Object motion control method and device, equipment, medium and program product

Abstract

The embodiment of the invention discloses an object motion control method and device, equipment, a medium and a program product. A specific embodiment of the method comprises the following steps: in response to determining that a target object moves from a first position to a second position, adding a visual field penalty term in a target path planning model to obtain an added path planning model, a target motion marker exists between the first position and the second position, and the target motion marker is a target motion marker between the first position and the second position; the visual field penalty term represents that path penalty is carried out under the condition that no target motion marker exists in the motion visual field; configuring view constraint information; according to the motion parameter information, utilizing the added path planning model to generate a first optimal motion path meeting the view constraint information; and controlling the target object to move according to the first optimal motion path. The implementation mode is related to motion path planning, visual field punishment can be set, and the optimal motion path of the target motion marker in the motion visual field in the motion process is accurately generated.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of motion path planning, and in particular, to an object motion control method, device, equipment, medium and program product. BACKGROUND

[0002] At present, path planning is one of the main research contents of motion planning, and is widely used in various fields (for example, the field of unmanned driving). For optimal path planning of target motion markers (for example, traffic lights), the commonly used way is to identify target motion markers based on computer vision results to perform optimal path planning according to the marker identification results.

[0003] However, the inventors have found that when the above-mentioned way is used for optimal path planning, the following technical problems often exist:

[0004] During the motion of the object, the camera field of view (FOV) is often limited, which may cause the identification of the target motion marker to fail, resulting in serious motion accidents.

[0005] The above information disclosed in this BACKGROUND section is only for the purpose of enhancing the understanding of the background of the present inventive concepts, and therefore, it can contain information that does not form the prior art that is already known to those of ordinary skill in the art in the country. SUMMARY

[0006] The summary section of the present disclosure is used to introduce the concepts in a brief manner, which will be described in detail in the specific embodiments section. The summary section of the present disclosure is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to be used to limit the scope of the claimed technical solutions.

[0007] Some embodiments of the present disclosure propose an object motion control method, device, equipment, medium and program product to solve the technical problems mentioned in the background section.

[0008] In a first aspect, some embodiments of the present disclosure provide a method for object motion control, comprising: in response to determining that a target object moves from a first position to a second position, adding a field-of-view penalty term to a target path planning model to obtain an added path planning model, wherein the first position and the second position are between a target motion marker, and the field-of-view penalty term represents a path penalty in a case where the target motion marker is not in a motion field-of-view; configuring field-of-view constraint information corresponding to the added path planning model; generating a first optimal motion path satisfying the field-of-view constraint information by using the added path planning model according to motion parameter information, wherein the motion parameter information represents a motion parameter in a process in which the target object moves from the first position to the second position; and controlling the target object to move according to the first optimal motion path.

[0009] Optionally, the adding the field-of-view penalty term to the target path planning model to obtain the added path planning model in response to determining that the target object moves from the first position to the second position comprises: in response to determining that the target object moves to a target position, obtaining a field-of-view penalty term for the target motion marker sent by a target motion system, wherein the target position is a position between the first position and the second position; and adding the field-of-view penalty term to the target path planning model to generate the added path planning model.

[0010] Optionally, the field-of-view penalty term comprises a first field-of-view orientation corresponding to a first field-of-view penalty parameter and a second field-of-view orientation corresponding to a second field-of-view penalty parameter; and the adding the field-of-view penalty term to the target path planning model to generate the added path planning model comprises: adding the first field-of-view penalty parameter and the second field-of-view penalty parameter to generate an added parameter; multiplying the added parameter by a preset penalty coefficient to generate a multiplied parameter; and adding the multiplied parameter to the target path planning model to generate the added path planning model.

[0011] Optionally, the field-of-view constraint information comprises constraint information representing that the target motion marker is in a first direction of a first orientation vector and constraint information representing that the target motion marker is in a second direction of a second orientation vector, wherein the first orientation vector is an orientation vector corresponding to the first field-of-view orientation, and the second orientation vector is an orientation vector corresponding to the second field-of-view orientation.

[0012] Optionally, the added path planning model is an addition item among a path point deviation term, an object control penalty term, and the field of view penalty term, the added path planning model has corresponding object control quantity constraint information, obstacle avoidance constraint information, and starting point constraint information; and the first optimal motion path satisfying the field of view constraint information is generated by using the added path planning model according to the motion parameter information, including: performing optimal solution calculation on the added path planning model according to the motion parameter information to generate the first optimal motion path, wherein the first optimal motion path satisfies the object control quantity constraint information, the obstacle avoidance constraint information, the starting point constraint information, and the field of view constraint information.

