WO2018107505A1 - 一种对目标进行控制的方法、控制装置及控制设备 - Google Patents

一种对目标进行控制的方法、控制装置及控制设备 Download PDF

Info

Publication number
WO2018107505A1
WO2018107505A1 PCT/CN2016/110567 CN2016110567W WO2018107505A1 WO 2018107505 A1 WO2018107505 A1 WO 2018107505A1 CN 2016110567 W CN2016110567 W CN 2016110567W WO 2018107505 A1 WO2018107505 A1 WO 2018107505A1
Authority
WO
WIPO (PCT)
Prior art keywords
branch point
target
control
level
task
Prior art date
Application number
PCT/CN2016/110567
Other languages
English (en)
French (fr)
Inventor
骆磊
Original Assignee
深圳前海达闼云端智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳前海达闼云端智能科技有限公司 filed Critical 深圳前海达闼云端智能科技有限公司
Priority to PCT/CN2016/110567 priority Critical patent/WO2018107505A1/zh
Priority to CN201680002692.0A priority patent/CN106716282B/zh
Publication of WO2018107505A1 publication Critical patent/WO2018107505A1/zh
Priority to US16/428,996 priority patent/US20190302779A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0287—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling
    • G05D1/0291—Fleet control
    • G05D1/0297—Fleet control by controlling means in a control room
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0287—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
    • G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4812—Task transfer initiation or dispatching by interrupt, e.g. masked
    • G06F9/4818—Priority circuits therefor

Definitions

  • the present application relates to the field of intelligent control technologies, and in particular, to a method, a control device, and a control device for controlling a target.
  • the embodiment of the present application proposes a method, a control device, a control device, and a computer readable storage medium for controlling a target, so as to solve the technical problem existing in the prior art due to limitations imposed by manual implementation of the control.
  • an embodiment of the present application provides a method for controlling a target, including: acquiring a current location of a target; and determining, according to the current location of the target, performing the target
  • the controlled member and each member should arrive at the location and time, and for each selected member, notify the member of the specified location and time that the member should arrive; the location is a location at which the target can be controlled;
  • Some or all of the members are robots.
  • an embodiment of the present application provides an apparatus for controlling a target, including a target acquiring module, a control module, and a notification module;
  • a target acquisition module configured to acquire a current location of the target
  • control module configured to determine, according to the current location of the target, a member and each member to reach a position and time; the position is a position at which the target can be controlled; and the selected member is part or all of a robot;
  • the notification module is configured to notify the member of the selected member and the specified location and time that the member should arrive for each selected member.
  • an embodiment of the present application provides an apparatus for controlling a target, including a processor and a communication component;
  • a processor configured to acquire a current location of the target; and a member and a member for determining the location and time to be controlled according to the current location of the target; the location is a location at which the target can be controlled; Some or all of the selected members are robots.
  • a communication component for notifying the member of the specified location and time that the member should arrive for each selected member.
  • embodiments of the present application provide a computer readable storage medium storing computer instructions for causing the computer to perform various steps of the above described control methods.
  • the target is controlled by calculating a real-time deployment member, and the control may be blocking, pursuing or rescuing the target. Since some or all of the members controlling the target in this application are robots, the manual control (such as hunting, blocking, etc.) is reduced as much as possible. The limitations caused. The degree of automation and intelligent control of the solution of this application far exceeds the current manual control mode, which will be a direction for future development.
  • FIG. 1 is a schematic plan view showing a position of a target in an embodiment of the present application
  • Embodiment 2 is a flow chart showing a method for controlling a target in Embodiment 1 of the present application
  • FIG. 3 is a schematic structural diagram of an apparatus for controlling a target in Embodiment 2 of the present application.
  • FIG. 4 is a schematic structural diagram of an apparatus for controlling a target in Embodiment 3 of the present application.
  • the work of controlling the target is manually performed.
  • the manual control method cannot fully meet the needs due to the limited number and physical strength of the personnel, and the route, time, frequency, and density.
  • due to manual control it is impossible to transmit the image of the scene and other information back to the monitoring center in real time, which brings inconvenience to the command decision for the emergency.
  • the manual control method has a high success rate and endangers personal safety, and has great limitations.
  • the embodiment of the present application provides a method, a control device, a control device, and a computer readable storage medium for controlling a target, and the member and each member that can control the target according to the current location of the target should be determined.
