis of the geographic coordinate system, and the c edge of the robot (i.e. any edge of the robot in the side view which is perpendicular to the ground) is parallel to the z-axis of the geographic coordinate system. Figure 2D Among them, the azimuth angle of the robot is: the included angle between the projection of the a edge of the robot on the xoy plane and the y-axis of the geographic coordinate system. For example, the azimuth angle of the robot is a shown in FIG. 1D.

[0084] Among them, OB is parallel to the a edge of the robot, oB' is the projection of oB on the xoy plane, BB' is perpendicular to oB', and a is the included angle between oB' and the y-axis. Figure 2E The pitch angle of the robot is: the included angle between the projection of the a edge of the robot on the yoz plane and the y-axis of the geographic coordinate system. For example, the pitch angle of the robot is β shown in FIG. 1E.

[0085] Among them, OB is parallel to the a edge of the robot, oB' is the projection of oB on the yoz plane, BB' is perpendicular to oB', and β is the included angle between oB' and the y-axis. Figure 2E The roll angle of the robot is: the included angle between the projection of the a edge of the robot on the xoz plane and the x-axis of the geographic coordinate system. For example, the pitch angle of the robot is γ shown in FIG. 1F.

[0086] Among them, OB is parallel to the a edge of the robot, oB' is the projection of oB on the xoz plane, BB' is perpendicular to oB', and γ is the included angle between oB' and the y-axis. Figure 2E Among them, the heading angle of the robot can be expressed in the form of (a, β, γ). a is the azimuth angle of the robot, β is the pitch angle of the robot, and λ is the roll angle of the robot.

[0087]

[0088] ​The camera can capture images or videos. For example, the camera can capture a face image of a user around. For another example, the camera can also capture surrounding environment information. For yet another example, the camera can calculate a distance between the user and the camera, i.e., the camera can calculate a distance between the user and the robot. In some embodiments, the robot can include one or N cameras, N being a positive integer greater than 1.

[0089] The robot can implement a display function through a GPU, a display, and a processor, etc. The GPU is a microprocessor for image processing, connecting the display and the processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor can include one or more GPUs, which execute program instructions to generate or change display information.

[0090] The display is used to display images, videos, etc. The display includes a display panel. For example, when the robot is a service robot, the display can be used to display a menu interface, a help interface, etc. For another example, when the robot is a navigation robot, the display can be used to display a navigation route interface.

[0091] The robot can implement an audio function through a receiver, a microphone, a speaker, and a processor, etc. For example, the robot can capture a user's voice through the receiver and talk to the user through the speaker. Also, the robot can implement a control function through the receiver, the microphone, and the processor, etc. For example, the robot can capture a user's voice instruction through the receiver and determine an operation instruction by the processor, so that the robot performs a control event.

[0092] The robot includes a plurality of limbs composed of servos. Each limb of the robot can be made of metal or other materials and driven by a servo device, so that the robot can express actions through the limbs and perform control events. For example, to achieve the effect of personification, the robot can include nine servo limbs, so that the robot can perform common limb actions (such as nodding, shaking, turning, hugging, greeting, etc.). For example, when the robot's abdomen receives a heavy blow operation, the robot can perform the action of bowing and covering the abdomen.

[0093] The processor can include one or more processing units, for example: the processor can include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), and / or a neural-network processing unit (NPU), etc. Among them, different processing units can be independent devices, or can be integrated in one or more processors.

[0094] The controller can be the nerve center and command center of the robot. The controller can generate operation control signals according to instruction operation codes and timing signals, complete the control of instruction fetching and instruction execution.

[0095] The memory can also be provided in the processor, for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. The memory can save instructions or data that the processor has just used or repeatedly uses. If the processor needs to use the instructions or data again, it can directly call from the memory. Avoiding repeated access, reducing the waiting time of the processor, thus improving the efficiency of the system.

[0096] In some embodiments, the processor can include one or more interfaces. The interface can include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a general-purpose input / output (GPIO) interface, and / or a universal serial bus (USB) interface, etc.

[0097] The robot can realize AI capabilities through the above-mentioned input components, output components, processors, and the like. For example, the robot can realize capabilities such as Text To Speech (TTS) and voiceprint recognition through a microphone, a speaker, a processor, and the like. For another example, the robot can realize capabilities such as face recognition and face tracking through a camera and a processor, and the like. Of course, the robot can also realize capabilities such as ASE, affective computing, and sound source positioning. In this way, the robot can improve the degree of personification and provide users with more comprehensive functions such as communication, learning, entertainment, and service.

[0098] It should be noted that the robot including the above-mentioned input components, output components, and processors is only an example, and the robot can have more or fewer components than the above-mentioned devices, can combine two or more components, or can have a different component configuration. The above-mentioned various components can be implemented in hardware, software, or a combination of hardware and software including one or more signal processing and / or application specific integrated circuits.

[0099] After introducing the hardware structure of the robot of the embodiments of the present application, the robot is divided into multiple functional modules to introduce the system architecture of the robot. As shown in Figure 3A The robot includes a hardware distribution layer 301, an algorithm processing layer 302, and a business implementation layer 303.

[0100] The hardware distribution layer 301 can collect the operation information input by the user. The hardware distribution layer 301 includes the above-mentioned touch sensor, IMU, and camera, and the like. Specifically, the touch sensor can collect position information and operation types of the operation acting on the robot. For example, the touch sensor can collect the operation of the user pressing the hand input for 2 seconds on the robot. The IMU can collect the heading angle of the robot. The camera can collect the face image of the user around and calculate the face distance between the user and the robot. Moreover, the hardware distribution layer 301 can also transmit the collected operation information to the algorithm processing layer 302, and the algorithm processing layer 302 determines the touch event according to the operation information.