[0013] Optionally, before the field of view penalty term for the target motion marker sent by the target motion system is obtained in response to a determination that the target object moves to the target position, the method further includes: in response to a determination that the target object does not move to the target position, generating a second optimal motion path based on the target path planning model; and controlling the target object to move according to the second optimal motion path to move to the target position.

[0014] In a second aspect, some embodiments of the present disclosure provide an object motion control device, including: an adding unit configured to add a field of view penalty term in a target path planning model in response to a determination that a target object moves from a first position to a second position, to obtain an added path planning model, wherein the first position and the second position have a target motion marker therebetween, and the field of view penalty term represents a path penalty in the case that the target motion marker is not in the motion field of view; a configuration unit configured to configure field of view constraint information corresponding to the added path planning model; an optimal solution calculation unit configured to generate a first optimal motion path satisfying the field of view constraint information by using the added path planning model according to motion parameter information, wherein the motion parameter information represents a motion parameter in the process that the target object moves from the first position to the second position; and a control unit configured to control the target object to move according to the first optimal motion path.

[0015] Optionally, the adding unit can be configured to: in response to a determination that the target object moves to a target position, obtain a field of view penalty term for the target motion marker sent by a target motion system, wherein the target position is a position between the first position and the second position; and add the field of view penalty term in the target path planning model to generate an added path planning model.

[0016] Optionally, the field of view penalty term includes a first field of view penalty parameter corresponding to the first field of view orientation and a second field of view penalty parameter corresponding to the second field of view orientation; and the adding unit is configured to: add the first field of view penalty parameter and the second field of view penalty parameter to generate an added parameter; multiply the added parameter by a preset penalty coefficient to generate a multiplied parameter; and add the multiplied parameter to the target path planning model to generate an added path planning model.

[0017] Optionally, the added path planning model is an addition term between a path point deviation term, an object control penalty term, and the field of view penalty term, and the added path planning model has corresponding object control quantity constraint information, obstacle avoidance constraint information, and starting point constraint information; and the optimal solution obtaining unit is configured to: perform optimal solution obtaining on the added path planning model according to the motion parameter information to generate the first optimal motion path, wherein the first optimal motion path satisfies the object control quantity constraint information, the obstacle avoidance constraint information, the starting point constraint information, and the field of view constraint information.

[0018] Optionally, the adding unit is configured to: in response to determining that the target object does not move to the target position, generate a second optimal motion path based on the target path planning model; and control the target object to move according to the second optimal motion path to move to the target position.

[0019] In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the first aspect.

[0020] In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method described in any implementation manner of the first aspect.

[0021] In a fifth aspect, some embodiments of the present disclosure provide a computer program product including a computer program, the computer program being executed by a processor to implement the method described in any implementation manner of the first aspect.

[0022] The above various embodiments of the present disclosure have the following beneficial effects: through the object motion control method of some embodiments of the present disclosure, a field of view penalty can be set, and an optimal motion path with a target motion marker in the motion field of view during motion can be accurately generated. Specifically, the reason why the related optimal motion path is not accurate is that during the motion of the object, there are often cases where the camera shooting field of view is limited, which may cause the identification of the target motion marker to fail, resulting in serious motion accidents. Based on this, the object motion control method of some embodiments of the present disclosure first, in response to determining that a target object moves from a first position to a second position, adds a field of view penalty term in a target path planning model to obtain an added path planning model, wherein the first position and the second position are between the target motion markers, and the field of view penalty term represents a path penalty in the case where the target motion marker does not exist in the motion field of view. Here, by adding the field of view penalty term in the target path planning model, the target motion marker can be effectively present in the motion field of view of the target object during the motion of the target object from the first position to the second position, so that the generation of the subsequent first optimal motion path can refer to the motion requirements given by the target motion marker. Then, the field of view constraint information corresponding to the added path planning model is configured to further constrain the field of view content in the motion field of view, so that the target motion marker exists in the motion field of view as much as possible. Further, according to the motion parameter information, the first optimal motion path satisfying the field of view constraint information is generated by using the added path planning model. The motion parameter information represents the motion parameters of the target object moving from the first position to the second position. Here, through the optimal solution of the added path planning model, the content of the target motion marker existing in the motion field of view during the entire motion process can be accurately generated, so as to move according to the motion requirements corresponding to the motion marker, and the first optimal motion path can be accurately generated. Finally, the target object is controlled to move safely and efficiently according to the first optimal motion path. In summary, by adding the field of view penalty term in the target path planning model and generating the corresponding field of view constraint information, the optimal motion path with the target motion marker existing in the motion field of view during the motion can be accurately generated according to the motion requirements corresponding to the target motion marker. BRIEF DESCRIPTION OF DRAWINGS

[0023] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent upon consideration of the following detailed description, taken in conjunction with the accompanying drawings. Throughout the drawings, like or similar reference numerals can be used to refer to like or similar elements. It should be understood that the drawings are schematic, and elements and features are not necessarily to scale.