  • Arrival location and time for each selected member, notify the member of the specified location and time that the member should arrive; the location is a location that can control the target; some or all members who control the target are Robot, according to the target line
  • the current global state of the process is unified and coordinated to dynamically maintain the members of the implementation control; the control may be to block, hunt or rescue the target. The details will be described below.
  • FIG. 1 is a schematic diagram of a scenario when the target is controlled in the embodiment of the present application. Assume that the current street scene top view is as shown in FIG. 1 , and the intersections of the two streets are respectively marked with letters, and the target is currently between B3 and C3. O1 point, and is traveling in the direction of B3 with speed v.
  • the white circle in the figure is the control member in the task or idle state.
  • Step 1 Obtain the current location of the target to be controlled
  • control end such as the cloud
  • the control may monitor the target and confirm the location thereof, or may obtain the target location that has been determined from other paths, which is not limited by the embodiment of the present application.
  • Step 2 Determine, according to the current location of the target, the member and each member that should control the target, and the location and time, and for each selected member, notify the member of the designated location and time that the member should arrive.
  • the position is a position at which the target can be controlled; the member is part or all of a robot.
  • the control here can be to block, chase, hunt or rescue the target.
  • step 1 obtaining the current location of the target specifically includes:
  • the intersection closest to the target on the road is the first-level branch point.
  • the primary branch points are B3 and C3.
  • each road where the target is located The intersections adjacent to the target are all first-level branch points; as shown in Fig. 1, if the current position of the target is O2, the first-level branch points are C3, C5, B4, and D4.
  • step 2 the members that control the target according to the current location of the target include:
  • Step 21 determining, according to the target image and the map related information such as road conditions, the maximum possible average moving speed vmax of the target for a period of time, assuming that the primary branching point for controlling the target is n, and determining the target to each level according to the vmax.
  • control end such as the cloud
  • the control end may be, but is not limited to, giving a vmax experience value according to the target current speed v and the target shape, and the experience value may be Based on historical statistics of many data on many targets.
  • Step 22 For each primary branch point, check the status of the nearby members to determine whether at least one member can move to the first-level branch point in the shortest time, that is, the computing member arrives at the branch at its average speed. Whether the time of the point does not exceed the minimum time, the shortest time is the time at which the target reaches the branch point at the current maximum speed; if yes, step 23 is performed; otherwise, step 24 is performed;
  • control end stores information about each member, such as the maximum speed at which the task is executed, the average speed, and the like; the member selected by the control terminal for each branch point is a different member.
  • Step 23 Select at least one member to perform a control task for the target, and notify the selected member to rush to the first branch point in the shortest time; the shortest time is the time at which the target reaches the branch point at the current maximum speed.
  • Step 24 If one or more primary branch points exist, no member can arrive in the shortest time. In the case of the point, the next branch point is searched for the branch point, that is, the second branch point; whether there is a member near each level branch point can arrive before the target arrives at the second branch point, and if yes, the steps are executed. 25, otherwise step 26; in this step, the members selected for each branch point are different members;
  • the secondary branch point is the next intersection away from the target on the road where the primary branch point is located, as shown in Figure 1, if the primary branch point B3 of the target O1 has no members before the target reaches the point at the current maximum speed.
  • B3 the primary branch point of the target O1
  • B4 the secondary branch points of B3, namely B2, A3 and B4.
  • Step 25 If yes, select at least one member to perform a control task for the target, and notify the selected member to rush to the secondary branch point before the target reaches the point.
  • Step 26 If there is still no member in the secondary branch point, the target can reach the point before the target reaches the point, that is, control cannot be implemented at the point (such as blocking), and then the next level branch of the second node is continuously searched. Point; and according to the above method to determine whether the next level branch point meets the control requirements, that is, whether a member can arrive at the point before the target reaches the point.
  • the threshold level is reached until the branch point level at which the control or lookup of the target can be completed at the branch point.
  • the specific search for several levels of branch points can be flexibly set according to specific tasks, terrain and other factors, and this application does not limit this.
  • the maximum number of branch points can be found as the set threshold.
  • the setting of each priority task may be different.
  • the control may not be satisfied.
  • the search determines whether a branch point has a member to control the target at the branch point, if the branch point has been previously searched and judged, no further search judgment is made.
  • the member in the hunt candidate team that is in the idle state satisfies that one or more members can reach C3 point in tC3 time, and one or more members can be in tB2 time.
