Robot solicitation control method, device, electronic device and storage medium

Abstract

The present application discloses a robot solicitation control method, device, electronic device and storage medium, belonging to the field of artificial intelligence technology. In the method, the interactive intention characterization data of the target object located in the solicitation range at time t is obtained, and the interactive intention characterization data of the target object at time t at least includes the radial velocity and tangential velocity of the target object. Based on the interactive intention characterization data of the target object at time t, the interactive intention of the target object is analyzed, and based on the interactive intention analysis result of the target object at time t, the solicitation behavior of the robot is controlled. In this way, the solicitation behavior of the robot is controlled based on the interactive intention of the target object located in the solicitation range, and the solicitation method is more reasonable, which is conducive to improving the solicitation success rate of the robot and improving the intelligence level of the robot.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a robot recruitment control method, device, electronic device and storage medium. Background Art

[0002] In recent years, robots have been increasingly used in the service industry. An important role of robots in the service industry is to interact with users, and attracting users is the first step in interacting with users.

[0003] In the related art, the robot solicits users by using a camera to detect all detection objects such as faces and bodies within the robot's field of view, and calculate the distance between each detection object and the robot. If the distance between a detection object and the robot is within the set solicitation range, such as 3 meters or 5 meters, the robot is controlled to make solicitation actions to solicit the corresponding user. However, in reality, not all users who appear in the solicitation range want to interact with the robot, so this solicitation method will make the robot look clumsy and reduce the user experience. Summary of the invention

[0004] The embodiments of the present application provide a robot recruitment control method, device, electronic device and storage medium to solve the problem of unreasonable robot recruitment method in related technologies.

[0005] In a first aspect, an embodiment of the present application provides a robot solicitation control method, comprising:

[0006] Acquire interaction intention characterization data of a target object within the solicitation range at time t, wherein the interaction intention characterization data of the target object at time t at least includes a radial velocity and a tangential velocity of the target object;

[0007] Analyzing the interaction intention of the target object based on the interaction intention representation data of the target object at time t;

[0008] Based on the interaction intention analysis result of the target object, the solicitation behavior of the robot is controlled.

[0009] In some possible implementations, analyzing the interaction intention of the target object based on the interaction intention representation data of the target object at time t includes:

[0010] The interaction intention is analyzed based on the radial speed and tangential speed of the target object to obtain the speed score of the target object at time t. The speed score is used to characterize the level of interaction probability based on the walking trend.

[0011] In some possible implementations, performing interaction intention analysis based on the radial velocity and tangential velocity of the target object to obtain a velocity score of the target object at time t includes:

[0012] Determining a velocity ratio of a tangential velocity to a radial velocity of the target object;

[0013] According to the rule that the speed ratio is negatively correlated with the interaction probability and the tangential speed is positively correlated with the interaction probability, the speed score of the target object at time t is determined.

[0014] In some possible implementations, the interaction intention representation data of the target object at time t also includes any combination of the distance between the target object and the robot, the orientation of the target object, and the length of time the target object stays within the solicitation range;

[0015] Analyzing the interaction intention of the target object based on the interaction intention representation data of the target object at time t, further comprising any combination of the following steps:

[0016] Performing interaction intention analysis based on the distance between the target object and the robot to obtain a distance score of the target object at time t, wherein the distance score is used to characterize the level of interaction probability based on the distance;

[0017] Performing interaction intention analysis based on the orientation of the target object to obtain an orientation score of the target object at time t, wherein the orientation score is used to characterize the level of interaction probability based on the orientation;

[0018] An interaction intention analysis is performed based on the target object's stay time within the solicitation scope to obtain a stay score of the target object at time t, and the stay score is used to characterize the level of interaction probability based on the stay time.

[0019] In some possible implementations, performing interaction intention analysis based on the distance between the target object and the robot to obtain a distance score of the target object at time t includes:

[0020] Determine a distance ratio between the target object and the robot and a preset distance, wherein the preset distance is determined according to a detection limit of a laser radar;

[0021] According to the rule that the distance ratio is negatively correlated with the interaction probability, the distance score of the target object at time t is determined.

[0022] In some possible implementations, performing interaction intention analysis based on the orientation of the target object to obtain the orientation score of the target object at time t includes:

[0023] Determining the score corresponding to the orientation of the target object based on a preset correspondence relationship between the orientation and the score;

[0024] The determined score and the orientation score of the target object at time t-1 are weighted averaged to obtain the orientation score of the target object at time t.

[0025] In some possible implementations, performing interaction intention analysis based on the target object's stay time in the solicitation scope to obtain the target object's stay score at time t includes:

[0026] Determine the product of the distance score of the target object at time t and the target stay interval, where the target stay interval refers to the time difference between time t-1 and time t;

[0027] The sum of the product and the stay score of the target object at time t-1 is determined as the stay score of the target object at time t.