[0024] Figures 1-2is a schematic diagram of one application scenario of an object motion control method according to some embodiments of the present disclosure;

[0025] Figure 3 is a flowchart of some embodiments of an object motion control method according to the present disclosure;

[0026] Figure 4 is a schematic diagram of a first field of view orientation and a second field of view orientation in some embodiments of an object motion control method according to the present disclosure;

[0027] Figure 5 is a schematic diagram of a first optimal motion path in some embodiments of an object motion control method according to the present disclosure;

[0028] Figure 6 is a flowchart of some other embodiments of an object motion control method according to the present disclosure;

[0029] Figure 7 is a structural schematic diagram of some embodiments of an object motion control apparatus according to the present disclosure;

[0030] Figure 8 is a structural schematic diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0031] Embodiments of the present disclosure will be described in more detail with reference to the drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly and completely understood. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0032] It should also be noted that, for ease of description, only parts related to the present application are shown in the drawings. The embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0033] It should be noted that the terms "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units.

[0034] It should be noted that the adjectives "one", "multiple" mentioned in the present disclosure are illustrative and not restrictive, and those skilled in the art should understand that "one or more" should be understood unless otherwise explicitly stated in the context.

[0035] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0036] With regard to the collection, storage, and use of user personal information (such as motion parameter information and motion paths) involved in this disclosure, before performing corresponding operations, relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, fulfilling the obligation to inform the personal information subject, and obtaining the authorization and consent of the personal information subject in advance.

[0037] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0038] Figures 1-2 is a schematic diagram of an application scenario of the object motion control method according to some embodiments of the present disclosure.

[0039] exist Figures 1-2 In an application scenario, first, in response to determining that a target object has moved from a first position to a second position, the electronic device 101 may add a field of view penalty term to the target path planning model 102 to obtain a post-addition path planning model 103. A target motion marker exists between the first and second positions. The field of view penalty term represents a path penalty imposed when the target motion marker is not present in the field of view. In this application scenario, the target object may be vehicle A, and the target motion marker may be a traffic light. The electronic device 101 may then configure field of view constraint information 105 corresponding to the post-addition path planning model 103. In this application scenario, the field of view constraint information 105 may include: field of view constraint information for an upper field of view and field of view constraint information for a lower field of view. The field of view constraint information for an upper field of view may indicate the presence of a traffic light within the upper field of view, corresponding to the red and green display content. The field of view constraint information for a lower field of view may indicate the presence of a traffic light within the lower field of view, corresponding to the red and green display content. Furthermore, the electronic device 101 may utilize the post-addition path planning model 103 based on the motion parameter information 104 to generate a first optimal motion path 106 that satisfies the field of view constraint information. The motion parameter information 104 represents the motion parameters of the target object during its movement from the first position to the second position. In this application scenario, the first optimal motion path 106 may be motion path A. Finally, the electronic device 101 may control the target object to move according to the first optimal motion path 106.

[0040] It should be noted that the electronic device 101 described above can be hardware or software. When the electronic device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or as a single server or a single terminal device. When the electronic device is software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.

[0041] It should be understood that Figures 1-2 The number of electronic devices in the above description is only illustrative. Depending on the implementation needs, there can be any number of electronic devices.

[0042] With reference to Figure 3 , a flow 300 of some embodiments of the object motion control method according to the present disclosure is shown. The object motion control method includes the following steps:

[0043] Step 301, in response to determining that the target object moves from the first position to the second position, adding a field of view penalty term in the target path planning model to obtain an added path planning model.

[0044] In some embodiments, in response to determining that the target object moves from the first position to the second position, the execution subject (e.g. Figure 1 The electronic device 101 shown in the above description) of the object motion control method described above can add a field of view penalty term in the target path planning model to obtain an added path planning model. Wherein, there is a target motion marker between the first position and the second position. The field of view penalty term represents path penalty in the absence of the target motion marker in the motion field of view. Wherein, the target object can be an object to be moved. In practice, for the driving field, the corresponding target object can be an unmanned vehicle to be automatically driven. The first position can be the starting point of the motion of the target object. The second position can be the termination point of the motion of the target object. The target path planning model can be a model for generating an optimal path. For example, the target path planning model can be a neural network model based on reinforcement learning. The field of view penalty term represents path penalty in the absence of the target motion marker in the motion field of view. The field of view penalty term can be various forms of information. For example, the field of view penalty term can be information in the form of a formula. For the target path planning model being a neural network model, the corresponding field of view penalty term can be a pre-set loss function representing path penalty in the absence of the target motion marker in the motion field of view. The target motion marker can be a marker indicating the motion restriction requirement of the target object. For example, the target motion marker can be a traffic light, and can also be a slow down and yield sign. The position corresponding to the target motion marker is located in the motion route from the first position to the second position.

