Human-computer interaction position determination method, device, robot and storage medium

Abstract

The present invention belongs to the field of intelligent control technology, and discloses a method, device, robot and storage medium for determining a human-computer interaction position. The method includes: when a wake-up voice is received, determining the sound source position according to the wake-up voice; determining the human-computer interaction edge according to the sound source position and the parameter configuration information of the robot; determining the standby movement route according to the human-computer interaction edge and the sound source position; and controlling the robot to move to the human-computer interaction position according to the standby movement route to receive the user's operation instructions. Through the above-mentioned method, it is achieved that there is no need to rely on a continuously turned-on camera, and there is no need to perform image recognition and model training and use processes. While saving energy consumption, the robot's calculation steps are also reduced, making the robot control more energy-saving and convenient.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a method, device, robot and storage medium for determining a human-machine interaction position. Background Art

[0002] When the existing intelligent robot receives the user's voice wake-up, it will move towards the user and turn on the camera until the camera captures the user's image. The robot stops and waits for the user's control posture information, and then performs the cleaning task according to the user's control posture. However, when the robot moves towards the user, the camera needs to collect image information in real time and recognize each collected image information. This process occupies the system process, reduces the robot's computing power, and wastes electricity when the moving distance is long.

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

[0004] The main purpose of the present invention is to provide a method, device, robot and storage medium for determining the position of human-machine interaction, aiming to solve the technical problems of serious energy consumption and complex algorithms in the automatic standby process of the robot in the prior art.

[0005] To achieve the above object, the present invention provides a method for determining a human-computer interaction position, the method comprising the following steps:

[0006] When a wake-up voice is received, determining a sound source position according to the wake-up voice;

[0007] Determining a human-machine interaction edge according to the sound source position and parameter configuration information of the robot;

[0008] Determine a standby moving route according to the human-machine interaction edge and the sound source position;

[0009] The robot is controlled to move to the human-machine interaction position according to the standby movement route to receive the user's operation instruction.

[0010] Optionally, when a wake-up voice is received, determining a sound source position according to the wake-up voice includes:

[0011] When the wake-up voice is received, the audio collection information collected by the audio collector on the robot is retrieved, where the audio collector includes a first audio collector and a second audio collector;

[0012] Determine, according to the audio collection information, a first collection time and a first sound intensity collected by the first audio collector;

[0013] Determine a second collection time and a second sound intensity collected by the second audio collector according to the audio collection information;

[0014] The sound source position is determined according to the first acquisition time, the second acquisition time, the first sound intensity, and the second sound intensity.

[0015] Optionally, determining the sound source position according to the first acquisition time, the second acquisition time, the first sound intensity, and the second sound intensity includes:

[0016] Determine time difference information according to the first acquisition time and the second acquisition time;

[0017] Determine sound intensity difference information according to the first sound intensity and the second sound intensity;

[0018] Determine a first estimated sound source position according to the time difference information;

[0019] Determine a second estimated sound source position according to the sound intensity difference information;

[0020] The first estimated sound source position and the second estimated sound source position are fitted to determine the sound source position.

[0021] Optionally, the parameter configuration information includes a maximum elevation angle, a maximum depression angle, a height above the ground, and a preset recognition height for recognizing a user control posture of a visual sensor of the robot, and determining the human-machine interaction edge according to the sound source position and the parameter configuration information of the robot includes:

[0022] Determine a first horizontal detection distance according to the maximum depression angle and the height above the ground;

[0023] Determining a second horizontal detection distance according to the maximum elevation angle and the preset recognition height;

[0024] determining a target detection distance according to the first horizontal detection distance and the second horizontal detection distance;

[0025] The human-computer interaction edge is determined according to the target detection distance and the sound source position.

[0026] Optionally, the first horizontal detection distance is calculated using the following formula:

[0027] r1=H1*tan(90-θ1);

[0028] Wherein, r1 is the first horizontal detection distance, H1 is the height above the ground, and θ1 is the maximum depression angle;

[0029] The second level detection distance is calculated using the following formula:

[0030] r2=(H2-H1) / tan(θ2);

[0031] Among them, r2 is the second horizontal detection distance, H1 is the height from the ground, H2 is the first vertical distance, and θ2 is the maximum elevation angle.