[0101] The algorithm processing layer 302 can receive operation information from the hardware distribution layer 301. For example, the algorithm processing layer 302 can receive operation type and operation area location information from the touch sensor. It can also receive the heading angle from the IMU. Furthermore, it can receive facial information (face image and face distance) from the camera. The algorithm processing layer 302 can also detect whether the robot vibrates based on its heading angle to determine the force of the operation received by the robot. For example, if the robot's heading angle does not change when it receives a 2-second press input from the user's hand, the robot can determine that the pressing force is small. Conversely, if the robot's heading angle changes when it receives a continuous tap from the user's head, the robot can determine that the continuous tapping force is large.

[0102] Furthermore, the algorithm processing layer 302 can also determine the touch event based on the operation information. For example... Figure 3B As shown, the algorithm processing layer 302 can perform fusion perception based on the operation type and location information of the operation area detected by the touch sensors of various parts of the robot, the human image information, and the robot's heading angle to determine the touch event. For example, the algorithm processing layer 302 can receive information that the user tapped the robot's head, the robot's heading angle when the tapping operation was received, and the distance to the human face being 0.5 meters. The algorithm processing layer 302 can combine the above operation information to determine that the touch event is a human tapping event. Furthermore, the algorithm processing layer 302 can determine the control event to be executed by the robot based on the touch event and send the control event to the business implementation layer 303.

[0103] The business implementation layer 303 can receive control events from the algorithm processing layer 302 and control the robot to execute these events. The robot can execute control events through actions, facial expressions, sounds, etc. For example, when the control event is a handshake event, the robot can perform a handshake action. Another example is when the control event is a happy event, the robot can smile. Yet another example is when the control event is a laughing event, the robot can make a "hahaha" sound.

[0104] The methods described in the following embodiments can all be implemented in a robot having the above-described hardware structure and system architecture.

[0105] This application provides a feedback method for a robot. The method is applied to a robot. The inner side of the robot's shell includes multiple preset areas (such as a first preset area) equipped with touch sensors.

[0106] Specifically, the inner side of the robot's shell includes multiple first preset areas, and each first preset area is equipped with a touch sensor. The number of these first preset areas is not limited in this embodiment. For example, the inner side of the robot's shell may include 10 first preset areas. Or, for example, the inner side of the robot's shell may include 20 first preset areas.

[0107] In some embodiments, the first predetermined region may be distributed on the inner side of the outer shell of any part of the robot. For example, as shown... Figure 4 As shown, the robot's outer shell includes 28 first preset areas. These 28 first preset areas are distributed on the inner sides of the robot's head shell, cheek (lower left and lower right cheek) shell, abdomen shell, waist (lower right and lower left waist) shell, back of hands (back of right and back of left hand) shell, palms (palms of right and left hand) shell, shoulders (left and right shoulders) shell, ears (left and right ears) shell, and forehead (left and right forehead) shell. In other words, touch sensors can be located within these 28 first preset areas.

[0108] It should be understood that, although Figure 4 Only the first preset area in the robot's main view is displayed. However, Figure 4 The aforementioned 28 first preset areas may also include Figure 4 Any first predetermined region in the left, right, top, and rear views of the robot that is not shown. For example, the first predetermined region inside the back shell in the rear view of the robot.

[0109] Understandable, Figure 4 The robot shown is equipped with numerous touch sensors. This allows the robot to receive operations applied to any area, ensuring it can respond to any action received in any area and thus enhancing its anthropomorphic nature.

[0110] In other embodiments, the area where the touch sensor is located may be an area corresponding to a region on the robot's outer shell surface where user operation is more frequent.

[0111] In this embodiment, the area on the robot's outer shell surface that is frequently touched by the user can be referred to as the second preset area. The robot's outer shell surface may include multiple second preset areas, and each second preset area is a region where the user's operation frequency is greater than a preset frequency threshold. In other words, the second preset area is the robot's outer shell surface, the area that the user frequently touches.

[0112] The plurality of first preset areas inside the shell of the robot correspond to the plurality of second preset areas on the surface of the shell of the robot one by one. That is, the first preset areas can be distributed on the inside of the shell of the robot part that is frequently operated by the user, and the touch sensor can be arranged on the inside of the shell of the robot part that is frequently operated by the user.

[0113] For example, before mass production of the robot, a plurality of users can be randomly selected to interact with the robot, and the areas (i.e., the second preset areas) that are frequently touched among the plurality of areas (e.g., the plurality of third preset areas) included on the surface of the shell of the robot are recorded. The surface of the shell of the robot includes a plurality of third preset areas (e.g., the 28 first preset areas shown in FIG. 2 correspond to the areas on the surface of the shell), and the plurality of third preset areas can completely or almost cover the surface of the shell of the robot (e.g., the total area of the plurality of third preset areas accounts for 90% of the area of the surface of the shell). For example, in combination with the above table 1, the plurality of third preset areas on the surface of the shell of the robot can be determined as follows. Figure 4 Figure 4 For example, please refer to Table 1, which shows the number of operation types received by each third preset area when 20 users interact with the robot.

[0114] Table 1

[0115] Tap / Time Tap / Time …… Tap / Time Total 1 (Head) 0 1 2 2 5 2 0 3 1 1 4 (Right lower cheek) 1 1 1 3 5 (Left lower cheek) 1 2 3 …… …… 10 (Left underarm) 6 4 10 11 (Right underarm) 6 4 10 12 (Chest) 3 4 7 13 (Abdomen) 1 7 4 12 14 (Right lower back) 2 1 3 15 (Left lower back) 5 2 7 16 (Right back of hand) 4 4 8 17 (Right palm) 1 1 2 18 (Left palm) 5 0 5 19 (Left back of hand) 13 3 16 20 0 21 0 22 (Right shoulder) 1 1 2 23 (Left shoulder) 1 2 1 4 24 (Right ear) 2 2 4 25 (Left ear) 1 1 2 26 (Right forehead) 3 2 5 27 (Left forehead) 4 3 7 28 (Back) 1 1 1 3 Total 3 5 69 50

[0116] As can be seen from the above table 1, the third preset areas on the surface of the shell of the robot, such as the head, the left lower cheek, the right lower cheek, the chest, the abdomen, the left underarm, the right underarm, the right palm, the left palm, the right back of the hand, and the left back of the hand, are areas that are frequently operated by the user. That is, the areas on the surface of the shell of the robot, such as the head, the left lower cheek, the right lower cheek, the chest, and the abdomen, are the second preset areas. In this way, the areas on the inside of the shell of the robot, such as the head, the left lower cheek, the right lower cheek, the chest, and the abdomen, are the first preset areas, and the touch sensor can be arranged on the first preset areas on the inside of the shell of these parts.