[0045] In some optional implementations of some embodiments, the above-mentioned field of view penalty item includes: a first field of view penalty parameter corresponding to a first field of view orientation and a second field of view penalty parameter corresponding to a second field of view orientation. The first field of view orientation may be the orientation of the target object in the first field of view within the moving field of view. In practice, the first field of view orientation may be an orientation expressed in vector form. For example, the first field of view orientation may be the orientation vector between the target object and the leftmost point where the target motion marker appears in the moving field of view. The first field of view penalty parameter may be the magnitude of the field of view penalty to be applied if the leftmost point of the target motion marker is located to the left of the first field of view orientation. The second field of view orientation may be the orientation of the target object in the second field of view within the moving field of view. In practice, the second field of view orientation may be an orientation expressed in vector form. For example, the second field of view orientation may be the orientation vector between the target object and the rightmost point where the target motion marker appears in the moving field of view. The second field of view penalty parameter may be the magnitude of the field of view penalty to be applied if the rightmost point of the target motion marker is located to the right of the first field of view orientation. It should be noted that the first field of view penalty parameter may represent the sum of the squares of the penalty values ​​of each path point in the first field of view. Each path point may be a pre-set path point between the first position and the second position. For example, a path point may be collected every 0.1 seconds between the first position and the second position, thereby obtaining each path point. The second field of view penalty parameter may represent the sum of the squares of the penalty values ​​of each path point in the second field of view.

[0046] like Figure 4 As shown, a schematic diagram of the first field of view orientation and the second field of view orientation is shown. The rectangle in the figure is the target object, and the coordinates of the target object in the coordinates under st are (x, y). Among them, (x, y) can represent the position of the target object. The square filled with black color in the figure is the target motion marker. The dotted line corresponding to left_line in the figure is the vector under the first field of view orientation. The dotted line corresponding to right_line in the figure is the vector under the second field of view orientation. The middle dotted line between the dotted line corresponding to left_line and the dotted line corresponding to right_line is the driving direction of the target object. The angle between the middle dotted line and the dotted line corresponding to left_line is α L The angle between the middle dashed line and the dashed line corresponding to right_line is α RThe angle between the dashed line corresponding to the right_line and the dashed line corresponding to the left_line can represent the motion field of view corresponding to the target object. When the target motion marker is within the motion field of view, the first field of view penalty parameter and the second field of view penalty parameter will not be triggered. When the target motion marker is to the left of the dashed line corresponding to the left_line, the first field of view penalty parameter will be triggered. When the target motion marker is to the right of the dashed line corresponding to the right_line, the second field of view penalty parameter will be triggered.

[0047] Optionally, the execution subject can add the field of view penalty term to the target path planning model to generate an added path planning model, including the following steps:

[0048] Firstly, the first field of view penalty parameter and the second field of view penalty parameter are added to generate an added parameter.

[0049] Secondly, the added parameter is multiplied by a preset penalty coefficient to generate a multiplied parameter. The preset penalty coefficient can be a value between 0 and 1. The larger the value, the greater the penalty degree in the field of view.

[0050] As an example, the execution subject can add the first field of view penalty parameter in the added parameter to the first penalty coefficient to obtain a first added result. The second field of view penalty parameter in the added parameter is added to the second penalty coefficient to obtain a second added result. Finally, the sum of the first added result and the second added result is determined as the multiplied parameter.

[0051] Thirdly, the multiplied parameter is added to the target path planning model to generate an added path planning model. The target path planning model can be a kinematic model in the form of a formula.

[0052] In practice, the target path planning model can be the following formula:

[0053]

[0054] X k+1 =F(X k ,U k ),X0=X init ,X M =X goal ,

[0055] Wherein, X init may be the first position. X goal is the second position. k can be the motion time. represents the state of the target object at k time. (x k , y k) can be the position of the target object at time k. is the heading angle of the target object at time k. k can be the control input of the target object at time k. Wherein, U k = [v k , δ k ] T , v k can be the forward speed of the target object at time k. δ k can be the front wheel steering angle of the target object at time k. X k+1 is the state of the target object at time k+1. ||X k -X goal || is used to punish the deviation of the path point from X goal . ||U k || is used to punish the large control input. ||·|| can represent the Euclidean distance. can be the first field of view punishment parameter. can be the second field of view punishment parameter. σ can be a preset punishment coefficient. r L，k can be the punishment value of the path point in the first field of view (i.e. the left field of view) and at time k. r R，k can be the punishment value of the path point in the second field of view (i.e. the right field of view) and at time k.