[0032] Optionally, the target detection distance is calculated using the following formula:

[0033] d = r1 + (r2 - r1) / 2;

[0034] Wherein, d is the target detection distance, r1 is the first horizontal detection distance, and r2 is the second horizontal detection distance.

[0035] Optionally, determining the standby moving route according to the human-computer interaction edge and the sound source position includes:

[0036] Select N candidate endpoints from the human-computer interaction edge;

[0037] Determining N alternative routes according to the N alternative destinations and the current position of the robot;

[0038] The shortest candidate route is selected from the N candidate routes as the standby moving route.

[0039] In addition, to achieve the above-mentioned purpose, the present invention further proposes a human-computer interaction position determination device, the human-computer interaction position determination device comprising:

[0040] A sound source localization module, configured to determine the sound source position according to the wake-up voice when a wake-up voice is received;

[0041] An edge computing module, used to determine the human-computer interaction edge according to the sound source position;

[0042] A route making module, used for determining a standby moving route according to the human-machine interaction edge;

[0043] The automatic control module is used to control the robot to move to the human-machine interaction position according to the standby movement route to receive the user's operation instruction.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes a robot, which includes: a memory, a processor, and a human-computer interaction position determination program stored in the memory and executable on the processor, wherein the human-computer interaction position determination program is configured to implement the steps of the human-computer interaction position determination method as described above.

[0045] In addition, to achieve the above objectives, the present invention also proposes a storage medium, on which a human-computer interaction position determination program is stored, and when the human-computer interaction position determination program is executed by a processor, the steps of the human-computer interaction position determination method described above are implemented.

[0046] When the present invention receives a wake-up voice, the sound source position is determined according to the wake-up voice; the human-machine interaction edge is determined according to the sound source position and the parameter configuration information of the robot; the standby movement route is determined according to the human-machine interaction edge and the sound source position; and the robot is controlled to move to the human-machine interaction position according to the standby movement route to receive the user's operation instructions. In this way, the sound source position of the user's wake-up voice is determined according to the wake-up voice, and then the human-machine interaction edge is determined according to the sound source position, so as to automatically determine the best standby movement route, and then the robot is controlled to automatically move to the human-machine interaction position according to the standby movement route to receive the user's operation instructions. In this way, it does not rely on the camera that is continuously turned on, and reduces the robot's calculation steps while saving energy consumption, making the robot control more energy-saving and convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the structure of a robot in a hardware operating environment involved in an embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram of the flow chart of the first embodiment of the method for determining the human-computer interaction position of the present invention;

[0049] Figure 3 It is a flow chart of the second embodiment of the method for determining a human-computer interaction position of the present invention;

[0050] Figure 4 This is a schematic diagram of calculating the first horizontal detection distance of an embodiment of a method for determining a human-computer interaction position according to the present invention;

[0051] Figure 5 This is a schematic diagram of calculating the second horizontal detection distance of an embodiment of a method for determining a human-computer interaction position according to the present invention;

[0052] Figure 6 This is a schematic diagram of the target detection range of an embodiment of the method for determining a position of human-computer interaction of the present invention;

[0053] Figure 7 This is a structural block diagram of the first embodiment of the human-computer interaction position determination device of the present invention.

[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0056] Reference Figure 1 , Figure 1 A schematic diagram of the robot structure of the hardware operating environment involved in the embodiment of the present invention.

[0057] like Figure 1 As shown, the robot may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0058] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the robot, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0059] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a human-computer interaction position determination program.

[0060] exist Figure 1 In the robot shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the robot of the present invention includes a processor 1001 and a memory 1005, and the robot calls the human-computer interaction position determination program stored in the memory 1005 through the processor 1001, and executes the human-computer interaction position determination method provided by an embodiment of the present invention.

[0061] The embodiment of the present invention provides a method for determining a human-computer interaction position, referring to Figure 2 , Figure 2The figure is a flow chart of a first embodiment of a method for determining a human-computer interaction position according to the present invention.

[0062] In this embodiment, the method for determining a human-computer interaction position includes the following steps:

[0063] Step S10: When a wake-up voice is received, the sound source position is determined according to the wake-up voice.

[0064] It should be noted that the executor of this embodiment is a robot, specifically a robot that can collect voice information and perform automatic control and movement.