[0117] It should be noted that in the embodiments of the present application, users of different identities can be selected to interact with the robot according to the type or purpose of the robot. For example, if the robot is a food ordering robot, the randomly selected users can be diners. For another example, if the robot is an entertainment robot, the randomly selected users can be children. The identity of the user is not limited in the embodiments of the present application.

[0118] Optionally, by recording the areas frequently operated by the user (i.e., the second preset areas), the number of touch sensors arranged on the robot can be reduced by arranging the touch sensors only on the first preset areas corresponding to the second preset areas. In this way, the cost can be reduced while ensuring the interaction experience of the user with the robot.

[0119] ​And, the robot is further provided with at least one IMU, which can collect the heading angle of the robot. The IMU can be installed at the center of gravity of the robot, which can be the head and / or the chest of the robot. Generally, when the robot vibrates, the center of gravity of the robot will also vibrate. Therefore, when the robot receives an operation with too much force, the center of gravity of the robot will vibrate. In this way, the robot can obtain the change amount of the heading angle of the center of gravity of the robot, i.e. the change amount of the heading angle of the robot, through the IMU.

[0120] In some embodiments, after receiving an operation (e.g. a first operation) acting on any region (e.g. a first region) of the plurality of first preset regions of the robot, the robot can obtain the position information of the first region and the operation type of the first operation through the touch sensor. And, according to the principle of collecting the heading angle of the robot through the IMU introduced in the above embodiments, the robot can obtain the heading angle of the robot before receiving the first operation (e.g. a first initial heading angle) through the IMU, obtain the heading angle of the robot after receiving the first operation (e.g. a first heading angle) through the IMU, and calculate the difference between the first heading angle and the first initial heading angle to obtain a first offset. The first offset is used to reflect the force of the first operation acting on the robot. Then, the robot can execute a control event (e.g. a first control event) corresponding to the position information of the first region, the operation type of the first operation and the force of the first operation acting on the robot in response to the first operation.

[0121] For example, the first operation received by the robot is a tapping operation acting on the head region of the robot. And, the tapping operation causes the heading angle of the robot to change, i.e. the force of the tapping operation is large, causing the robot to vibrate. In response to the tapping operation, the robot can execute a hand covering the head region and emit a "ouch!" sound.

[0122] For another example, the first operation received by the robot is a tapping operation acting on the head region of the robot. And, the tapping operation does not cause the heading angle of the robot to change, i.e. the force of the tapping operation is small, and the robot does not vibrate. In response to the tapping operation, the robot can execute a questioning event, such as emitting a "Hello, what can I do for you?" sound.

[0123] It can be understood that in the embodiments of the present application, after the robot receives the first operation acting on the robot, the position information of the first region, the operation type of the first operation, and the offset amount of the heading angle of the robot after receiving the first operation (i.e., the first offset amount) can be obtained. Among them, the first offset amount can reflect the force of the first operation acting on the robot. In this way, the robot can execute the corresponding control event according to the position information of the first region, the operation type of the first operation, and the operation force of the first operation. Therefore, in the embodiments of the present application, the robot can combine various external factors (operation region, operation type and operation force) to accurately execute the corresponding control event, and the degree of humanization of the robot is higher and higher.

[0124] The embodiments of the present application provide a feedback method of a robot, as shown in the figure, the feedback method of the robot can include S501-S503. Figure 5

[0125] S501, the robot receives a first operation acting on a first region.

[0126] Among them, the first region is any region in a plurality of first preset regions. For example, the first region can be the region inside the head shell of the robot. For another example, the first region can be the region inside the abdominal shell of the robot. The first operation can be a long press operation, a touch operation, a tapping operation, etc.

[0127] In the embodiments of the present application, the above-mentioned first operation can be divided into different operation types according to the touch parameters of the first operation. The touch parameters include touch duration, touch displacement distance, and touch frequency. Among them, the touch duration is the time when the first operation acts on the first region; for example, the touch duration can be 0.3 seconds, 1 second, 2 seconds, etc. The touch displacement distance is the distance of the first operation sliding on the first region; for example, the touch displacement distance can be 0.5 centimeters, 2 centimeters, 5 centimeters, etc. The touch frequency is the number of times of touching the first region in a unit time; for example, the touch frequency can be 1 time of tapping the robot in 1 second, or 3 times of tapping the robot in 2 seconds.

[0128] In a possible design, if the touch duration of the first operation is short and the touch frequency is low, the first operation can be a tapping (or tapping) operation, etc. For example, the first operation is a tapping operation, the touch duration of the tapping operation on the first region is 0.2 seconds, and the number of times of touching the first region in a unit time (for example, 2 seconds) is 1.

[0129] ​If the touch duration of the first operation is short and the touch frequency is high, the first operation can be a continuous tapping (or patting) operation, etc. For example, the first operation is a patting operation, the touch duration of the patting operation on the first region is 0.2 seconds, and the number of times of touching the first region per unit time (for example, within 2 seconds) is 3.

[0130] If the touch duration of the first operation is long, the first operation can be a long-press operation, etc. For example, the first operation is a long-press operation, the touch duration of the long-press operation on the first region is 2.5 seconds.