[0056]

[0057] Wherein, X k can be the lateral motion position of the target object at time k. y k can be the longitudinal motion position of the target object at time k. U k can be the control input of the target object at time k. Wherein, U k = [v k , δ k ] T , v k can be the forward speed of the target object at time k. δ k can be the front wheel steering angle of the target object at time k. F(, ) can be the kinematics model. θ k can be the heading angle of the target object at time k. L can be the distance between the center of the front wheel and the center of the rear wheel. The center of the front wheel can be the center point between the two front wheels. The center of the rear wheel can be the center point between the two rear wheels.

[0058] Here, the purpose of the target path planning model is to find a set of control inputs U0, U1, …, U M-1 , such that the path X0, X1, …, X MArrive at the second position while meeting the constraints of obstacle avoidance, unmanned vehicle kinematics, physical limits, etc.

[0059] In step 302, the field of view constraint information corresponding to the above-mentioned added path planning model is configured.

[0060] In some embodiments, the above-mentioned execution subject can configure the field of view constraint information corresponding to the above-mentioned added path planning model. The field of view constraint information can be information for constraining the motion field of view. In practice, the field of view constraint information can be various forms of constraint information. For example, for the added path planning model being a neural network, the corresponding field of view constraint information can be a loss function for the target motion marker existing in the motion field of view. For example, the field of view constraint information is an IoU (Intersection over Union) function.

[0061] In some optional implementations of some embodiments, the above-mentioned field of view constraint information includes: constraint information representing that the target motion marker is in a first direction of a first orientation vector. Constraint information representing that the target motion marker is in a second direction of a second orientation vector. The first orientation vector corresponds to the first field of view orientation. The second orientation vector corresponds to the second field of view orientation.

[0062] In practice, the constraint information representing that the target motion marker is in the first direction of the first orientation vector can be:

[0063] (s0-x k )sin(θ k +α L )-(t0-y k )cos(θ k +α L )>-r L，k . Wherein S0 can be the lateral coordinate of the target motion marker. t0 can be the longitudinal coordinate of the target motion marker.

[0064] The constraint information representing that the target motion marker is in the second direction of the second orientation vector can be:

[0065] (s0-x)sin(θ k -α R )-(t0-y k )cos(θ k -α R )<r R,k .

[0066] Optionally, the following constraint condition also exists:

[0067]

[0068] wherein, is the maximum value of the allowed field relaxation variable.

[0069] At step 303, a first optimal motion path satisfying the field constraint information is generated by using the above-mentioned added path planning model according to the motion parameter information.

[0070] In some embodiments, the above-mentioned execution subject can perform optimal solution seeking on the above-mentioned added path planning model according to the motion parameter information to generate the first optimal motion path satisfying the above-mentioned field constraint information. The motion parameter information characterizes the motion parameter of the target object moving from the first position to the second position. The motion parameter information can include but is not limited to at least one of the following: the first position, the second position, the initial speed, the initial acceleration, the initial steering angle, and the object size information. The first optimal motion path can be the optimal path from the first position to the second position in the presence of the target motion marker in the motion field.

[0071] As shown in Figure 5 , a schematic diagram of the first optimal motion path is shown. Figure 5 The two rectangular blocks in the figure represent the target object. The diamond block filled with black color is the target motion marker. The triangular blocks corresponding to the dashed lines are the motion fields of the target object in the front and back. The solid line in the figure is the first optimal motion path. The last pentagram mark is the second position.

[0072] As an example, first, the execution subject can add the field constraint information to the above-mentioned added path planning model to generate an initial path planning model. Then, a sample set similar to the scene corresponding to the target object moving from the first position to the second position is obtained. Next, the initial path planning model is trained according to the sample set to generate a path planning model. Finally, the motion parameter information is input into the path planning model to generate the first optimal motion path.

[0073] In some optional implementations of some embodiments, the added path planning model is an additive item between the path point deviation item, the object control penalty item, and the field of view penalty item, and the added path planning model has corresponding object control quantity constraint information, obstacle avoidance constraint information, and starting point constraint information. In practice, the path point deviation item can be a deviation item that penalizes deviation between a path point and the second position. The object control penalty item can be a penalty item that penalizes large control input. The field of view penalty item can be a penalty item that penalizes the absence of a target motion marker in the field of view. The object control quantity constraint information can be a constraint condition that constrains the control quantity (e.g., motion speed, motion acceleration, heading angle, and the like) of the target object. The obstacle avoidance constraint information can be a constraint condition that constrains the safe obstacle avoidance processing of the target object at each path point. The starting point constraint information can be a constraint condition for the starting point and the ending point.

[0074] Optionally, the generating, according to the motion parameter information, of the first optimal motion path that satisfies the field of view constraint information by using the added path planning model includes:

[0075] The optimal solution of the added path planning model is obtained according to the motion parameter information, so as to generate the first optimal motion path, where the first optimal motion path satisfies the object control quantity constraint information, the obstacle avoidance constraint information, the starting point constraint information, and the field of view constraint information.