[0065] It should be understood that currently when a robot or other automatically controlled robot automatically moves toward a user to achieve standby, it moves by turning on the camera in real time. When human body parts appear in the picture captured by the camera, it is determined that it has reached the standby position. However, in this way, the robot needs to keep the camera on for video and image acquisition while moving, which will consume a lot of energy and reduce the robot's battery life. In addition, to determine whether human body parts appear in the captured picture, the model used for image recognition needs to be pre-trained. A lot of calculations will also be performed during the recognition process, which will greatly occupy the robot's system process, resulting in the risk of slow system response and system jams.

[0066] Therefore, in this embodiment, the human-computer interaction edge is automatically determined according to the sound source position, and then the standby movement route is determined based on the human interaction edge, so as to control the robot to move to the human-computer interaction position, thereby realizing image acquisition without relying on the camera and there is no need to turn on the camera. The optimal standby movement route is automatically determined according to the sound source position, so as to reach the human-computer interaction position for standby, which greatly reduces the energy consumption of the robot and does not require tedious calculations of image recognition to determine whether the human-computer interaction position has been reached, thereby reducing the computing pressure of the system, making the system run more smoothly, and improving the user experience.

[0067] In a specific implementation, the wake-up voice may be a voice message or a password of any length and content preset by the user, and this embodiment does not impose any limitation on this.

[0068] It should be noted that when the audio acquisition device mounted on the robot body collects audio, it first determines whether the received audio is a wake-up voice. If it is determined to be a wake-up voice, the sound source position is determined based on the wake-up voice.

[0069] Furthermore, in order to accurately determine the position of the sound source according to the wake-up voice, so that the subsequent calculation of the human-computer interaction edge is more accurate, step S10 includes: when the wake-up voice is received, calling the audio collection information collected by the audio collector on the robot, the audio collector including a first audio collector and a second audio collector; determining the first collection time and the first sound intensity collected by the first audio collector according to the audio collection information; determining the second collection time and the second sound intensity collected by the second audio collector according to the audio collection information; determining the sound source position according to the first collection time, the second collection time, the first sound intensity and the second sound intensity.

[0070] It should be understood that the audio collector refers to an audio collection device mounted on the body of the robot, which may be a microphone, or other devices that can achieve this function.

[0071] In a specific implementation, the first audio collector and the second audio collector are both audio collection devices mounted on the body of the robot, and the first audio collector and the second audio collector are audio collectors arranged at different positions on the body. The first audio collector and the second audio collector can be any number of microphone matrices or microphone head matrices, and this embodiment does not limit this.

[0072] It should be noted that the audio collection information refers to the audio information of the wake-up voice collected by each audio collector.

[0073] It should be understood that determining the first collection time and the first sound intensity collected by the first audio collector according to the audio collection information means: extracting the moment when the sound is collected by the first audio collector from the audio collection information as the first collection time, and the sound intensity collected by the first audio collector as the first sound intensity.

[0074] In a specific implementation, determining the second collection time and the second sound intensity collected by the second audio collector according to the audio collection information means: extracting the moment when the sound is collected by the second audio collector from the audio collection information as the second collection time, and the sound intensity collected by the second audio collector as the second sound intensity.

[0075] It should be noted that determining the sound source position based on the first acquisition time, the second acquisition time, the first sound intensity and the second sound intensity means: determining the first estimated sound source position based on the time difference between the first acquisition time and the second acquisition time, and then determining the second estimated sound source position based on the intensity difference between the first sound intensity and the second sound intensity, and then fitting the first estimated sound source position and the second estimated sound source position to obtain a more accurate sound source position.

[0076] In this way, the sound source position can be accurately determined based on the time and sound intensity of the audio collected by the two audio collectors, so that the determination of the sound source position has a more accurate calculation and judgment basis, and the subsequent determination of the human-computer interaction edge and the standby movement route is more accurate and optimal.

[0077] Furthermore, in order to further determine and fit the determined sound source position through the two judgment criteria of time difference and sound intensity difference, the step of determining the sound source position according to the first acquisition time, the second acquisition time, the first sound intensity and the second sound intensity includes: determining the time difference information according to the first acquisition time and the second acquisition time; determining the sound intensity difference information according to the first sound intensity and the second sound intensity; determining the first estimated sound source position according to the time difference information; determining the second estimated sound source position according to the sound intensity difference information; and fitting the first estimated sound source position and the second estimated sound source position to determine the sound source position.