[0028] In some possible implementations, the following further includes:

[0029] Obtaining the interaction intention level of the target object at time t-1, where the interaction intention level is used to characterize the intensity of the interaction intention;

[0030] Based on the interaction intention analysis result of the target object, controlling the solicitation behavior of the robot includes:

[0031] Comparing the interaction intention analysis result of the target object with the intention level transition condition corresponding to the interaction intention level of the target object at time t-1 to determine the interaction intention level of the target object at time t, wherein the intention level transition condition includes at least one of a distance score threshold, a speed score threshold, a direction score threshold, and a stay score threshold;

[0032] Based on the interaction intention level of the target object at time t, the solicitation behavior of the robot is controlled.

[0033] In some possible implementations, if the robot is controlled to recruit the target object, the method further includes:

[0034] After controlling the robot to solicit the target object, the interaction intention level of the target object is set to a preset interaction intention level, and the interaction intention analysis result of the target object is set to a preset result, wherein the preset interaction intention level represents the least intense interaction intention.

[0035] In a second aspect, an embodiment of the present application provides a robot recruitment control device, comprising:

[0036] An acquisition module, used to acquire interaction intention representation data of a target object located within the solicitation range at time t, wherein the interaction intention representation data of the target object at time t at least includes a radial velocity and a tangential velocity of the target object;

[0037] An analysis module, configured to analyze the interaction intention of the target object based on the interaction intention representation data of the target object at time t;

[0038] A control module is used to control the solicitation behavior of the robot based on the interaction intention analysis result of the target object.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein:

[0040] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned robot solicitation control method.

[0041] In a fourth aspect, an embodiment of the present application provides a storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the above-mentioned robot recruitment control method.

[0042] In the embodiment of the present application, the interactive intention characterization data of the target object within the solicitation range at time t is obtained, and the interactive intention characterization data of the target object at time t at least includes the radial velocity and tangential velocity of the target object. Based on the interactive intention characterization data of the target object at time t, the interactive intention of the target object is analyzed, and based on the interactive intention analysis result of the target object at time t, the solicitation behavior of the robot is controlled. In this way, the solicitation behavior of the robot is controlled based on the interactive intention of the target object within the solicitation range, and the solicitation method is more reasonable, which is conducive to improving the solicitation success rate of the robot and improving the intelligence of the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 A schematic diagram of an application scenario of a robot solicitation control method provided in an embodiment of the present application;

[0045] Figure 2 A flowchart of a robot solicitation control method provided in an embodiment of the present application;

[0046] Figure 3A flow chart of a method for analyzing the interaction intention of a target object provided in an embodiment of the present application;

[0047] Figure 4 A flowchart of another robot solicitation control method provided in an embodiment of the present application;

[0048] Figure 5 A schematic diagram of a process of a robot solicitation control method provided in an embodiment of the present application;

[0049] Figure 6 A schematic diagram of the structure of a robot solicitation control device provided in an embodiment of the present application;

[0050] Figure 7 A schematic diagram of the hardware structure of an electronic device for implementing a robot solicitation control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to solve the problem of unreasonable robot recruitment methods in related technologies, the embodiments of the present application provide a robot recruitment control method, device, electronic device and storage medium.

[0052] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0053] Generally, the robot's recruitment range is located in the front. Figure 1 An application scenario diagram of a robot solicitation control method provided in an embodiment of the present application, wherein the robot can track target objects such as target object 1, target object 2, and target object 3 within the solicitation range, and can obtain interaction intention characterization data of each target object, analyze the interaction intention of the target object based on the interaction intention characterization data, and control the robot's solicitation behavior based on the interaction intention analysis result, wherein the target object can be a user, and the interaction intention characterization data of the target object at time t includes at least the radial velocity and tangential velocity of the target object.

[0054] Radial velocity refers to the velocity component of the target object in the direction of the robot's line of sight, that is, the projection of the velocity vector in the direction of the line of sight, also known as visual velocity.

[0055] Tangential velocity is the instantaneous speed of a target object when it moves in a curve. Its direction is along the tangent direction of the motion trajectory, so it is also called tangential velocity.

[0056] In this way, the robot's solicitation behavior is controlled based on the interaction intention of the target object within the solicitation range, and the solicitation method is more reasonable, which is beneficial to improving the robot's solicitation success rate and the robot's intelligence level.

[0057] Figure 2 A flowchart of a robot solicitation control method provided in an embodiment of the present application, the method comprising the following steps.

[0058] In step S201, the interaction intention representation data of the target object within the solicitation range at time t is obtained.

[0059] In specific implementation, at least one target object within the solicitation range can be tracked to obtain the motion state of each target object in real time. The motion state of each target object may include (θ, D, ) These state quantities, where θ refers to the angle between the target object and the robot, D refers to the distance between the target object and the robot, and θ refers to the tangential velocity between the target object and the robot. It is the radial velocity between the target object and the robot.