[0076] In step 304, the target object is controlled to move according to the first optimal motion path.

[0077] In some embodiments, the execution subject can control the target object to move according to the first optimal motion path.

[0078] The above various embodiments of the present disclosure have the following beneficial effects: through the object motion control method of some embodiments of the present disclosure, a field of view penalty can be set, and an optimal motion path with a target motion marker in the motion field of view during motion can be accurately generated. Specifically, the reason why the related optimal motion path is not accurate is that during the motion of the object, there are often cases where the camera shooting field of view is limited, which may cause the identification of the target motion marker to fail, resulting in serious motion accidents. Based on this, the object motion control method of some embodiments of the present disclosure first, in response to determining that a target object moves from a first position to a second position, adds a field of view penalty term in a target path planning model to obtain an added path planning model, wherein the first position and the second position are between the target motion markers, and the field of view penalty term represents a path penalty in the case that the target motion marker does not exist in the motion field of view. Here, by adding the field of view penalty term in the target path planning model, the target motion marker can be effectively present in the motion field of view of the target object during the motion of the target object from the first position to the second position, so that the generation of the subsequent first optimal motion path can refer to the motion requirements given by the target motion marker. Then, the field of view constraint information corresponding to the added path planning model is configured to further constrain the field of view content in the motion field of view, so that the target motion marker exists in the motion field of view as much as possible. Further, according to the motion parameter information, the first optimal motion path satisfying the field of view constraint information is generated by using the added path planning model. The motion parameter information represents the motion parameters of the target object moving from the first position to the second position. Here, through the optimal solution of the added path planning model, the content of the target motion marker existing in the motion field of view during the entire motion process can be accurately generated, so as to move according to the motion requirements corresponding to the motion marker, and the first optimal motion path can be accurately generated. Finally, the target object is controlled to move safely and efficiently according to the first optimal motion path. In summary, by adding the field of view penalty term in the target path planning model and generating the corresponding field of view constraint information, the optimal motion path with the target motion marker existing in the motion field of view during the motion can be accurately generated according to the motion requirements corresponding to the target motion marker.

[0079] Further reference is made to Figure 6 Fig. 6 shows the flow 600 of another embodiment of the object motion control method according to the present disclosure. The object motion control method comprises the following steps:

[0080] Step 601, in response to determining that a target object moves to a target position, a field of view penalty term for a target motion marker sent by a target motion system is obtained.

[0081] In some embodiments, in response to determining that the target object moves to the target location, the subject (eg, Figure 1 The electronic device 101 shown) can obtain the field of view penalty item for the target motion marker sent by the target motion system. The target position can be a position between the first position and the second position for triggering the execution of the field of view penalty for the target motion marker. In practice, the target position can be set based on relevant experience, or it can be the motion position where the target motion marker is preliminarily detected in the dynamic field of view. The target motion system can be a motion system carried by the target object. In practice, the target motion system can be an automatic driving system. The above-mentioned target position is a position between the above-mentioned first position and the above-mentioned second position.

[0082] In some optional implementations of some embodiments, after step 602, the steps further include:

[0083] In the first step, in response to determining that the target object has not moved to the target position, a second optimal motion path is generated based on the target path planning model.

[0084] As an example, the execution entity may generate a second optimal motion path based on the motion parameter information corresponding to the target object and using the target path planning model.

[0085] The second step is to control the target object to move according to the second optimal motion path to move to the target position.

[0086] Step 602 : Add the vision penalty term to the target path planning model to generate a post-addition path planning model.

[0087] In some embodiments, the execution entity may add the vision penalty term to the target path planning model to generate a post-addition path planning model.

[0088] Step 603: Configure the field of view constraint information corresponding to the added path planning model.

[0089] Step 604 : Based on the motion parameter information, using the added path planning model, a first optimal motion path that satisfies the field of view constraint information is generated.

[0090] Step 605: Control the target object to move according to the first optimal motion path.

[0091] In some embodiments, the specific implementation of steps 603-605 and the technical effects thereof can be referred to in Figure 3 Steps 302-304 in the corresponding embodiment are not repeated here.

[0092] fromFigure 6 As can be seen, Figure 3 compared to the description of some embodiments corresponding to Figure 6 The flow 600 of the object motion control method in some embodiments corresponding to some embodiments is described as follows. By setting the target position corresponding to the target motion marker, the field of view penalty term is dynamically set flexibly for the scene where the target motion marker is located, so as to ensure that the target object can generate the optimal motion path in the current scene.

[0093] Further reference is made to Figure 7 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an object motion control apparatus, which correspond to the method embodiments shown in Figure 3 The object motion control apparatus can be applied to various electronic devices.