  • one or more members can reach the A3 point within tA3 time, and one or more members can reach the B4 point within tB4 time, then
  • the control of target O1 can be completed; tC3, tB2, tA3 and tB4 are the shortest time for the target to reach the corresponding branch point.
  • the tasks of the control target are prioritized, and the tasks of the control target are divided into N priorities. How to divide the specific priorities and perform the tasks requires the quality and equipment of each member according to the actual situation. The situation is determined, and this application does not limit this. It should be noted that the more priority divisions are, the finer the target level is, the higher the intelligence is, but it depends on the actual situation. If the details are too small, the meaning of the initial priority will be more complicated.
  • the number of members required for the current control task and/or the number of equipment to be carried are analyzed and estimated according to the identified target. For example, this task is to arrest the target. If it is identified that the other party may have firearms or other weapons, it is determined that it is necessary to carry weapons and equipment that can restrict the other party; if the other party is identified as one or more suspicious robots, according to the large database Or intelligent analysis to determine the weakness of this / these robots and how to subdue them, such as how to determine the most easy to destroy their ability to move, how to most easily cut off their power supply, how to interfere with their activation of the self-detonation device, etc., and then determine the constraints A member of the robot's capabilities.
  • the current task priority is 2, and some ability is required to complete the control, such as completing the arrest (if the maximum speed is required to be at least 2*v, you need to carry weapons, etc.).
  • the members in the idle state are preferentially selected, and if there is no current idle member, the target can arrive before the target arrives at the point.
  • Point select at least one of the members of the lower priority task currently being executed to perform the task, and select from among the members who perform the lowest priority task. If no member of each low priority task can arrive before the target arrives at the branch point at the current maximum speed, the next level branch point of the branch point is looked up.
  • a threshold is set for each task, which may be the same priority task whose threshold is the same, and the threshold indicates that the completion probability of executing the control task cannot be lower than the set threshold.
  • next-level branch node When a member cannot be selected from the member who performs the lowest priority task to join the current task, it is judged from the next low priority task whether the member can be selected to join the current task; and so on, until a member who can join the current task is found, or After finding all the low-level priorities that are being executed, there are still not enough members to join the current task to determine whether the next-level branch node can be controlled (such as blocking).
  • the notification is confirmed and notified.
  • the member can arrive at the branch point before the target reaches the first-level branch point without rushing to the first-level branch point in the shortest time.
  • the control end (such as the cloud) confirms that the member moves according to the target movement condition, and if the target moves to B3, Then, the control end confirms and informs the member that it can move to C3 or monitor in place immediately after the target. If the target moves in the direction of C3, the control end confirms and informs that the member also moves to C3, and each member moves according to the received instruction. To ensure that the target reaches C3 before it reaches C3.
  • the control end (such as the cloud) confirms and informs the member that the target crosses between O1 and B3, and then moves according to the target movement condition.
  • the target moves in the direction of B3, it is confirmed and notified that the member arrives at B3 before the target reaches B3, and each member receiving the instruction moves according to the instruction.
  • the selected member is located at the i-th level Between the fulcrum and the i-1th branch point, the member is confirmed and notified to move preferentially to the i-1th branch point without first reaching the i-th branch point, for example, for the second branch point B2
  • the member selected for B2 is located between B2 and B3, and then the member is confirmed and notified to move to B3 without first arriving at B2, and each member receiving the notification moves according to the instruction.
  • the member when the selected member arrives at the corresponding branch point, if the target has not arrived, the member is confirmed and notified to continue to advance to the target position until the target is merged to complete the control work (such as capture), the task ends, and the control terminal (such as the cloud) confirm and notify the participating control members to enter the idle state.
  • the control work such as capture
  • the task ends and the control terminal (such as the cloud) confirm and notify the participating control members to enter the idle state.
  • the control end (such as the cloud) confirms that the lower-level branch point control that is branched by the branch point can be canceled, and the member can be released. , confirms and notifies the member to become idle or to resume its previous state (such as a lower priority task was previously executed).
  • the control end (such as the cloud) retains the way control member, and confirms that the release task is to control the members of B2 and A3, and informs the members of control B2 and A3 to be released.
  • cloud computing and control team analysis are performed in real time at a certain frequency, so team members may change at any time. For example, for target O1, assuming that B3 is not initially controllable, but an individual member suddenly completes its previous task between O1B3, is in an idle state, and satisfies the set of conditions for this task, the member is immediately assigned to this In the task control team, the members who control the secondary branch points B2, A3, and B4 can be released immediately.