[0060] Considering that the velocity information of the target object can reflect the interaction probability between the target object and the robot to a certain extent, the interaction intention characterization data of the target object at time t can at least include the radial velocity and tangential velocity of the target object. The position information of the target object can also reflect the interaction probability between the target object and the robot to a certain extent, so the interaction intention characterization data of the target object at time t can also include the distance between the target object and the robot. Moreover, the radial velocity, tangential velocity and distance between the target object and the robot can all be directly obtained from the motion state of the target object at the corresponding time.

[0061] In addition, the probability of the target object interacting with the robot is different when it is facing, facing away from, and facing sideways to the robot, that is, the orientation of the target object can also reflect the probability of interaction between the target object and the robot to a certain extent, so the target object's interaction intention representation data at time t can also include the orientation of the target object. Generally, the orientation of the target object can be obtained by analyzing the orientation of the human body area after successfully tracking the human body area of ​​the target object.

[0062] In addition, the length of time the target object stays within the solicitation range can also reflect the probability of interaction between the target object and the robot to a certain extent, so the target object's interaction intention characterization data at time t can also include the length of time the target object stays within the solicitation range.

[0063] In step S202, the interaction intention of the target object is analyzed based on the interaction intention representation data of the target object at time t.

[0064] See also Figure 3 In a specific implementation, based on the interaction intention representation data of the target object at time t, analyzing the interaction intention of the target object may include any combination of the following steps:

[0065] S301a: Perform interaction intention analysis based on the distance between the target object and the robot to obtain the distance score of the target object at time t.

[0066] Among them, the distance score is used to characterize the interaction probability in terms of distance.

[0067] In specific implementation, the distance ratio between the target object and the robot at time t and the preset distance can be determined, and then the distance score of the target object at time t can be determined according to the rule that the distance ratio is negatively correlated with the interaction probability, wherein the preset distance is determined according to the detection limit of the laser radar.

[0068] For example, the distance score SD(t) of the target object at time t is determined according to the following formula:

[0069]

[0070] Where D(t) is the distance between the target object and the robot at time t, and Dmax is the preset distance.

[0071] S302a: Perform interaction intention analysis based on the radial velocity and tangential velocity of the target object to obtain a velocity score of the target object at time t.

[0072] Among them, the speed score is used to characterize the probability of interaction based on the walking trend.

[0073] In specific implementation, the speed ratio of the tangential speed to the radial speed of the target object at time t can be determined, and then the speed score of the target object at time t can be determined according to the rule that the speed ratio is negatively correlated with the interaction probability and the tangential speed is positively correlated with the interaction probability.

[0074] For example, the speed score SV(t) of the target object at time t is determined according to the following formula:

[0075]

[0076] in, is the tangential velocity of the target object at time t, is the radial velocity of the target object at time t, k1 and k2 are predetermined decimals.

[0077] S303a: Perform interaction intention analysis based on the orientation of the target object to obtain the orientation score of the target object at time t.

[0078] Among them, the orientation score is used to characterize the interaction probability from the perspective of orientation.

[0079] In specific implementation, the score corresponding to the orientation of the target object at time t can be determined based on the corresponding relationship between the preset orientation and the score, and then the determined score and the orientation score of the target object at time t-1 are weighted averaged to obtain the orientation score of the target object at time t.

[0080] For example, the correspondence between the preset orientation and the score is: when facing the robot from the front, the score Bp=3, when facing the robot from the side, the score Bp=1, and when facing the robot from the back, the score Bp=0. Then, the orientation score SP(t) of the target object at time t is:

[0081] SP(t)=λ*Bp(t)+(1-λ)*SP(t-1);

[0082] Among them, Bp(t) is the score corresponding to the orientation of the target object at time t, SP(t-1) is the orientation score of the target object at time t-1, and λ is a predetermined weight, which is generally a decimal.

[0083] S304a: Perform interaction intention analysis based on the target object's stay time within the solicitation scope to obtain the target object's stay score at time t.

[0084] Among them, the stay score is used to characterize the probability of interaction based on the stay duration.

[0085] In some possible implementations, the stay score of the target object at time t may be determined according to the rule that the longer the stay time, the higher the probability of interaction intention.

[0086] For example, the target object's stay score ST(t) at time t is determined according to the following formula:

[0087] ST(t)=k*D(t);

[0088] Where D(t) is the length of time the target object stays within the solicitation range up to time t, and k is a preset proportional factor.

[0089] Considering that the probability of interaction with the robot is different when the target object stays at different positions within the solicitation range, in some possible implementations, the target object's distance score can be combined to determine the target object's stay score at time t.