[0094] As shown in Figure 7 An object motion control apparatus 700 includes an adding unit 701, a configuring unit 702, a generating unit 703, and a control unit 704. The adding unit 701 is configured to, in response to determining that a target object moves from a first position to a second position, add a field of view penalty term in a target path planning model to obtain an added path planning model, wherein the first position and the second position are between a target motion marker, and the field of view penalty term represents path penalty in the case that the target motion marker is not present in the motion field of view. The configuring unit 702 is configured to configure field of view constraint information corresponding to the added path planning model. The generating unit 703 is configured to generate a first optimal motion path satisfying the field of view constraint information by using the added path planning model according to motion parameter information, wherein the motion parameter information represents motion parameters in the process of the target object moving from the first position to the second position. The control unit 704 is configured to control the target object to move according to the first optimal motion path.

[0095] In some optional implementations of some embodiments, the adding unit 701 can be further configured to, in response to determining that the target object moves to a target position, obtain a field of view penalty term for the target motion marker sent by a target motion system, wherein the target position is a position between the first position and the second position; and add the field of view penalty term in the target path planning model to generate an added path planning model.

[0096] In some optional implementations of some embodiments, the field of view penalty term includes a first field of view penalty parameter corresponding to the first field of view orientation and a second field of view penalty parameter corresponding to the second field of view orientation; and the adding unit 701 can be further configured to: add the first field of view penalty parameter and the second field of view penalty parameter to generate an added parameter; multiply the added parameter by a preset penalty coefficient to generate a multiplied parameter; and add the multiplied parameter to the target path planning model to generate an added path planning model.

[0097] In some optional implementations of some embodiments, the added path planning model is an added term between the path point deviation term, the object control penalty term, and the field of view penalty term, and the added path planning model has corresponding object control quantity constraint information, obstacle avoidance constraint information, and starting point constraint information; and the generating unit 703 can be further configured to: perform optimal solution calculation on the added path planning model according to the motion parameter information to generate the first optimal motion path, where the first optimal motion path satisfies the object control quantity constraint information, the obstacle avoidance constraint information, the starting point constraint information, and the field of view constraint information.

[0098] In some optional implementations of some embodiments, the adding unit 701 can be further configured to: in response to determining that the target object does not move to the target position, generate a second optimal motion path based on the target path planning model; and control the target object to move according to the second optimal motion path to move to the target position.

[0099] It can be understood that the units described in the object motion control apparatus 700 correspond to the respective steps in the method described with reference to Figure 3 Thus, the operations, features, and advantages described above for the method also apply to the object motion control apparatus 700 and the units included therein, and are not repeated here.

[0100] Reference is made below to Figure 8 , which shows a structural schematic diagram of an electronic device (for example, the electronic device 101 in Figure 1 ) 800 suitable for use to implement some embodiments of the present disclosure. Figure 8 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of embodiments of the present disclosure.

[0101] As Figure 8As shown, the electronic device 800 can include a processing device (e.g., a central processor, a graphics processor, etc.) 801 that can perform various suitable actions and processes in accordance with programs stored in a read only memory 802 or loaded from a storage device 808 into a random access memory 803. Various programs and data required by the electronic device 800 to operate are also stored in the random access memory 803. The processing device 801, the read only memory 802, and the random access memory 803 are connected to each other by a bus 804. An input / output interface 805 is also connected to the bus 804.

[0102] Generally, the following devices can be connected to the input / output interface 805: input devices 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 808 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 809. The communication devices 809 can allow the electronic device 800 to communicate wirelessly or wired with other devices to exchange data. Although Figure 8 The electronic device 800 is shown with various devices, but it should be understood that not all of the shown devices are required to be implemented or present. More or fewer devices can alternatively be implemented or present. Figure 8 Each block shown in the flowcharts can represent a device or multiple devices as needed.

[0103] In particular, processes described above with reference to the flowcharts can be implemented as a computer software program according to some embodiments of the present disclosure. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In some such embodiments, the computer program can be downloaded and installed from a network through the communication devices 809, or installed from the storage devices 808, or installed from the read only memory 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the methods of some embodiments of the present disclosure are performed.

[0104] Note that the computer-readable medium or media used to provide the computer program sequence to the computer system can be embedded in a computer program product, which comprises all the respective features, which are provided with the computer program sequence, and which are enumerated above. It is understood that the computer-readable medium or media described herein are included in the computer program product, or are a component of the computer program product. In some embodiments of the disclosure, the computer-readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer-readable storage medium can be any tangible medium that contains, or stores a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the disclosure, a computer-readable signal medium can include a computer-readable storage medium in baseband or propagated as a carrier wave in a propagated data signal, which contains a computer-readable program code. Such a propagated signal can take a wide variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium that is not a computer-readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0105] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any current known or future developed networks.