[0078] It should be understood that the time difference information refers to the difference between the first acquisition time and the second acquisition time, that is, the time difference between the first audio collector and the second audio collector receiving the audio.

[0079] In a specific implementation, the sound intensity difference information refers to the difference in sound intensity between the audio collected by the first audio collector and the audio collected by the second audio collector.

[0080] It should be noted that determining the first estimated sound source position based on the time difference information means: based on the principle of binaural effect and the positions of the first audio collector and the second audio collector, combined with the propagation speed of sound waves in the air, determining the sound source position as the first estimated sound source position.

[0081] It should be understood that determining the second estimated sound source position based on the sound intensity difference information means: determining the sound source position as the second estimated sound source position based on the difference in sound intensity between the audio collected by the first audio collector and the second audio collector. Specifically, if a sound comes from the central axis directly in front of the first audio collector and the second audio collector, then the sound intensity of the sound reaching the first audio collector and the second audio collector should also be equal. Whenever there is a deviation, it will lead to a difference in sound intensity, and then the second estimated sound source position can be determined.

[0082] In a specific implementation, fitting the first estimated sound source position and the second estimated sound source position to determine the sound source position means: spatially fitting the first estimated sound source position and the second estimated sound source position, and taking the middle point of the line connecting the first estimated sound source position and the second estimated sound source position as the sound source position.

[0083] In this way, the estimated sound source position is calculated based on the time difference and the sound intensity difference, and then the two estimated sound source positions are fitted to obtain the final sound source position, making the determination of the sound source position more accurate.

[0084] Step S20: determining the human-machine interaction edge according to the sound source position and the parameter configuration information of the robot.

[0085] It should be noted that the human-machine interaction edge refers to the curve edge formed by the maximum distance from the user that the robot can recognize the user's control gesture when the robot interacts with the user. Since the robot can move to any position of the user, a circular curve can be determined with the sound source position as the center and the distance from the user's control gesture that the robot can recognize as the radius. This circular curve is the human-machine interaction edge.

[0086] It should be understood that determining the human-computer interaction edge according to the sound source position and the parameter configuration information of the robot means: determining the first horizontal detection distance according to the maximum elevation angle and the height above the ground in the parameter configuration information, the first horizontal detection distance being: when the robot's visual sensor is at the maximum elevation angle, the robot can accurately identify the farthest horizontal distance of the control posture, where the farthest horizontal distance is the farthest distance at which the robot can identify the user's footstep posture and / or hand posture; and determining the second horizontal detection distance according to the maximum depression angle combined with the height above the ground and the preset recognition height, the second horizontal detection distance being: when the robot's visual sensor is at the maximum depression angle, the robot can accurately identify the closest horizontal distance of the control posture, where the closest horizontal distance is the closest distance at which the robot can identify the user's footstep posture, thereby determining the human-computer interaction edge in combination with the first horizontal detection distance and the second horizontal detection distance.

[0087] Exemplarily, any value greater than the first horizontal detection distance and less than the second horizontal detection distance can be selected as the target detection distance, and a circular curve can be determined with the sound source position as the center and the target detection distance as the radius, and the circular curve can be used as the human-computer interaction edge, so that the robot can more accurately and completely capture the user's control posture at any position on the human-computer interaction edge.

[0088] Step S30: determining a standby moving route according to the human-computer interaction edge and the sound source position.

[0089] In a specific implementation, the standby movement route refers to the route followed by the robot when moving from the current position to the human-machine interaction position. Specifically, the standby movement route is the shortest route among the routes of the robot to various points on the human-machine interaction edge.

[0090] Furthermore, in order to select the optimal standby movement route and thereby reduce the movement distance and movement time of the robot, step S30 includes: selecting N alternative end points from the human-computer interaction edge; determining N alternative routes based on the alternative end points and the current position of the robot; and selecting the alternative route with the shortest distance from the N alternative routes as the standby movement route.