  • the cloud shares the target real-time coordinates, images or real-time video to the entire control team, and the information between the team members is completely shared.
  • the target is rushed.
  • the control end (such as the cloud) confirms that each member only needs to chase, and the control terminal recalculates the control in real time according to the above steps and establishes a new control team until the target is controlled (such as being captured).
  • the multi-level branch point is used to determine whether the target can be controlled step by step, and the method of dynamically controlling the control team according to the current control state is performed in real time through the cloud computing, so that the personnel input can be minimized under the premise of ensuring control.
  • the control of the lower-level branch point is immediately released, and even if the target breaks through the control, the cloud can immediately calculate the new control mode and the new control team.
  • the information of members in the group is always synchronized until the task is completed or terminated.
  • the degree of automation and intelligence of the program far exceeds the current control method and will be a direction for future development.
  • the cloud analyzes and determines the priority of the task according to various factors, and then determines the control team according to the priority, the real-time speed of the current target, the map information, and the current state of the robot/police controlled within a certain range. And according to the intelligent algorithm to determine and inform each member's respective travel route, in the process of controlling (such as encircling and arresting) the target, coordinate and maintain the control team dynamically according to the current global state, and if necessary, join the new control by the cloud control. The member releases the current part of the member when certain conditions are met, and always keeps the information of the members in the group synchronized until the task is completed or terminated. Without performing the task efficiently, no unnecessary control resources are wasted, and if the control team is all For robots or robots, the risk of personnel can be reduced.
  • the scheme utilizes multi-level branch points to determine whether the target can be controlled step by step, and dynamically adjusts the method for controlling members according to the current control state, and can minimize the personnel input under the premise of ensuring control, once the higher-level branch point is controlled Immediately release the control of the lower branch point, and even if the target breaks through the control, the cloud can immediately calculate the new control method and the new control team.
  • the information of members in the group is always synchronized until the task is completed or terminated.
  • the device includes: a target acquisition module, a control module, and a notification module;
  • a target acquisition module configured to acquire a current location of the target to be controlled
  • control module configured to determine, according to the current location of the target, a member and each member that should control the target, the location and time; the location is a location that can control the target; and the selected member is part or all of robot.
  • the control here can be blockade, chase, hunt or rescue.
  • the notification module is configured to notify the member of the selected member and the specified location and time that the member should arrive for each selected member.
  • the acquiring, by the target acquiring module, the current location of the target includes: acquiring a current location of the target on the map, and at least one primary branch point controlling the target, where the at least one branch point is a position at which the member can control the target; and is also used to determine a next-level branch point of the branch point when a certain branch point cannot be controlled, that is, when a certain one-level branch point cannot be controlled
  • the secondary branch point of the primary branch point determines the third-level branch point of the secondary branch point when a secondary branch point cannot be controlled.
  • Determining, by the control module, the member that controls the target and the position that each member should reach according to the current location of the target includes: determining, for each determined one-level branch point, whether at least one member can be at the current maximum speed of the target Arriving before reaching the branch point, that is, calculating whether the time at which the member reaches the branch point at its average speed does not exceed the time at which the target reaches the branch point at the current maximum speed, and then selecting members for the first-level branch point and determining each The time when the member reaches the corresponding one-level branch point, which should be no later than the time when the target reaches the branch point.
  • the target can be controlled, that is, A member can rush to the branch point before the target arrives, and the control module further searches for each of the next-level branch points of the first-level branch point, that is, the second-level branch point, and determines whether a member can access each of the second-level branch points.
  • Controlling that is, for each secondary branch point, whether at least one member can rush to the secondary branch point before the target reaches the secondary branch point at the current maximum speed, and if so, select at least one member and Determining the time when each member reaches the corresponding secondary branch point, which should be no later than the time at which the target reaches the branch point at the current maximum speed; otherwise, the branch that continues to reach the next level before the target arrives continues to find the branch of the next level. Point until the branch point level at which the target control or lookup can be completed at the branch point reaches a threshold.
  • the search determines whether a branch point has a member to control the target at the branch point, if the branch point has been previously searched and judged, no further search judgment is made.
  • control module selects members for each branch point, it selects different members for different branch points.
  • the maximum number of branch points can be found as the set threshold.