[0106] The computer readable medium can be included in the electronic device, or can exist separately from the electronic device. The computer readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to determining that a target object moves from a first position to a second position, where a target motion marker exists between the first position and the second position, add a field of view penalty term to a target path planning model to obtain an added path planning model, where the field of view penalty term represents path penalty in a case where the target motion marker does not exist in a motion field of view; configure field of view constraint information corresponding to the added path planning model; generate, according to motion parameter information representing a motion parameter in a process in which the target object moves from the first position to the second position, a first optimal motion path that satisfies the field of view constraint information by using the added path planning model; and control the target object to move according to the first optimal motion path.

[0107] Computer program code for carrying out operations of some embodiments of the disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0109] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor. For example, they may be described as: a processor comprising an adding unit, a configuration unit, a generating unit, and a control unit. The names of these units do not, in some cases, constitute limitations on the units themselves. For example, the control unit may also be described as a "unit for controlling the target object to move according to the first optimal motion path."

[0110] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0111] Some embodiments of the present disclosure further provide a computer program product, including a computer program, which implements any of the above-mentioned motion control methods when executed by a processor.

[0112] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for controlling object motion, comprising: In response to determining that the target object moves from a first position to a second position, adding a field of view penalty term to the target path planning model to obtain a post-addition path planning model, wherein a target motion marker exists between the first position and the second position, and the field of view penalty term represents a path penalty when the target motion marker is not present in the motion field of view; Configuring the field of view constraint information corresponding to the added path planning model; generating, based on the motion parameter information and utilizing the added path planning model, a first optimal motion path that satisfies the field of view constraint information, wherein the motion parameter information represents motion parameters of the target object during the process of moving from the first position to the second position; The target object is controlled to move according to the first optimal motion path.

2. The method according to claim 1, wherein In response to determining that the target object moves from the first position to the second position, adding a field of view penalty term to the target path planning model to obtain a post-addition path planning model includes: In response to determining that the target object moves to a target position, obtaining a field of view penalty item for the target motion marker sent by a target motion system, wherein the target position is a position between the first position and the second position; The vision penalty term is added to the target path planning model to generate a post-addition path planning model.

3. The method according to any one of claims 1 to 2, wherein: The field of view penalty item includes: a first field of view penalty parameter corresponding to the first field of view orientation and a second field of view penalty parameter corresponding to the second field of view orientation; and Adding the vision penalty term to the target path planning model to generate a post-addition path planning model includes: Adding the first view penalty parameter and the second view penalty parameter to generate an added parameter; Multiplying the added parameter by a preset penalty coefficient to generate a multiplied parameter; The multiplication parameters are added to the target path planning model to generate a post-addition path planning model.

4. The method according to claim 3, wherein: The field of view constraint information includes: constraint information characterizing that the target motion marker is in a first direction of a first orientation vector, and constraint information characterizing that the target motion marker is in a second direction of a second orientation vector, wherein the first orientation vector is the orientation vector corresponding to the first field of view orientation, and the second orientation vector is the orientation vector corresponding to the second field of view orientation.

5. The method according to claim 1, wherein The added path planning model is the sum of the path point deviation term, the object control penalty term, and the field of view penalty term, and the added path planning model has corresponding object control amount constraint information, obstacle avoidance constraint information, and starting point constraint information; as well as The step of generating a first optimal motion path that satisfies the field of view constraint information by using the added path planning model according to the motion parameter information includes: Based on the motion parameter information, an optimal solution is obtained for the added path planning model to generate the first optimal motion path, wherein the first optimal motion path satisfies the object control amount constraint information, the obstacle avoidance constraint information, the starting point constraint information and the field of view constraint information.

6. The method according to claim 2, wherein: Before acquiring the field of view penalty item for the target motion marker sent by the target motion system in response to determining that the target object has moved to the target position, the method further includes: In response to determining that the target object has not moved to the target position, generating a second optimal motion path based on the target path planning model; The target object is controlled to move according to the second optimal motion path to move to the target position.

7. An object motion control device comprising: an adding unit configured to, in response to determining that the target object moves from a first position to a second position, add a field of view penalty term to the target path planning model to obtain a post-addition path planning model, wherein a target motion marker exists between the first position and the second position, and the field of view penalty term represents a path penalty when the target motion marker does not exist in the motion field of view; a configuration unit, configured to configure the field of view constraint information corresponding to the added path planning model; a generating unit configured to generate a first optimal motion path satisfying the field of view constraint information using the added path planning model according to motion parameter information, wherein the motion parameter information represents motion parameters of the target object during the process of moving from the first position to the second position; A control unit is configured to control the target object to move according to the first optimal motion path.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images