[0091] It should be noted that the alternative endpoints can be the coordinates of multiple position points randomly selected from the human-computer interaction edge, or N points uniformly selected from the curve of the human-computer interaction edge as the alternative endpoints, that is, the distances between adjacent points are the same, so as to avoid the N randomly selected alternative endpoints being too concentrated.

[0092] It should be understood that determining N alternative routes based on the alternative endpoints and the current position of the robot means that N alternative routes can be obtained by taking the current position of the robot as the starting point and each alternative endpoint as the endpoint.

[0093] In a specific implementation, selecting the shortest alternative route from the N alternative routes as the standby moving route means: calculating the distances of the various alternative routes and selecting the shortest alternative route as the standby moving route.

[0094] In this way, the shortest distance route from the robot's current position to any point on the human-computer interaction edge is determined based on the human-computer interaction edge, which reduces the robot's moving distance and moving time when going to standby, reduces energy loss, and improves the user experience.

[0095] Step S40: Control the robot to move to the human-machine interaction position according to the standby movement route to receive the user's operation instruction.

[0096] It should be noted that controlling the robot to move to the human-computer interaction position according to the standby movement route to receive the user's operation instructions means: controlling the robot to move according to the set standby movement route until the end of the standby movement route, that is, the intersection of the standby movement route and the human-computer interaction edge. At this time, the robot's visual sensor is adjusted to an angle that can collect the user's control posture information to receive the user's control posture information.

[0097] This embodiment determines the sound source position according to the wake-up voice when the wake-up voice is received; determines the human-machine interaction edge according to the sound source position and the parameter configuration information of the robot; determines the standby movement route according to the human-machine interaction edge and the sound source position; and controls the robot to move to the human-machine interaction position according to the standby movement route to receive the user's operation instructions. In this way, the sound source position of the user's wake-up voice is determined according to the wake-up voice, and then the human-machine interaction edge is determined according to the sound source position, so as to automatically determine the best standby movement route, and then the robot is controlled to automatically move to the human-machine interaction position according to the standby movement route to receive the user's operation instructions. In this way, it does not rely on the camera that is continuously turned on, and there is no need to perform image recognition and model training and use processes. While saving energy consumption, it also reduces the robot's calculation steps, making the robot control more energy-saving and convenient.

[0098] refer to Figure 3 , Figure 3 It is a flow chart of a second embodiment of a method for determining a human-computer interaction position according to the present invention.

[0099] Compared with the first embodiment mentioned above, in this embodiment, the robot can determine the maximum distance from the user when it can detect the control posture of the user's hand based on the information of the maximum upward elevation angle and the maximum downward depression angle of the visual sensor carried by itself, and then determine the most accurate human-computer interaction edge. This can make the robot go to the predetermined standby position more accurately, and can minimize the moving distance and moving time of the robot to the target standby position, thereby improving the user experience.

[0100] In this embodiment, the parameter configuration information in step S20 in the above embodiment 1 includes the maximum elevation angle, maximum depression angle, height from the ground and the preset recognition height for recognizing the user control posture of the robot's visual sensor. Step S20 may include:

[0101] Step S201: determining a first horizontal detection distance according to the maximum depression angle and the height above the ground.

[0102] It should be noted that the height above the ground refers to the height of the lowest end of the visual sensor from the ground when the visual sensor is installed on the robot body. The visual sensor refers to the image acquisition sensor carried by the robot body, which can include various types of cameras and other equipment.

[0103] It should be understood that the maximum elevation angle refers to the maximum angle at which the camera of the visual sensor is flipped upward, and the maximum depression angle refers to the maximum angle at which the camera of the visual sensor is flipped downward.

[0104] In a specific implementation, determining the first horizontal detection distance according to the maximum depression angle and the height above the ground means that the visual blind spot distance of the robot can be determined according to the maximum depression angle of the visual sensor and the height above the ground of the visual sensor, that is, Figure 4 As shown in the first horizontal detection distance r1, it can be understood that the area determined by the vertical projection point of the robot's center O0 on the ground as the center and the sum of r1+r0 as the radius is a visual blind spot that the robot cannot recognize, wherein r0 is the distance between the center of the robot and the visual sensor. At this time, if the user stands in this visual blind spot, the robot cannot see the user's foot posture, and then the user cannot control the robot through the foot posture, and human-computer interaction cannot be achieved.