  • the setting of each priority task may be different. After the threshold is reached, the control may not be satisfied. Return to the first branch point to determine whether the control can be completed. If the current situation cannot be performed. For control, chasing is used first, but the calculation is real-time, and the position of the target is constantly changing in the map. At some point, it is possible to control the target, such as blocking.
  • the device further includes a setting module
  • the setting module is configured to prioritize tasks
  • the control module selects a member, the member in the idle state is preferentially selected
  • control module When the control module is further configured to select a member for performing control for a certain branch point, if none of the members in the idle state can reach the branch point before the target rushes to the branch point, the slave task is prioritized over the current task. Selecting at least one member of the low level task to perform control of the branch point; if no member of each low priority task can find the branch before the target arrives at the current maximum speed before reaching the branch point The next branch point of the point.
  • the setting module is further configured to set a threshold for each task, and the tasks of the same priority have the same threshold, and the threshold indicates the possibility of completing the task when the control task is executed. Cannot fall below this set threshold.
  • control module determines the location that the member should reach, if the selected member is located between the primary branch point and the target, as shown in FIG. 1 , if the selected member is between O1 and C3, the confirmation is performed.
  • the member moves or stays in place to monitor the target without first coming to the first branch point; if the member selection is made for the i-th branch point, i ⁇ 2, the selected member is located at the i-th branch point Between the branch point of the i-1th level, it is confirmed that the member moves preferentially to the i-1th branch point without first reaching the i-th branch point, for example, when selecting a member for the second branch point B2 If the member selected for B2 is between B2 and B3, then the member moves to B3 without first arriving at B2.
  • the control module is further configured to: when selecting a member from the lower priority tasks, determine whether the completion probability of the lower priority task is still not low after the selected member exits the task being executed Setting a threshold thereon, if yes, determining that the member exits the task being executed to join the current task, and the branch point and time that the member should arrive, otherwise determining that the member does not exit the lower priority being executed task.
  • control module is further configured to: when the selected member reaches the corresponding branch point, if the target has not arrived, determine that the member continues to advance to the target position, until the target merges to complete the control, the task ends, and the participation control is updated. The member enters the idle state or restores the previous state.
  • the notification module is further configured to notify the member to continue to advance to the target location until the target is merged to complete the control, and notify all members of the execution control task to enter the idle state or the state before the recovery after the task ends.
  • the control module is further configured to: if a member controls a higher-level branch point in the control process, determine to cancel control of a lower-level branch point that is branched by the branch point, and release the lower one A member of a branch point of the level that updates the state of the member of the lower-level branch point to an idle state or restores its previous state.
  • the notification module is further configured to notify the member when a member of one or more branch points is released The member enters the idle state or resumes the previous state.
  • an apparatus for controlling a target is also provided in the embodiment of the present application.
  • the control device in this embodiment refer to the implementation of the control method in the first embodiment, and details are not described herein again.
  • the processor and the communication component are included;
  • a processor configured to obtain a current location of the target to be controlled; and a member and a member to control the position and time to be controlled according to the current location of the target; the position is to control the target
  • the location of the selected member is part or all of the robot.
  • the control here can be blocking or chasing.
  • a communication component for notifying the member of the specified location and time that the member should arrive for each selected member.
  • the acquiring, by the processor, the current location of the target to be controlled includes: acquiring a current location of the target on a map, and at least one primary branch point that controls the target, where the at least one primary branch point is a position at which the member can control the target; and is also used to determine a next-level branch point of the branch point when a certain branch point cannot be controlled, that is, when a certain branch point cannot be controlled.
  • the secondary branch point of the primary branch point is determined, and when a secondary branch point cannot be controlled, the third-level branch point of the secondary branch point is determined.
  • Determining, by the processor, that the member that controls the target and the member should reach the location according to the current location of the target includes: determining, for each determined one-level branch point, whether at least one member can be at the current maximum speed of the target Arriving before reaching the branch point, that is, calculating whether the time at which the member reaches the branch point at its average speed does not exceed the time at which the target reaches the branch point at the current maximum speed, and then selecting members for the first-level branch point and determining each The time when the member reaches the corresponding one-level branch point, which should be no later than the time when the target reaches the branch point.
  • the processor further searches for the level Each of the next-level branch points of the branch point is a secondary branch point, and it is determined whether there is a member that can control each of the second-level branch points, that is, for each of the second-level branch points, whether at least one member can be at the target at the current maximum Arriving at the secondary branch point before the speed reaches the secondary branch point, if at least one member is selected and determining the time at which each member reaches the corresponding secondary branch point, the time should be no later than the target reaching the branch point time.