[0090] In specific implementation, the product of the distance score of the target object at time t and the target stay interval can be determined, where the target stay interval refers to the time difference between time t-1 and time t. Then, the sum of the product and the stay score of the target object at time t-1 is determined as the stay score of the target object at time t.

[0091] For example, the target object's stay score ST(t) at time t is determined according to the following formula:

[0092] ST(t)=dt*SD(t)+ST(t-1);

[0093] Among them, dt is the target stay interval, SD(t) is the distance score of the target object at time t, and ST(t-1) is the stay score of the target object at time t-1.

[0094] It should be noted that in the embodiment of the present application, the interaction intention characterization data of the target object can be determined based on the motion state of each target object obtained in real time, but the update time interval of the motion state will change with the change of the time interval for obtaining the observation data of the target object (such as radar observation data and / or visual observation data). Therefore, for the same target object, the stay interval in different time periods is not necessarily fixed, that is, the time difference between t-2 and t-1 may be the same as or different from the time difference between t-1 and t.

[0095] In addition, it should be noted that when the stay score does not depend on the distance score, there is no strict order relationship between the above S301a-S304a; when the stay score depends on the distance score, there is a order relationship between the above S301a and S304a, but there is still no strict order relationship between S301a-S303a.

[0096] In step S203, based on the analysis result of the interaction intention of the target object, the solicitation behavior of the robot is controlled.

[0097] In specific implementation, the target object's interaction intention level at time t can be determined based on the interaction intention analysis results and the intention level classification conditions. If the target object's interaction intention level at time t is included in the interaction intention level corresponding to the preset solicitation strategy (such as high initiative, medium initiative or low initiative), it is determined that solicitation is triggered, and the robot can be controlled to solicit the target object; if the target object's interaction intention level at time t is not included in the interaction intention level corresponding to the preset solicitation strategy, it is determined that solicitation is not triggered. Among them, the interaction intention level is used to characterize the intensity of the interaction intention, and the intention level classification conditions include at least one of the distance score threshold, the speed score threshold, the orientation score threshold and the stay score threshold.

[0098] Assume that the interaction intention is divided into three levels: high, medium, and low, where:

[0099] The intention level classification condition corresponding to high interaction intention can be: (SD>TH-SD||SV>TH-SV)&&SP>TH-SP, && represents the logical AND operation, || represents the logical OR operation, that is, when the distance score (SD) is greater than the distance score threshold (TH-SD), the speed score (SV) is greater than the speed score threshold (TH-SV), and the orientation score (SP) is greater than the orientation score threshold (TH-SP), it is determined to be a high interaction intention;

[0100] The intention level division condition corresponding to the medium interaction intention can be: SD>TH-SD||SV>TH-SV||ST>TH-ST, that is, when the distance score (SD) is greater than the distance score threshold (TH-SD), the speed score (SV) is greater than the speed score threshold (TH-SV), and the stay score (ST) is greater than the stay threshold, it is determined to be a medium interaction intention;

[0101] The intention level division condition corresponding to low interaction intention can be: SD≤TH-SD&&SV≤TH-SV, that is, when the distance score (SD) is not greater than the distance score threshold (TH-SD) and the speed score (SV) is not greater than the speed score threshold (TH-SV), it is determined to be a low interaction intention.

[0102] In specific implementation, when the solicitation strategy (solicitation initiative) is different, the robot can be controlled to solicit target objects with different interaction intention levels. Table 1 shows a corresponding relationship between a solicitation strategy (solicitation initiative) and an interaction intention level. In Table 1, when the solicitation initiative is high, the robot can be controlled to solicit target objects with high, medium, and low interaction intention levels, that is, to solicit all target objects within the solicitation range; when the solicitation initiative is medium, the robot can be controlled to solicit objects with high and medium interaction intention levels, that is, to solicit target objects with high and medium interaction intention levels within the solicitation range; when the solicitation initiative is low, the robot can be controlled to solicit objects with high interaction intention levels, that is, to solicit target objects with high interaction intention levels within the solicitation range.

[0103] In actual applications, the correspondence between solicitation strategies and interaction intention levels can be determined by customers according to their actual needs. For example, in scenarios that tend to attract more users, such as restaurant scenarios, high solicitation initiative can be selected, and in scenarios that tend to receive visitors, such as company front desks, low solicitation initiative can be selected. In addition, in a solicitation scenario, one of the corresponding relationships between solicitation strategies and interaction intention levels in Table 1 can be selected.

[0104] Table 1

[0105]

[0106] In addition, when the interaction intention analysis results of more than one target object meet the set solicitation strategy, a target object can be selected for solicitation based on the set object selection conditions, where the object selection conditions include being closest to the robot, located in front of the robot, and the distance between the robot and the robot is less than a preset value.

[0107] Figure 4 A flowchart of another robot solicitation control method provided in an embodiment of the present application, the method comprising the following steps.