[0105] For details, see Figure 4 The right side of the figure is a schematic diagram of the robot, point O1 is the robot's visual sensor, θ1 is the maximum depression angle of the visual sensor, and H1 is the height from the ground. Therefore, the calculation formula for the first horizontal detection distance r1 is: r1=H1*tan(90-θ1). For example: if H1 is 0.2 meters and θ1 is 45°, then r1 is calculated to be 0.2 meters.

[0106] Step S202: determining a second horizontal detection distance according to the maximum elevation angle and the preset recognition height.

[0107] It should be noted that the preset recognition height refers to the height of the user's hand from the ground set by the user in advance. When the user makes a control gesture, the default height can be any height set by the user in advance, which can generally be 1.2 meters. The control gesture includes but is not limited to hand gestures and other body movements of the user.

[0108] In the specific implementation, Figure 5 The figure shows a schematic diagram of calculating the second horizontal detection distance, wherein the right side is a schematic diagram of the robot, point O1 is the robot's visual sensor, θ2 is the maximum elevation angle of the visual sensor, H1 is the height from the ground, and H2 is the preset recognition height. The calculation formula for the second horizontal detection distance r2 is: r2 = (H2-H1) / tan(θ2). For example: when H2 is 1.2 meters, H1 is 0.2 meters, and θ1 is 45°, then r2 is calculated to be 1 meter.

[0109] Step S203: determining a target detection distance according to the first horizontal detection distance and the second horizontal detection distance.

[0110] It should be noted that the target detection distance refers to the distance obtained based on the first level detection distance and the second level detection distance. For example, see Figure 6, the calculation formula of the target detection distance can be: d=r1+(r2-r1) / 2, where d is the target detection distance, r1 is the first horizontal detection distance, and r2 is the second horizontal detection distance. When the distance between the robot and the sound source is the target detection distance, the robot can collect a complete control posture image.

[0111] In order to obtain the optimal human-computer interaction edge, the steps of determining the human-computer interaction edge according to the first horizontal detection distance, the second horizontal detection distance and the sound source position include: determining a first horizontal detection range at the sound source position according to the first horizontal detection distance; determining a second horizontal detection range at the sound source position according to the second horizontal detection distance; determining a target detection range according to the first horizontal detection range and the second horizontal detection range; and determining a target detection distance according to the target detection range.

[0112] In this way, an optimal human-computer interaction edge composed of positions capable of completely collecting the user's control posture information is achieved according to the first horizontal detection range and the second horizontal detection range, thereby improving the user experience.

[0113] Step S204: determining a human-computer interaction edge according to the target detection distance and the sound source position.

[0114] See also Figure 6 , the circular trajectory that can be obtained with the sound source position O as the center and the target detection distance d as the radius is the target standby curve, that is, the human-computer interaction edge, which is Figure 6 The dotted track in .

[0115] Compared with the human-computer interaction edge determination scheme in the above-mentioned embodiment, the human-computer interaction edge determined in this embodiment is better, which can avoid the user being too close or too far away from the robot due to calculation errors, thereby ensuring that the robot can capture the user's control posture more accurately and completely.

[0116] This embodiment determines the first horizontal detection distance according to the maximum depression angle and the height above the ground; determines the second horizontal detection distance according to the maximum elevation angle and the preset recognition height; determines the target detection distance according to the first horizontal detection distance and the second horizontal detection distance; and determines the human-machine interaction edge according to the target detection distance and the sound source position. The robot can determine the farthest distance from the user when the user's control posture can be detected based on the information of the maximum upward elevation angle and the maximum downward depression angle of the visual sensor carried by itself, and then determine the most accurate human-machine interaction edge, which can make the robot more accurate in going to the predetermined standby position, can minimize the moving distance and moving time of the robot to the target standby position, and improve the user experience.

[0117] In addition, an embodiment of the present invention further provides a storage medium, on which a human-computer interaction position determination program is stored. When the human-computer interaction position determination program is executed by a processor, the steps of the human-computer interaction position determination method described above are implemented.

[0118] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0119] Reference Figure 7 , Figure 7 This is a structural block diagram of the first embodiment of the human-computer interaction position determination device of the present invention.

[0120] like Figure 7 As shown, the human-computer interaction position determination device proposed in the embodiment of the present invention includes:

[0121] The sound source localization module 10 is used to determine the sound source position according to the wake-up voice when the wake-up voice is received.