  • the processor selects members for each branch point, the processor selects different members for different branch points.
  • the device further includes a setting component
  • the setting component is used to prioritize tasks
  • the processor preferentially selects a member in an idle state when selecting a member
  • the processor is further configured to select a member for performing control for a certain branch point, if none of the members in the idle state can rush to the branch point before the target rushes to the branch point, the slave task has priority over the current task. Selecting at least one member of the low level task to perform control of the branch point; if no member of each low priority task can find the branch before the target arrives at the current maximum speed before reaching the branch point The next branch point of the point.
  • the setting component is further configured to set a threshold for each task, and may be the same priority task whose threshold is the same, and the threshold indicates that the task completion possibility cannot be lower than the set threshold when the control task is executed.
  • the processor is further configured to: when selecting a member from the lower priority tasks, determine whether the completion probability of the lower priority task is still not low after the selected member exits the task being executed Setting a threshold thereon, if yes, determining that the member exits the task being executed to join the current task, and the branch point and time that the member should arrive, otherwise determining that the member does not exit the lower priority being executed task.
  • the processor determines the location that the member should reach, if the selected member bit Between the first branch point and the target, as shown in FIG. 1, assuming that the selected member is between O1 and C3, it is confirmed that the member follows the target moving or stays in the original monitoring target without first going to the first one.
  • Level branch point if member selection is made for the i-th branch point, i ⁇ 2, and the selected member is located between the i-th branch point and the i-1th-level branch point, then it is confirmed that the member preferentially goes to the first
  • the i-1 level branch point moves without first reaching the i-th branch point. For example, when a member is selected for the second branch point B2, and the member selected for B2 is located between B2 and B3, the member moves to B3. No need to reach B2 first.
  • the processor is further configured to: when the selected member arrives at the corresponding branch point, if the target has not arrived, determine and notify the member to continue to advance to the target location, until the target merges to complete the control, the task ends, and is updated.
  • the member participating in the control enters the idle state or the state before the recovery.
  • the communication component is further configured to notify the member to continue to advance to the target location until the target is merged to complete the control, and notify all members of the execution control task to enter the idle state or the state before the recovery after the task ends.
  • the processor is further configured to: if a member controls a higher-level branch point in the control process, determine to cancel control of a lower-level branch point that is branched by the branch point, and release the low one A member of a branch point of the level that updates the state of the member of the lower-level branch point to an idle state or restores its previous state.
  • the communication component is further configured to notify the member to enter an idle state or a state before recovery when a member of one or more branch points is released.
  • a computer readable storage medium is further provided in the embodiment of the present application, where the computer readable storage medium stores computer instructions for causing the computer to execute the method in the foregoing embodiment Each step.
  • the real-time deployment member controls the target through the calculation of the cloud, such as blocking or chasing. Since some or all of the members of the control used in this application are robots, the limitations due to manual control are reduced as much as possible.
  • the solution utilizes multi-level branch points to determine whether the target can be controlled step by step, and dynamically adjusts the method for controlling members according to the current control state, and can minimize the personnel input under the premise of ensuring control, once the first-level branch point is high. Being controlled immediately releases the control of the lower branch point, and even if the target breaks through the control, the cloud can immediately calculate the new control method and the new control team.
  • the information of members in the group is always synchronized until the task is completed or terminated.
  • the cloud analyzes and determines the priority of the task according to various factors, and then according to the priority, the real-time speed of the current target, the map information, and the current state of the member performing control within a certain range, such as the current state of the robot/police, Determine the control team, and determine and inform each member's respective route according to the intelligent algorithm.
  • the target such as encirclement and arrest
  • coordinate and maintain the control group dynamically according to the current global state if necessary, if necessary
  • the new member is added by the cloud control or the current part member is released when certain conditions are met, and the information of the members in the group is always synchronized until the task is completed or terminated, and unnecessary control resources are not wasted under the premise of efficiently performing the task.