[0108] In step S401, the interaction intention representation data of the target object within the solicitation range at time t is obtained.

[0109] The target object's interaction intention characterization data at time t may include the distance between the target object and the robot, the radial velocity and tangential velocity of the target object, the orientation of the target object, and the length of time the target object stays within the solicitation range.

[0110] In step S402, the interaction intention of the target object is analyzed based on the interaction intention representation data of the target object at time t.

[0111] The implementation of this step can refer to the implementation of step S202, which will not be repeated here.

[0112] In step S403, the interaction intention level of the target object at time t-1 is obtained.

[0113] In specific implementation, if the target object's interaction intention level at time t-1 cannot be obtained, for example, the target object appears at time t, then the target object's interaction intention level at time t-1 can be initialized to a preset interaction intention level, and the preset interaction intention level represents the least intense interaction intention. For example, the interaction intention level includes three categories: high, medium and low, and the preset interaction intention level is a low interaction intention level.

[0114] In step S404, the interaction intention analysis result of the target object is compared with the intention level transition condition corresponding to the interaction intention level of the target object at time t-1 to determine the interaction intention level of the target object at time t.

[0115] The intention level transition condition may include at least one of a distance score threshold, a speed score threshold, a direction score threshold, and a stay score threshold, and the intention level transition conditions corresponding to different interaction intention levels may be different.

[0116] Table 2 shows the corresponding relationship between an interaction intention level and an intention level transition condition. Among them, the low, medium, and high in the first column represent the interaction intention levels of the target object at the (t - 1) moment. Each cell that is not on the diagonal except for the first row and the first column corresponds to an intention level transition condition. The low, medium, and high in the first row represent the determined interaction intention levels of the target object at the t moment. TH-SD-1 and TH-SD-2 are different distance score thresholds, and TH-SD-1 < TH-SD-2; TH-SV-1 and TH-SV-2 are different speed score thresholds, and TH-SV-1 < TH-SV-2; TH-SP is an orientation score threshold; TH-ST-1 and TH-ST-2 are different stay score thresholds, and TH-ST-1 < TH-ST-2.

[0117] Table 2

[0118]

[0119] Analyzing Table 2, it can be seen that the intention level transition condition for the interaction intention to rise, such as from low to high, is looser than the intention level transition condition for the interaction intention to fall, such as from high to low. In this way, as many target objects with interaction intentions as possible can be found to expand the solicitation scope as much as possible on the premise of ensuring accuracy.

[0120] In step S405, based on the interaction intention level of the target object at the t moment, control the solicitation behavior of the robot.

[0121] Specifically, during implementation, it is possible to determine whether to trigger solicitation based on the interaction intention level of the target object at the t moment and the corresponding relationship between the selected row's solicitation strategy and the interaction intention level in Table 1. Specifically, when the interaction intention level of the target object at the t moment is included in the interaction intention levels corresponding to the solicitation strategy of the selected row, it is determined to trigger solicitation; when the interaction intention level of the target object at the t moment is not included in the interaction intention levels corresponding to the solicitation strategy of the selected row, it is determined not to trigger solicitation. And after determining to trigger solicitation, the robot can be controlled to solicit the target object.

[0122] In step S406, if the robot is controlled to solicit the target object, then after controlling the robot to solicit the target object, the interaction intention level of the target object can be set to a preset interaction intention level, and the interaction intention analysis result of the target object can be set to a preset result.

[0123] Among them, the preset interaction intention level represents the least intense interaction intention, and the preset results such as distance score, speed score, orientation score, and stay score are all zero.

[0124] In this way, the situation of always recruiting the same target object in a period of time can be avoided, thereby improving the rationality of recruitment. In addition, if the target object recruited after a period of time is the target object recruited before, the robot can be controlled to adjust the recruitment words such as "See you again" to improve the robot's intelligence and improve the user experience.

[0125] It should be noted that there is no strict sequence relationship between the above step S402 and step S403.

[0126] The following example uses the interaction intent level as high, medium, and low. Figure 5 The process diagram of the robot solicitation control method shown illustrates the solution of the embodiment of the present application.

[0127] In practical applications, a human tracker can be used to track each target object within the solicitation range, and the interactive intention representation data [θ, D, P], where P represents the body orientation.

[0128] In the specific implementation, a human tracker outputs the latest interaction intention representation data [θ, D, P], the target object's interaction intention can be analyzed according to the following formula, that is, various interaction intention scores can be calculated:

[0129] 1. Distance score:

[0130] The distance score SD(t) of the target object at time t is determined according to the following formula:

[0131]

[0132] Where D(t) is the distance between the target object and the robot at time t, and Dmax is the preset distance.