[0122] The edge computing module 20 is used to determine the human-machine interaction edge according to the sound source position and the parameter configuration information of the robot.

[0123] The route making module 30 is used to determine a standby moving route according to the human-machine interaction edge and the sound source position.

[0124] The automatic control module 40 is used to control the robot to move to the human-machine interaction position according to the standby movement route to receive the user's operation instruction.

[0125] When the present embodiment receives a wake-up voice, the sound source position is determined according to the wake-up voice; the human-machine interaction edge is determined according to the sound source position and the parameter configuration information of the robot; the standby movement route is determined according to the human-machine interaction edge and the sound source position; and the robot is controlled to move to the human-machine interaction position according to the standby movement route to receive the user's operation instructions. In this way, the sound source position of the user's wake-up voice is determined according to the wake-up voice, and then the human-machine interaction edge is determined according to the sound source position, so as to automatically determine the best standby movement route, and then the robot is controlled to automatically move to the human-machine interaction position according to the standby movement route to receive the user's operation instructions. In this way, it is not necessary to rely on the camera that is continuously turned on, and there is no need to perform image recognition and model training and use processes. While saving energy consumption, the robot's calculation steps are also reduced, making the robot control more energy-saving and convenient.

[0126] In one embodiment, the sound source localization module 10 is further used to retrieve audio collection information collected by an audio collector on the robot when a wake-up voice is received, the audio collector including a first audio collector and a second audio collector; determine a first collection time and a first sound intensity collected by the first audio collector according to the audio collection information; determine a second collection time and a second sound intensity collected by the second audio collector according to the audio collection information; and determine the sound source position according to the first collection time, the second collection time, the first sound intensity, and the second sound intensity.

[0127] In one embodiment, the sound source localization module 10 is further used to determine time difference information based on the first acquisition time and the second acquisition time; determine sound intensity difference information based on the first sound intensity and the second sound intensity; determine a first estimated sound source position based on the time difference information; determine a second estimated sound source position based on the sound intensity difference information; and fit the first estimated sound source position and the second estimated sound source position to determine the sound source position.

[0128] In one embodiment, the edge computing module 20 is further used to determine a first horizontal detection distance based on the maximum depression angle and the height above the ground; determine a second horizontal detection distance based on the maximum elevation angle and the preset recognition height; determine a target detection distance based on the first horizontal detection distance and the second horizontal detection distance; and determine a human-computer interaction edge based on the target detection distance and the sound source position.

[0129] In one embodiment, the edge computing module 20 is also used to calculate the first horizontal detection distance using the following formula: r1=H1*tan(90-θ1); wherein r1 is the first horizontal detection distance, H1 is the height above the ground, and θ1 is the maximum depression angle; the second horizontal detection distance is calculated using the following formula: r2=(H2-H1) / tan(θ2); wherein r2 is the second horizontal detection distance, H1 is the height above the ground, H2 is the first vertical distance, and θ2 is the maximum elevation angle.

[0130] In one embodiment, the edge computing module 20 is also used to calculate the target detection distance using the following formula: d=r1+(r2-r1) / 2; wherein d is the target detection distance, r1 is the first horizontal detection distance, and r2 is the second horizontal detection distance.

[0131] In one embodiment, the route planning module 30 is also used to select N alternative destinations from the human-machine interaction edge; determine N alternative routes based on the alternative destinations and the current position of the robot; and select the alternative route with the shortest distance from the N alternative routes as the standby moving route.

[0132] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0133] Since the present device adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0134] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0135] In addition, for technical details not fully described in this embodiment, reference may be made to the method for determining a human-computer interaction position provided in any embodiment of the present invention, and will not be repeated here.

[0136] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0137] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes N instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0139] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for determining a human-computer interaction position, characterized in that: The method for determining a human-computer interaction position comprises: When a wake-up voice is received, determining a sound source position according to the wake-up voice; Determine a human-machine interaction edge according to the sound source position and the parameter configuration information of the robot, wherein the human-machine interaction edge is a curve edge formed by the farthest distance from the user at which the robot can recognize the user's control posture when the robot interacts with the user, that is, the human-machine interaction edge is a circular curve with the sound source position as the center and the target detection distance at which the robot can recognize the user's control posture as the radius, and the target detection distance is a distance greater than the first horizontal detection distance and less than the second horizontal detection distance; Determine a standby moving route according to the human-machine interaction edge and the sound source position; The robot is controlled to move to the human-machine interaction position according to the standby movement route to receive the user's operation instruction.