[0131] If the displacement distance of the first operation is long, the first operation can be a stroking operation. For example, the first operation is a stroking operation, and the sliding distance of the stroking operation on the first region is 3 centimeters.

[0132] S502, the robot obtains position information of the first region, an operation type of the first operation, and a first offset.

[0133] The first offset is used to indicate a change amount of a heading angle of the robot after the robot receives the first operation, and the first offset can be used to reflect the force of the first operation acting on the robot.

[0134] In the embodiments of the present application, the robot can obtain a first heading angle and a first initial heading angle. The first heading angle is a heading angle of the robot after the robot receives the first operation, and the first initial heading angle is a heading angle of the robot before the robot receives the first operation. Then, the robot can calculate a difference between the first heading angle and the first initial heading angle to obtain the first offset.

[0135] For example, the heading angle of the robot (i.e., the first initial heading angle) before the robot receives the first operation (e.g., a tapping operation) is A. After the robot receives the tapping operation, the robot vibrates, and the heading angle of the robot (i.e., the first heading angle) is B. Then, the first offset is B-A.

[0136] In a possible design, the robot can divide the first operation into a light operation and a heavy operation according to the first offset. The light operation is an operation with a small operation force, and the heavy operation is an operation with a large operation force. The force corresponding to the heavy operation is greater than the force corresponding to the light operation. Specifically, if the first offset is greater than a preset offset threshold, the first operation is a heavy operation. If the first offset is less than the preset offset threshold, the first operation is a light operation.

[0137] It can be understood that when the force of the first operation acting on the robot is too large, the robot can vibrate; when the force of the first operation acting on the robot is small, the robot does not vibrate. When the robot vibrates, the heading angle of the robot changes. Therefore, the degree of force of the first operation acting on the robot can be reflected according to the first offset of the heading angle of the robot.

[0138] It should be noted that if the preset offset threshold is 0, it means that the robot vibrates slightly, and when the first offset is small, the robot can determine that the first operation is a heavy operation. That is, when the preset offset threshold is 0, the division threshold of the heavy operation is low. If the preset offset threshold is greater than 0, it means that even if the robot vibrates slightly, when the first offset is small (that is, the first offset is greater than 0 and less than the preset offset threshold), the robot determines that the first operation is a light operation. That is, when the preset offset threshold is greater than 0, the division threshold of the heavy operation is high. The preset offset threshold is not limited in the embodiment of the application.

[0139] For example, assuming that the preset offset threshold is 0. The robot is in a static state when it does not receive the first operation, and the robot can collect the initial heading angle a through the IMU; after receiving the first operation, the robot can collect the first heading angle b through the IMU. If a and b are not the same (that is, the first initial heading angle and the first heading angle are not the same), the robot can determine that the first operation is a heavy operation. If a and b are the same (that is, the first initial heading angle is equal to the first heading angle), the robot can determine that the first operation is a light operation.

[0140] In another possible design, the robot can divide the first operation into multiple level operations (such as a first level operation and a second level operation) according to the first offset. The degree of force corresponding to a high level operation is greater than the degree of force corresponding to a low level operation; for example, the degree of force corresponding to a third level operation is greater than the degree of force corresponding to a second level operation. For example, the robot can set multiple preset offset thresholds (such as a first preset offset threshold and a second preset offset threshold). If the first offset is less than the first preset offset threshold, the first operation is a first level operation. If the first offset is less than the second preset offset threshold and greater than the first preset offset threshold, the first operation is a second level operation.

[0141] It can be understood that by setting multiple preset offset thresholds, the degree of force of the first operation acting on the robot can be accurately divided. In this way, the robot can execute different control events according to operations of different degrees, thereby improving the degree of humanization of the robot.

[0142] In the embodiments of the present application, the robot can obtain the position information of the first region through the touch sensor arranged in the first region. Specifically, each touch sensor corresponds to a preset identifier, and the preset identifiers of each touch sensor are different. For example, the preset identifier of the touch sensor arranged on the inner side of the head shell is No. 1, and the preset identifier of the touch sensor arranged on the inner side of the abdominal shell is No. 13. Moreover, the robot can save the correspondence between the preset identifier of each touch sensor and the region where each touch sensor is arranged. When the robot obtains the touch parameter (including the preset identifier of the touch sensor) from the touch sensor, the robot can obtain the position information of the first region according to the preset identifier of the touch sensor and the correspondence between the preset identifier of the touch sensor and the region where the touch sensor is arranged.

[0143] For example, if the preset identifier of the touch sensor arranged in the first region is No. 1, and No. 1 corresponds to the region on the inner side of the head shell of the robot. When the robot receives the first operation acting on the first region, the robot can obtain that the preset identifier of the touch sensor is No. 1, and the robot can determine that the position of the first region is the head of the robot.

[0144] Moreover, the robot can obtain the operation type of the first operation through the touch sensor arranged in the first region. Specifically, the robot can obtain the touch parameter generated by the first operation on the first region through the touch sensor, and determine the operation type of the first operation according to the touch parameter. For example, if the robot is provided with a touch duration threshold, a touch displacement distance threshold and a touch interval duration threshold. If the touch duration obtained by the robot is greater than the touch duration threshold, the robot determines that the first operation is a long press operation. If the touch displacement distance obtained by the robot is greater than the touch displacement distance threshold, the robot determines that the first operation is a stroking operation. If the touch frequency obtained by the robot is greater than the touch frequency threshold, the robot determines that the first operation is a continuous pressing operation.

[0145] S503, in response to the first operation, the robot performs a first control event corresponding to the position information of the first region, the operation type of the first operation and the force of the first operation acting on the robot.

[0146] In some embodiments, in response to the first operation, the robot can determine a first touch event corresponding to the first operation according to the position information of the first region, the operation type of the first operation and the force of the first operation acting on the robot (hereinafter referred to as operation force). Then, the robot can perform a first control event corresponding to the first touch event.