  • the control team is all robots or robots, it can reduce the risk of personnel.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Manipulator (AREA)

Abstract

一种对目标进行控制的方法、控制装置、控制设备及计算机可读介质，该方法包括：获取目标当前所处位置；根据目标当前所处位置确定对所述目标进行控制的成员及各成员应到达位置和时间，针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员；所述位置为可对目标进行控制的位置；所述成员部分或全部为机器人。上述方法通过云端计算的实时对实施控制的成员进行调整，实现智能化的控制，可解决现有技术中由于人工控制造成的局限性的技术问题。

Description

一种对目标进行控制的方法、控制装置及控制设备 技术领域
本申请涉及智能控制技术领域，尤其涉及一种对目标进行控制的方法、控制装置及控制设备。
背景技术
当前机器人领域的发展迅猛，若干年之后，很多行业必将由机器人替代人工。现有技术中，对目标实施控制的工作几乎都由人工完成，例如对目标进行巡逻搜寻、追捕或解救等，现有的控制手段由于耗费大量人工，且效率不高，识别手段不如机器算法准确，且有伤亡的危险，很有可能成为较早被机器人、无人机等替代的领域。尤其是确定了目标坐标之后，当前必然需要人去完成最后的控制工作(例如封锁、追捕、解救等)，而人的先天条件，如暗光下看不清，眼睛找寻目标速度较慢等等，制约了对目标进行控制的成功率，另外遇到携带武器的目标人员或者目标本身就是机器人，则实施控制的过程危险性也较高。
现有技术不足在于：
现有技术中对目标进行控制的工作几乎都由人工完成，成功率不高且危及人身安全，存在较大局限性。
发明内容
本申请实施例提出了一种对目标进行控制的方法、控制装置、控制设备及计算机可读存储介质，以解决现有技术中现有由于人工实施控制造成的局限性的技术问题。
在一个方面，本申请实施例提供了一种对目标进行控制的方法，包括：获取目标当前所处位置；根据所述目标当前所处位置确定对所述目标实施 控制的成员及各成员应到达位置及时间，针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员；所述位置为可对所述目标进行控制的位置；所述成员部分或全部为机器人。
在另一个方面，本申请实施例提供了一种对目标进行控制的装置，包括目标获取模块，控制模块及通知模块；
目标获取模块，用于获取目标当前所处位置；
控制模块，用于根据目标当前所处位置确定对其进行控制的成员及各成员应到达位置及时间；所述位置为可对目标进行控制的位置；所述选择的成员部分或全部为机器人；
通知模块，用于针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员。
在另一个方面，本申请实施例提供了一种对目标进行控制的设备，包括处理器及通信组件；
处理器，用于获取目标的当前所处位置；以及用于根据目标当前所处位置确定对其进行控制的成员及各成员应到达位置及时间；所述位置为可对目标进行控制的位置；所述选择的成员部分或全部为机器人。
通信组件，用于针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员。
在另一个方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储计算机指令，所述计算机指令用于使所述计算机执行上述控制方法中的各个步骤。
有益效果如下：
采用本申请方案，通过计算实时调配成员对目标进行控制，该控制可以是对目标进行封锁、追捕或解救等。由于本申请中对目标进行控制的成员部分或全部为机器人，尽可能地降低了由于人工控制(如追捕、封锁等) 造成的局限性。本申请方案的自动化程度和智能控制水平远超当前的人工控制方式，将是未来发展的一个方向。
附图说明
下面将参照附图描述本申请的具体实施例，其中：
图1示出了本申请实施例中目标所处位置的平面示意图；
图2示出了本申请实施例一中对目标进行控制的方法流程图；
图3示出了本申请实施例二中对目标进行控制的装置结构示意图；
图4示出了本申请实施例三中对目标进行控制的设备结构示意图。
具体实施方式
为了使本申请的技术方案及优点更加清楚明白，以下结合附图对本申请的示例性实施例进行进一步详细的说明，显然，所描述的实施例仅是本申请的一部分实施例，而不是所有实施例的穷举。并且在不冲突的情况下，本申请中的实施例及实施例中的特征可以互相结合。
发明人在研究现有技术的过程中注意到：