[0133] 2. Speed ​​score:

[0134] The speed score SV(t) of the target object at time t is determined according to the following formula:

[0135]

[0136] in, is the tangential velocity of the target object at time t, is the radial velocity of the target object at time t, k1 and k2 are predetermined decimals.

[0137] 3. Direction score:

[0138] The orientation score SP(t) of the target object at time t is determined according to the following formula:

[0139] SP(t)=λ*Bp(t)+(1-λ)*SP(t-1);

[0140] Among them, Bp(t) is the score corresponding to the orientation of the target object at time t, SP(t-1) is the orientation score of the target object at time t-1, λ is a predetermined weight, generally a decimal, when the front is facing the robot, the score Bp=3, when facing the side of the robot, the score Bp=1, and when facing the back of the robot, the score Bp=0.

[0141] 4. Stay score:

[0142] The target object’s stay score ST(t) at time t is determined according to the following formula:

[0143] ST(t)=dt*SD(t)+ST(t-1);

[0144] Among them, dt is the target stay interval, SD(t) is the distance score of the target object at time t, and ST(t-1) is the stay score of the target object at time t-1.

[0145] Furthermore, the target object's most recent interaction intention level may be obtained. If the target object is newly present within the solicitation scope, the target object's interaction intention level may be initialized to a low interaction intention level, that is, the target object's most recent interaction intention level is a low interaction intention level.

[0146] Then, based on the target object's most recent interaction intention level, the interaction intention scores calculated above, and Table 2, the target object's current interaction intention level may be determined.

[0147] Furthermore, based on the current interaction intention level of the target object and the correspondence between the solicitation strategy and the interaction intention level of the selected row in Table 1, it can be determined whether solicitation is currently triggered. If so, the solicitation action is triggered to solicit the target object, and the current solicitation interaction intention level of the target object is reset to low, and each interaction intention score is set to zero; if not, the interaction intention representation data of the target object is re-acquired to enter the next round of solicitation processing flow.

[0148] In addition, different solicitation strategies (i.e. different solicitation initiatives) can use different solicitation methods. For example, when the solicitation initiative is high, you can use action + voice to solicit, when the solicitation initiative is medium, you can use action to solicit, and when the solicitation initiative is low, you can use voice to solicit.

[0149] In specific implementation, once a target object is determined to be recruited, after recruiting the target object, the target object's interaction intention can be reset to low, and the target object's most recent SD, SV, SP and ST scores can also be reset to zero to avoid repeatedly recruiting the target object in a short period of time. After performing these operations, if the target object meets the recruitment conditions again, it can be reflected in the recruitment words, such as adding "See you again" to improve user favorability.

[0150] Based on the same technical concept, an embodiment of the present application also provides a robot solicitation control device. The principle of solving the problem by the robot solicitation control device is similar to that of the above-mentioned robot solicitation control method. Therefore, the implementation of the robot solicitation control device can refer to the implementation of the robot solicitation control method, and the repeated parts will not be repeated. Figure 6 A schematic structural diagram of a robot recruitment control device provided in an embodiment of the present application includes an acquisition module 601, an analysis module 602, and a control module 603.

[0151] An acquisition module 601 is used to acquire interaction intention representation data of a target object located within the solicitation range at time t, wherein the interaction intention representation data of the target object at time t at least includes a radial velocity and a tangential velocity of the target object;

[0152] An analysis module 602 is used to analyze the interaction intention of the target object based on the interaction intention representation data of the target object at time t;

[0153] The control module 603 is used to control the solicitation behavior of the robot based on the interaction intention analysis result of the target object.

[0154] In some possible implementations, the analysis module 602 is specifically used to:

[0155] The interaction intention is analyzed based on the radial speed and tangential speed of the target object to obtain the speed score of the target object at time t. The speed score is used to characterize the level of interaction probability based on the walking trend.

[0156] In some possible implementations, the analysis module 602 is specifically used to:

[0157] Determining a velocity ratio of a tangential velocity to a radial velocity of the target object;

[0158] According to the rule that the speed ratio is negatively correlated with the interaction probability and the tangential speed is positively correlated with the interaction probability, the speed score of the target object at time t is determined.

[0159] In some possible implementations, the interaction intention representation data of the target object at time t also includes any combination of the distance between the target object and the robot, the orientation of the target object, and the length of time the target object stays within the solicitation range;

[0160] The analysis module 602 is further configured to analyze the interaction intention of the target object according to any combination of the following steps:

[0161] Performing interaction intention analysis based on the distance between the target object and the robot to obtain a distance score of the target object at time t, wherein the distance score is used to characterize the level of interaction probability based on the distance;

[0162] Performing interaction intention analysis based on the orientation of the target object to obtain an orientation score of the target object at time t, wherein the orientation score is used to characterize the level of interaction probability based on the orientation;

[0163] An interaction intention analysis is performed based on the target object's stay time within the solicitation scope to obtain a stay score of the target object at time t, and the stay score is used to characterize the level of interaction probability based on the stay time.