[0147] It should be noted that the robot can save the correspondence relationship (which can be referred to as an identification strategy) between the position information of the operation operated region, the operation type of the operation, and the operation force of the operation and the touch event. In this way, the robot can determine the touch event according to the identification strategy. And the robot can save the correspondence relationship (which can be referred to as a feedback strategy) between the touch event and the control event. In this way, the robot can execute the control event according to the feedback strategy.

[0148] For example, as shown in Table 2, the correspondence relationship between the position information of the operation operated region, the operation type of the operation, the operation force of the operation, the touch event, and the control event is shown.

[0149] Table 2

[0150]

[0151]

[0152] According to Table 2, the robot can identify different touch events according to different position information of the operation operated region, operation type, and operation force, and execute different control events. For example, when the robot receives the operation of the user long pressing the palm of the robot, and the operation force is small, the robot can execute the handshaking event (such as lifting the arm and merging the palm).

[0153] It should be noted that Table 2 described above is an example proposed by the embodiment of the present application. The identification strategy and the feedback strategy described above are not limited by the embodiment of the present application.

[0154] Based on the above scheme, after receiving the first operation acting on the robot, the robot can obtain the position information of the first region, the operation type of the first operation, and the offset of the heading angle after the robot receives the first operation (i.e. the first offset). The first offset can reflect the force of the first operation acting on the robot. In this way, the robot can execute the corresponding control event according to the position information of the first region, the operation type of the first operation, and the operation force of the first operation. Therefore, in the embodiment of the present application, the robot can combine various external factors (operation region, operation type, and operation force) to accurately execute the corresponding control event, and the degree of humanization of the robot is higher and higher.

[0155] In some embodiments, the control event executed by the robot is related to the position information of the operation region and the operation force, and is irrelevant to the operation type. Specifically, after receiving the first operation acting on the first region, the robot can obtain the position information of the first region and the first offset. In response to the first operation, the robot can execute the control event corresponding to the position information of the first region and the force of the first operation acting on the robot.

[0156] For example, if the robot receives an operation acting on the head, and the operation has a large operation strength, the robot can cry and make "wuuuuu" sound. The operation can be any type of operation. For example, the operation can be pressing. For another example, the operation can be tapping. For another example, the operation can be continuous tapping.

[0157] It can be understood that in the above technical solution, the robot only combines the position information of the operation area and the operation strength to perform the corresponding control event, which can reduce the amount of data calculation of the robot, improve the response speed of the robot, and make the robot more and more humanized.

[0158] In some embodiments, the control event performed by the robot is related to the operation type and the operation strength of the operation, and is irrelevant to the operation area. Specifically, after receiving a first operation acting on a first area, the robot can obtain the operation type and the first offset of the first operation. In response to the first operation, the robot can perform a control event corresponding to the operation type of the first operation and the strength of the first operation acting on the robot.

[0159] For example, if the robot receives a touch operation, and the operation has a small operation strength, the robot can make a smiling expression. The touch operation can act on any first preset area of the robot. For example, the first preset area can be the head of the robot. For another example, the first preset area can be the back of the robot. For another example, the first preset area can be the abdomen of the robot.

[0160] It can be understood that in the above technical solution, the robot only combines the operation type and the operation strength to perform the corresponding control event, which can reduce the amount of data calculation of the robot, improve the response speed of the robot, and make the robot more and more humanized.

[0161] It should be noted that the robot can also only obtain any one of the position information, operation type and operation strength of the operation area, and perform a control event corresponding to the parameter. In this way, the amount of data calculation of the robot can be reduced, the response speed of the robot can be improved, and the degree of humanization of the robot can be higher and higher.

[0162] In some embodiments, the robot can also include a camera that can capture portrait information. The robot can determine whether the first touch event is a human event according to the portrait information.

[0163] In one possible design, in response to the first operation, if the robot captures portrait information, the robot can determine that the first touch event is a human event. In response to the first operation, if the robot does not capture portrait information, the robot can determine that the first touch event is a non-human event.

[0164] For example, in response to the pressing operation acting on the abdomen, if the robot can collect the portrait information and the first offset is greater than the preset offset threshold, the robot can determine that the touch event is a human hitting event. For another example, in response to the pressing operation acting on the abdomen, if the robot does not collect the portrait information and the first offset is greater than the preset offset threshold, the robot can determine that the touch event is an accidental hitting event, such as a robot falling, a robot colliding with an object, and the like.

[0165] In another possible design, in response to the first operation, the robot can determine whether the first operation is a human event according to a distance between the user and the robot when the robot can collect the portrait information. Specifically, the portrait information includes a face image and a portrait distance, where the portrait distance is the distance between the user and the robot. In response to the first operation, if the robot can collect the portrait information and the portrait distance is less than a preset distance threshold, the robot can determine that the first touch event is a human event. In response to the first operation, if the robot can collect the portrait information but the portrait distance is greater than the preset distance threshold, the robot can determine that the first touch event is a non-human event.

[0166] For example, assuming that the preset distance threshold is 1 meter. In response to the knocking operation, the robot can collect the face image. If the portrait distance is 0.5 meters, the robot can determine that the knocking operation is a human knocking operation. If the portrait distance is 3 meters, the robot can determine that the knocking operation is an accidental hitting event, such as a robot being hit by an object (such as a stone), a robot colliding with an object, and the like.

[0167] It can be understood that the robot determines whether the first operation is a human event through the portrait information (the face image and the portrait distance), which can increase the touch events recognized by the robot. In this way, the robot can feed back more control events, and the degree of personification of the robot is improved.

[0168] In some embodiments, after the robot receives the first operation, the robot can further receive a second operation. The robot can perform a corresponding control event according to whether the robot receives the second operation within a preset time length after receiving the first operation. For example, as shown in FIG. 6, the method further includes: Figure 6A

[0169] S601, the robot receives a second operation acting on a second region.