2. The method according to claim 1, characterized in that When the wake-up voice is received, determining the sound source position according to the wake-up voice includes: When the wake-up voice is received, the audio collection information collected by the audio collector on the robot is retrieved, where the audio collector includes a first audio collector and a second audio collector; Determine, according to the audio collection information, a first collection time and a first sound intensity collected by the first audio collector; Determine a second collection time and a second sound intensity collected by the second audio collector according to the audio collection information; The sound source position is determined according to the first acquisition time, the second acquisition time, the first sound intensity, and the second sound intensity.

3. The method according to claim 2, characterized in that The determining the sound source position according to the first acquisition time, the second acquisition time, the first sound intensity, and the second sound intensity includes: Determine time difference information according to the first acquisition time and the second acquisition time; Determine sound intensity difference information according to the first sound intensity and the second sound intensity; Determine a first estimated sound source position according to the time difference information; Determine a second estimated sound source position according to the sound intensity difference information; The first estimated sound source position and the second estimated sound source position are fitted to determine the sound source position.

4. The method according to claim 1, characterized in that The parameter configuration information includes a maximum elevation angle, a maximum depression angle, a height from the ground, and a preset recognition height for recognizing a user control posture of a robot's visual sensor, and determining the human-machine interaction edge according to the sound source position and the parameter configuration information of the robot includes: Determine a first horizontal detection distance according to the maximum depression angle and the height above the ground; Determining a second horizontal detection distance according to the maximum elevation angle and the preset recognition height; determining a target detection distance according to the first horizontal detection distance and the second horizontal detection distance; The human-computer interaction edge is determined according to the target detection distance and the sound source position.

5. The method according to claim 4, characterized in that The first horizontal detection distance is calculated using the following formula: r1=H1*tan(90-θ1); Wherein, r1 is the first horizontal detection distance, H1 is the height above the ground, and θ1 is the maximum depression angle; The second level detection distance is calculated using the following formula: r2=(H2-H1) / tan(θ2); Among them, r2 is the second horizontal detection distance, H1 is the height from the ground, H2 is the first vertical distance, and θ2 is the maximum elevation angle.

6. The method according to claim 4, characterized in that The target detection distance is calculated using the following formula: d=r1+（r2-r1） / 2； Wherein, d is the target detection distance, r1 is the first horizontal detection distance, and r2 is the second horizontal detection distance.

7. The method according to any one of claims 1 to 6, characterized in that The step of determining the standby moving route according to the human-machine interaction edge and the sound source position includes: Select N candidate endpoints from the human-computer interaction edge; Determining N alternative routes according to the N alternative destinations and the current position of the robot; The shortest candidate route is selected from the N candidate routes as the standby moving route.

8. A human-computer interaction position determination device, characterized in that: The human-computer interaction position determination device comprises: A sound source localization module, configured to determine the sound source position according to the wake-up voice when a wake-up voice is received; an edge computing module, for determining a human-machine interaction edge according to the sound source position, wherein the human-machine interaction edge is a curve edge formed by the farthest distance from the user at which the robot can recognize the user's control posture when the robot interacts with the user, that is, the human-machine interaction edge is a circular curve with the sound source position as the center and the target detection distance at which the robot can recognize the user's control posture as the radius, and the target detection distance is a distance greater than the first horizontal detection distance and less than the second horizontal detection distance; A route making module, used for determining a standby moving route according to the human-machine interaction edge; The automatic control module is used to control the robot to move to the human-machine interaction position according to the standby movement route to receive the user's operation instruction.

9. A robot, characterized in that: The robot comprises: a memory, a processor, and a human-machine interaction position determination program stored in the memory and executable on the processor, wherein the human-machine interaction position determination program is configured to implement the human-machine interaction position determination method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a human-computer interaction position determination program, and when the human-computer interaction position determination program is executed by the processor, the human-computer interaction position determination method according to any one of claims 1 to 7 is implemented.

Images