[0164] In some possible implementations, the analysis module 602 is specifically used to:

[0165] Determine a distance ratio between the target object and the robot and a preset distance, wherein the preset distance is determined according to a detection limit of a laser radar;

[0166] According to the rule that the distance ratio is negatively correlated with the interaction probability, the distance score of the target object at time t is determined.

[0167] In some possible implementations, the analysis module 602 is specifically used to:

[0168] Determining the score corresponding to the orientation of the target object based on a preset correspondence relationship between the orientation and the score;

[0169] The determined score and the orientation score of the target object at time t-1 are weighted averaged to obtain the orientation score of the target object at time t.

[0170] In some possible implementations, the analysis module 602 is specifically used to:

[0171] Determine the product of the distance score of the target object at time t and the target stay interval, where the target stay interval refers to the time difference between time t-1 and time t;

[0172] The sum of the product and the stay score of the target object at time t-1 is determined as the stay score of the target object at time t.

[0173] In some possible implementations, the acquisition module 601 is further used to acquire the interaction intention level of the target object at time t-1, where the interaction intention level is used to characterize the intensity of the interaction intention;

[0174] The control module 603 is specifically used to compare the interaction intention analysis result of the target object with the intention level transition condition corresponding to the interaction intention level of the target object at time t-1, so as to determine the interaction intention level of the target object at time t, wherein the intention level transition condition includes at least one of a distance score threshold, a speed score threshold, a direction score threshold and a stay score threshold; based on the interaction intention level of the target object at time t, the robot's solicitation behavior is controlled.

[0175] In some possible implementations, the control module 603 is further configured to:

[0176] If the robot is controlled to solicit the target object, then after controlling the robot to solicit the target object, the interaction intention level of the target object is set to a preset interaction intention level, and the interaction intention analysis result of the target object is set to a preset result, and the preset interaction intention level represents the least intense interaction intention.

[0177] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, the functional modules in the embodiments of the present application may be integrated in a processor, or may exist physically separately, or two or more modules may be integrated in one module. The coupling between the modules may be achieved through some interfaces, which are usually electrical communication interfaces, but it is not excluded that they may be mechanical interfaces or other forms of interfaces. Therefore, the modules described as separate components may or may not be physically separated, and may be located in one place or distributed to different locations of the same or different devices. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0178] Figure 7A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, the electronic device includes a transceiver 701 and a physical device such as a processor 702, wherein the processor 702 can be a central processing unit (CPU), a microprocessor, a dedicated integrated circuit, a programmable logic circuit, a large-scale integrated circuit, or a digital processing unit, etc. The transceiver 701 is used for electronic devices and other devices to send and receive data.

[0179] The electronic device may also include a memory 703 for storing software instructions executed by the processor 702, and of course, some other data required by the electronic device, such as identification information of the electronic device, encryption information of the electronic device, user data, etc. The memory 703 may be a volatile memory, such as a random access memory (RAM); the memory 703 may also be a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), or the memory 703 is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 703 may be a combination of the above memories.

[0180] The specific connection medium between the processor 702, the memory 703 and the transceiver 701 is not limited in the embodiment of the present application. Figure 7 In the example, the memory 703, the processor 702 and the transceiver 701 are connected via the bus 704. Figure 7 The connections between the other components are shown in bold lines, which are only for illustration and are not intended to be limiting. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0181] The processor 702 can be dedicated hardware or a processor that runs software. When the processor 702 can run software, the processor 702 reads the software instructions stored in the memory 703 and, driven by the software instructions, executes the robot recruitment control method involved in the aforementioned embodiments.

[0182] It should be noted that the electronic device can be a control device inside the robot or a control device outside the robot, and this application does not make any specific limitation.

[0183] An embodiment of the present application also provides a storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the robot solicitation control method involved in the aforementioned embodiment.

[0184] In some possible implementations, various aspects of the robot solicitation control method provided in the present application can also be implemented in the form of a program product, which includes a program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the robot solicitation control method involved in the aforementioned embodiments.