[0170] The second region is any region in the plurality of first preset regions.

[0171] ​In the embodiments of the present application, whether the first region and the second region are the same is not limited. That is, the first region and the second region can be the same region, and the first region and the second region can also be different regions. For example, the first operation and the second operation can both act on the head of the robot. For another example, the first operation can act on the right underarm part of the robot, and the second operation can act on the left underarm part of the robot.

[0172] In the embodiments of the present application, whether the first operation and the second operation are the same is not limited. That is, the first operation and the second operation can be the same operation, and the first operation and the second operation can also be different operations.

[0173] It should be noted that the specific introduction of the robot receiving the second operation acting on the second region can refer to the description of the robot receiving the first operation acting on the first region in S501, which is not repeated here.

[0174] S602, the robot acquires position information of the second region, an operation type of the second operation and a second offset.

[0175] The second offset is the difference between the second heading angle of the robot and the second initial heading angle of the robot, the second heading angle is the heading angle of the robot after the robot receives the second operation, the second initial heading angle is the heading angle of the robot before the robot receives the second operation, and the second offset is used to reflect the force of the second operation acting on the robot.

[0176] It should be noted that the specific introduction of the robot acquiring the position information of the second region, the operation type of the second operation and the second offset can refer to the description in S502 above, which is not repeated here.

[0177] S603, the robot determines whether the robot receives the second operation within a preset time length after receiving the first operation.

[0178] In the embodiments of the present application, if the second operation is an operation received by the robot within the preset time length after receiving the first operation, the first operation and the second operation can correspond to one touch event. That is, the robot receives the second operation within the preset time length after receiving the first operation, and the robot executes one control event corresponding to the first operation and the second operation, instead of executing the first control event corresponding to the first operation and the second control event corresponding to the second operation. For example, as shown in FIG. 6, if the touch interval between operation 1 and operation 2 is less than the preset time length, operation 1 and operation 2 can correspond to one touch event (for example, continuous shooting). Figure 6B

[0179] ​If the second operation is an operation received by the robot after a preset time length after the first operation, the first operation and the second operation can correspond to two control events. That is, the robot receives the second operation within the preset time length after receiving the first operation, and the robot only performs the control event corresponding to the second operation. For example, as shown in FIG. 6, if the touch interval between operation 2 and operation 3 is greater than the preset time length, operation 2 can correspond to a touch event (for example, a pat), and operation 2 can correspond to a touch event (for example, a caress). Figure 6B

[0180] It should be noted that the present application does not limit the setting of the above-mentioned preset time length. For example, the above-mentioned preset time length can be positively correlated with the touch time length of the first operation. That is, the longer the touch time length of the first operation, the longer the preset time length. For example, when the first operation is a press, the touch time length of the press is 0.8 seconds, and the preset time length can be 1.5 seconds. For another example, when the first operation is a long press, the touch time length of the long press is 2 seconds, and the above-mentioned preset time length is 3 seconds.

[0181] In a possible design, if the robot receives a second operation acting on the second region within the preset time length after receiving the first operation, the robot can perform S604. If the robot receives a second operation acting on the second region after the preset time length after receiving the first operation, the robot can perform S605.

[0182] It should be noted that if the robot receives a second operation acting on the second region within the preset time length after receiving the first operation, the robot does not perform S503. If the robot receives a second operation acting on the second region after the preset time length after receiving the first operation, the robot can perform S503 after S502.

[0183] S604, in response to the first operation and the second operation, the robot performs a third control event corresponding to the position information of the first region, the operation type of the first operation and the force of the first operation acting on the robot, the position information of the second region, the operation type of the second operation and the force of the second operation acting on the robot.

[0184] For example, if the preset time length is 3 seconds. The interval time length between the first operation and the second operation received by the robot is 1 second. The first operation is to press the right armpit of the robot, and the robot can collect the portrait information and the first offset; the second operation is to press the left armpit of the robot, and the robot can collect the portrait information and the second offset. The robot can identify the touch event composed of the first operation and the second operation as a hug event. Then, the robot can perform a hug control event corresponding to the hug event, for example, the robot can raise both arms and hug the user.

[0185] ​It can be understood that the robot can perform one control event (i.e., a third control event) in response to the first operation and the second operation. In this way, the robot can feed back a control event for a combination of multiple operations, thereby improving the humanization of the robot.

[0186] S605, in response to the second operation, the robot performs a second control event corresponding to the position information of the second region, the operation type of the second operation, and the force of the second operation acting on the robot.

[0187] For example, if the preset time length is 3 seconds, the interval time length between the first operation and the second operation received by the robot is 3.5 seconds. For example, the second operation is pressing the left armpit of the robot, and the robot can collect portrait information through the camera, the robot can identify the second operation as a tickling event, and the robot can emit a "haha, itchy" sound.

[0188] It can be understood that when the interval time length between the first operation and the second operation is greater than the preset time length, the robot can divide the first operation and the second operation into two touch events and perform different control events. In this way, the robot can perform more control events, thereby improving the humanization of the robot.

[0189] Based on the above scheme, the robot can perform a corresponding control event according to whether the robot receives the second operation within the preset time length after receiving the first operation. In this way, the robot can perform more control events according to different operations, thereby improving the humanization of the robot.

[0190] In other embodiments, the robot can also identify a corresponding touch event without receiving the first operation. For example, Figure 7 When the robot does not obtain the touch parameter collected by the touch sensor and the portrait information collected by the camera, but obtains the change amount of the heading angle, the robot can detect a non-human vibration event (or a falling event). When the robot does not obtain the touch parameter collected by the touch sensor and the change amount of the heading angle, but obtains the portrait information, the robot can detect a user identification event. When the robot does not obtain the touch parameter collected by the touch sensor, but obtains the portrait information and the change amount of the heading angle, the robot can detect a human vibration event.

[0191] Of course, when the robot obtains the touch parameter collected by the touch sensor, the robot can also identify the touch event according to the touch parameter and other operation information (such as the heading angle and the portrait information). For example, Figure 7As shown, when the robot acquires the touch parameter collected by the touch sensor, does not acquire the change amount of the heading angle and the portrait information, the robot can detect the non-human touch event. When the robot acquires the touch parameter collected by the touch sensor and the change amount of the heading angle, does not acquire the portrait information, the robot can detect the non-human heavy hitting event. When the robot acquires the touch parameter collected by the touch sensor and the portrait information, does not acquire the change amount of the heading angle, the robot can detect the human touch event. When the robot acquires the touch parameter collected by the touch sensor, the change amount of the heading angle and the portrait information, the robot can detect the human heavy hitting event.

[0192] It should be noted that the specific introduction of the non-human vibration event, the human vibration event, the user identification event, the non-human heavy hitting event, the human heavy hitting event, the human touch event and the non-human touch event can refer to the description in the above embodiments, which will not be repeated here.

[0193] The above mainly introduces the scheme provided by the embodiments of the present application from the perspective of the robot. It can be understood that the robot includes the hardware structure and / or software module corresponding to the execution of each function in order to realize the above functions. Those skilled in the art should easily realize that the steps of the feedback method of the robot of each example described in combination with the embodiments disclosed in the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or software driven by the robot depends on the specific application and design constraints of the technical solution. The professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0194] The embodiments of the present application can divide the robot into functional modules or functional units according to the above method examples. For example, each functional module or functional unit can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be realized in the form of hardware or software functional module or functional unit. Among them, the division of modules or units in the embodiments of the present application is illustrative, and is only a logical function division. When actually implemented, there can be another division method.

[0195] Some other embodiments of the present application provide a robot (such as Figure 2AThe robot can include a memory and one or more processors. The memory and the processors are coupled. The robot can further include a camera. Alternatively, the robot can be externally connected with a camera. The memory is configured to store computer program codes including computer instructions. When the processors execute the computer instructions, the robot can perform various functions or steps performed by the robot in the above method embodiments. The structure of the robot can refer to the structure of the robot 202 shown in Figure 2A The structure of the robot 202 shown in

[0196] The embodiments of the present application further provide a chip system, as shown in Figure 8 The chip system includes at least one processor 801 and at least one interface circuit 802. The processor 801 and the interface circuit 802 can be interconnected through a line. For example, the interface circuit 802 can be configured to receive signals from other devices (for example, the memory of the robot). For another example, the interface circuit 802 can be configured to send signals to other devices (for example, the processor 801). For example, the interface circuit 802 can read instructions stored in the memory and send the instructions to the processor 801. When the instructions are executed by the processor 801, the robot (for example, the robot 202 shown in Figure 2A The chip system can further include other discrete devices, which are not limited in the embodiments of the present application.

[0197] The embodiments of the present application further provide a computer storage medium including computer instructions, when the computer instructions are run on the above robot (for example, the robot 202 shown in Figure 2A The computer instructions make the robot perform various functions or steps performed by the robot in the above method embodiments.

[0198] The embodiments of the present application further provide a computer program product, when the computer program product is run on a computer, makes the computer perform various functions or steps performed by the robot in the above method embodiments.

[0199] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions.

[0200] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are merely illustrative, for example, the division of the modules or units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another apparatus, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or other forms.

[0201] The units described as separate components can or can not be physically separate, and the components shown as units can be one physical unit or a plurality of physical units, that is, can be located in one place or can be distributed to a plurality of different places. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0202] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0203] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application essentially or the parts that make contributions to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing an apparatus (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0204] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any change or replacement within the technical scope disclosed in the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A feedback method of a robot characterized by, The application is applied to a robot, an inertial measurement unit (IMU) and a camera are installed in the robot, a plurality of first preset areas inside a shell of the robot are each provided with a touch sensor, the touch sensor is used to collect an operation acting on the robot, the IMU is used to collect a heading angle of the robot, and the camera is used to collect an image; the method comprises the following steps: The robot receives a first operation acting on a first area, the first area is any area in the plurality of first preset areas; The robot acquires position information of the first area, an operation type of the first operation and a first offset, the first offset is used to indicate an offset of the heading angle of the robot after the robot receives the first operation, and the first offset is used to reflect a force degree of the first operation acting on the robot; In response to the first operation, the robot performs a first control event corresponding to the position information of the first area, the operation type of the first operation and the force degree of the first operation acting on the robot based on an identification strategy and a feedback strategy, the first control event is an anthropomorphic event; wherein if the first offset is greater than a preset offset threshold, the first operation is a heavy operation; if the first offset is less than the preset offset threshold, the first operation is a light operation; the force degree corresponding to the heavy operation is greater than the force degree corresponding to the light operation; the identification strategy is used to reflect a corresponding relationship between operation information generated by the operation received by the robot and a touch event, and the feedback strategy is used to reflect a corresponding relationship between the touch event and the control event; In response to the first operation, if the robot collects portrait information, the robot determines that the first control event is a control event triggered by a human being; If the robot receives a second operation acting on a second area within a preset time period after receiving the first operation; The robot acquires position information of the second area, an operation type of the second operation and a second offset; wherein the second offset is a difference between a second heading angle of the robot and a second initial heading angle of the robot, the second heading angle is a heading angle of the robot after the robot receives the second operation, the second initial heading angle is a heading angle of the robot before the robot receives the second operation, and the second offset is used to reflect a force degree of the second operation acting on the robot; In response to the first operation and the second operation, the robot performs a third control event corresponding to the position information of the first area, the operation type of the first operation and the force degree of the first operation acting on the robot, the position information of the second area, the operation type of the second operation and the force degree of the second operation acting on the robot.