[0185] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0186] The program product for robot solicitation control in the embodiment of the present application may adopt a CD-ROM and include program code, and may be run on a computing device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0187] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0188] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

[0189] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device via any type of network such as a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0190] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0191] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0192] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0193] The present application is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0194] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0195] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0196] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0197] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A robot solicitation control method, characterized in that: include: Obtaining the interaction intention characterization data of the target object within the solicitation range at time t, and obtaining the interaction intention level of the target object at time t-1, wherein the interaction intention characterization data includes the radial speed and tangential speed of the target object, the distance between the target object and the robot, the direction of the target object, and the length of time the target object stays within the solicitation range, and the interaction intention level is used to characterize the intensity of the interaction intention; Based on the interaction intention characterization data, analyzing the interaction intention of the target object, wherein the radial speed and the tangential speed of the target object are used to determine the speed score, the distance between the target object and the robot is used to determine the distance score, the orientation of the target object is used to determine the orientation score, and the stay time is used to determine the stay score; Comparing the interaction intention analysis result of the target object with the intention level transition condition corresponding to the interaction intention level of the target object at time t-1 to determine the interaction intention level of the target object at time t, wherein the intention level transition condition includes at least one of a distance score threshold, a speed score threshold, a direction score threshold, and a stay score threshold, and the intention level transition condition when the interaction intention increases is looser than the intention level transition condition when the interaction intention decreases; Based on the interaction intention level of the target object at time t, the solicitation behavior of the robot is controlled.

2. The method according to claim 1, characterized in that Analyzing the interaction intention of the target object based on the interaction intention representation data includes: Performing interaction intention analysis based on the radial speed and tangential speed of the target object to obtain a speed score of the target object at time t, wherein the speed score is used to characterize the level of interaction probability based on walking trends; Performing interaction intention analysis based on the distance between the target object and the robot to obtain a distance score of the target object at time t, wherein the distance score is used to characterize the level of interaction probability based on the distance; Performing interaction intention analysis based on the orientation of the target object to obtain an orientation score of the target object at time t, wherein the orientation score is used to characterize the level of interaction probability based on the orientation; An interaction intention analysis is performed based on the target object's stay time within the solicitation scope to obtain a stay score of the target object at time t, and the stay score is used to characterize the level of interaction probability based on the stay time.

3. The method according to claim 2, characterized in that Performing interaction intention analysis based on the radial velocity and tangential velocity of the target object to obtain a velocity score of the target object at time t includes: Determining a velocity ratio of a tangential velocity to a radial velocity of the target object; According to the rule that the speed ratio is negatively correlated with the interaction probability and the tangential speed is positively correlated with the interaction probability, the speed score of the target object at time t is determined.

4. The method according to claim 2, characterized in that Performing interaction intention analysis based on the distance between the target object and the robot to obtain a distance score of the target object at time t includes: Determine a distance ratio between the target object and the robot and a preset distance, wherein the preset distance is determined according to a detection limit of a laser radar; According to the rule that the distance ratio is negatively correlated with the interaction probability, the distance score of the target object at time t is determined.

5. The method according to claim 2, characterized in that Performing interaction intention analysis based on the orientation of the target object to obtain the orientation score of the target object at time t includes: Determining the score corresponding to the orientation of the target object based on a preset correspondence relationship between the orientation and the score; The determined score and the orientation score of the target object at time t-1 are weighted averaged to obtain the orientation score of the target object at time t.

6. The method according to claim 2, characterized in that An interaction intention analysis is performed based on the target object's stay time within the solicitation scope to obtain the target object's stay score at time t, including: Determine the product of the distance score of the target object at time t and the target stay interval, where the target stay interval refers to the time difference between time t-1 and time t; The sum of the product and the stay score of the target object at time t-1 is determined as the stay score of the target object at time t.

7. The method according to claim 1, characterized in that If the robot is controlled to recruit the target object, it also includes: After controlling the robot to solicit the target object, the interaction intention level of the target object is set to a preset interaction intention level, and the interaction intention analysis result of the target object is set to a preset result, wherein the preset interaction intention level represents the least intense interaction intention.

8. A robot solicitation control device, characterized in that: include: an acquisition module, used to acquire the interaction intention characterization data of the target object within the solicitation range at time t, and acquire the interaction intention level of the target object at time t-1, wherein the interaction intention characterization data includes the radial speed and tangential speed of the target object, the distance between the target object and the robot, the direction of the target object, and the length of time the target object stays within the solicitation range, and the interaction intention level is used to characterize the intensity of the interaction intention; an analysis module, configured to analyze the interaction intention of the target object based on the interaction intention characterization data, wherein the radial speed and tangential speed of the target object are used to determine a speed score, the distance between the target object and the robot is used to determine a distance score, the orientation of the target object is used to determine an orientation score, and the stay time is used to determine a stay score; A control module is used to compare the interaction intention analysis result of the target object with the intention level transition condition corresponding to the interaction intention level of the target object at time t-1 to determine the interaction intention level of the target object at time t, and control the solicitation behavior of the robot based on the interaction intention level of the target object at time t, wherein the intention level transition condition includes at least one of a distance score threshold, a speed score threshold, a direction score threshold and a stay score threshold, and the intention level transition condition when the interaction intention increases is looser than the intention level transition condition when the interaction intention decreases.

9. An electronic device, characterized in that: include: at least one processor, and a memory communicatively connected to the at least one processor, wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the method as claimed in any one of claims 1 to 7.

Images