2. The method of claim 1, wherein, The robot acquires the first offset, comprising: The robot obtains a first heading angle and a first initial heading angle, the first heading angle being a heading angle of the robot after the robot receives the first operation, and the first initial heading angle being a heading angle of the robot before the robot receives the first operation. The robot calculates a difference between the first heading angle and the first initial heading angle to obtain the first offset.

3. The method according to claim 1 or 2, characterized in that, The head of the robot and / or the chest of the robot is provided with the IMU.

4. The method according to claim 1 or 2, characterized in that, The plurality of first preset areas inside the shell of the robot correspond to a plurality of second preset areas on the surface of the shell of the robot one by one. The plurality of second preset areas are areas on the surface of the shell of the robot, the frequency of user operation of which is greater than a preset frequency threshold.

5. The method of claim 1, wherein, The portrait information includes a face image and a portrait distance, the portrait distance being used to indicate a distance between the robot and the user. If the robot collects the portrait information, the robot determines that the first control event is a human triggered control event, including: If the robot collects the portrait information and the portrait distance is less than a preset distance threshold, the robot determines that the first control event is the human triggered control event.

6. The method of claim 5, wherein, The method further includes: If the robot collects the portrait information but the portrait distance is greater than the preset distance threshold, the robot determines that the first control event is a non-human triggered control event; or If the robot does not collect the portrait information, the robot determines that the first control event is the non-human triggered control event.

7. The method according to claim 1 or 2, characterized in that, The method further includes: If the robot receives a second operation acting on a second area after a preset time period after receiving the first operation, the second area being any of the plurality of first preset areas; The robot obtains position information of the second area, an operation type of the second operation, and a second offset; In response to the second operation, the robot performs a second control event corresponding to the position information of the second area, the operation type of the second operation, and the force of the second operation acting on the robot.

8. The method of claim 1 or 2, wherein, The touch sensor includes a copper sheet.

9. A robot, characterized in that The robot includes an inertial measurement unit (IMU), a memory, and one or more processors, a plurality of first preset areas inside a shell of the robot are each provided with a touch sensor and a camera, the IMU, the touch sensor, the memory, and the processor are coupled; the touch sensor is used to collect an operation acting on the robot, the IMU is used to collect a heading angle of the robot, and the camera is used to collect an image; the memory is used to store computer program code, the computer program code includes computer instructions, when the computer instructions are executed by the one or more processors, the robot performs the following operations: Receive a first operation acting on a first area, the first area being any of the plurality of first preset areas; obtain position information of the first region, an operation type of the first operation, and a first offset, the first offset being used to indicate an offset of the heading angle after the robot receives the first operation, the first offset being used to reflect a force degree of the first operation acting on the robot; in response to the first operation, perform a first control event corresponding to the position information of the first region, the operation type of the first operation, and the force degree of the first operation acting on the robot based on an identification strategy and a feedback strategy, the first control event being an anthropomorphic event; wherein if the first offset is greater than a preset offset threshold, the first operation is a heavy operation; if the first offset is less than the preset offset threshold, the first operation is a light operation; the force degree corresponding to the heavy operation is greater than the force degree corresponding to the light operation; the identification strategy is used to reflect a corresponding relationship between operation information generated by an operation received by the robot and a touch event, and the feedback strategy is used to reflect a corresponding relationship between a touch event and a control event; in response to the first operation, if the robot collects portrait information, the robot determines that the first control event is a control event triggered by a human being; if the robot receives a second operation acting on a second region within a preset time period after receiving the first operation; the robot obtains position information of the second region, an operation type of the second operation, and a second offset; wherein the second offset is a difference between a second heading angle of the robot and a second initial heading angle of the robot, the second heading angle being a heading angle of the robot after the robot receives the second operation, the second initial heading angle being a heading angle of the robot before the robot receives the second operation, and the second offset being used to reflect a force degree of the second operation acting on the robot; in response to the first operation and the second operation, the robot performs a third control event corresponding to the position information of the first region, the operation type of the first operation, and the force degree of the first operation acting on the robot, the position information of the second region, the operation type of the second operation, and the force degree of the second operation acting on the robot.

10. The robot of claim 9, wherein, When the computer instructions are executed by the one or more processors, the robot performs the following operations: obtain a first heading angle and a first initial heading angle, the first heading angle being a heading angle of the robot after the robot receives the first operation, and the first initial heading angle being a heading angle of the robot before the robot receives the first operation; calculate a difference between the first heading angle and the first initial heading angle to obtain the first offset.

11. The robot according to claim 9 or 10, characterized in that, The IMU is mounted on a head of the robot and / or a chest of the robot.

12. The robot according to claim 9 or 10, characterized in that, The plurality of first preset regions inside the shell of the robot correspond one-to-one to a plurality of second preset regions on the surface of the shell of the robot. The plurality of second preset areas are areas on a surface of a housing of the robot, and a user operation frequency of the areas is greater than a preset frequency threshold.

13. The robot of claim 9, wherein, The portrait information includes a face image and a portrait distance, and the portrait distance is used to indicate a distance between the robot and the user. If the robot collects the portrait information and the portrait distance is less than a preset distance threshold, the first control event is determined as the human triggered control event.

14. The robot of claim 13, wherein, If the robot collects the portrait information but the portrait distance is greater than the preset distance threshold, the first control event is determined as the non-human triggered control event. If the robot does not collect the portrait information, the first control event is determined as the non-human triggered control event. If a second operation acting on a second area is received after a preset time length after the first operation is received, the second area is any one of the plurality of first preset areas. Position information of the second area, an operation type of the second operation, and a second offset are obtained.

15. The robot according to claim 9 or 10, characterized in that, In response to the second operation, a second control event corresponding to the position information of the second area, the operation type of the second operation, and a force of the second operation acting on the robot is executed. The touch sensor includes a copper sheet. The computer instructions, when executed on a robot, cause the robot to perform the method of any one of claims 1-8. ​ 16. The robot according to claim 9 or 10, characterized in that, ​ 17. A computer storage medium, comprising, ​

Images