现有技术中对目标进行控制的工作都由人工完成，人工控制的方式由于人员的数量和体力有限，其路线、时间、频率、以及密度都不能完全满足需要。另外由于人工控制无法将现场的图像等信息实时回传监控中心，给针对突发事件的指挥决策带来了不便。并且人工控制方式成功率不高且危及人身安全，存在较大局限性。
基于此，本申请实施例提出了一种对目标进行控制的方法、控制装置、控制设备及计算机可读存储介质，可根据目标当前所处位置确定对所述目标进行控制的成员及各成员应到达位置及时间，针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员；该位置为可对目标进行控制的位置；对目标进行控制的部分或全部成员为机器人，根据目标行 进过程中的当前全局状态统一协调并实时动态维护实施控制的成员；该控制可以是对目标进行封锁、追捕或解救等等。下面进行具体说明。
图1示出了本申请实施例中对目标实施控制时场景示意图，假设当前街道场景俯视图如图1所示，两条街道的交点分别用字母进行了标注，假设目标当前处于B3与C3间的O1点，且正以速度v向B3方向行进，图中白色圆圈为处于任务中或空闲状态的控制成员。
实施例一
如图2所示，对目标进行控制的工作步骤如下所示：
步骤1：获取待控制目标当前所处位置；
该步骤中，可以是实施控制的控制端(如云端)自行对目标进行监控并确认其位置，也可以是从其他途径获取已经确定的目标位置，本申请实施例对此不作限定。
步骤2：根据目标当前所处位置确定对所述目标进行控制的成员及各成员应到达位置及时间，针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员；该位置为可对目标进行控制的位置；所述成员部分或全部为机器人。这里的控制可以是对目标进行封锁、追击、追捕或解救等等。
步骤1中，获取目标当前所处位置具体包括：
获取所述目标在地图上的当前位置，以及至少一级分支点，所述至少一级分支点为所述成员可对所述目标进行控制的位置，一级分支点的确定方式如下：
(1)当目标处在某条道路上(非路口)时，则这条路上距离目标最近的路口即为所述一级分支点。如图1所示，假设目标当前所处位置为O1点，则一级分支点为B3和C3。
(2)当目标处在两条或多条道路的交叉口时，则目标所在的每条道路 上与该目标相邻的路口均为一级分支点；如图1所示，假设目标当前所处位置为O2点，则一级分支点为C3、C5、B4和D4。
步骤2中，根据目标当前所处位置确定对所述目标进行控制的成员包括：
步骤21：根据目标图像结合路况等地图相关信息判定出此目标一段时间内的最大可能平均运动速度vmax，假设控制该目标的一级分支点为n个，根据该vmax判定目标到每个一级分支点m的最短所需时间，如图1中目标从O1点运动到B3和C3的最短所需时间分别为tB3和tC3，假设O1点至B3点的距离为O1B3，O1点至C3点的距离为O1C3，其中tB3＝O1B3/vmax，tC3＝O1C3/vmax；
该步骤中，假设控制端(如云端)无法判定出目标一段时间内的最大可能平均运动速度，则可以但不限于根据目标当前速度v和目标形态给出一个vmax经验值，该经验值可以是基于大数据对众多目标进行的历史统计而得出的。
步骤22：针对每个一级分支点，查看其附近成员情况，判断是否有至少一位成员可以在所述最短时间内移动到该一级分支点，即计算成员以其平均速度到达所述分支点的时间是否不超过该最短时间，该最短时间为目标以当前最大速度达到该分支点的时间；若是则执行步骤23，否则执行步骤24；
该步骤中，控制端存储有每个成员的信息，例如执行任务的最大速度、平均速度等；控制端为每个分支点选择的成员为不同的成员。
步骤23：选择至少一名成员执行对该目标的控制任务，并通知选中的成员在最短时间内赶到一级分支点；该最短时间为目标以当前最大速度达到该分支点的时间。
步骤24：若某个或多个一级分支点存在没有成员能在最短时间内赶到 该点的情况，则针对该分支点查找其下一级分支点，即二级分支点；判断各个二级分支点附近是否有成员可以在目标到达该二级分支点之前到达，若是则执行步骤25，否则执行步骤26；该步骤中，为每个分支点选择的成员为不同的成员；
二级分支点即为该一级分支点所处道路上远离目标的下一路口，如图1所示，若目标O1的一级分支点B3在目标以当前最大速度到达该点之前没有成员可以赶到，则查看该B3的二级分支点，即B2、A3和B4点。
步骤25：若有则选择至少一名成员执行对该目标的控制任务，并通知选中的成员在目标到达该点之前赶到该二级分支点。
步骤26：若该二级分支点仍没有一位成员可在目标到达该点之前赶到该点，即在该点无法实现控制(如封锁)，则继续查找该二级节点的下一级分支点；并按以上方法判断下一级分支点是否满足控制要求，即是否有成员可在目标到达该点之前赶到该点。直到在所述分支点可完成对目标的控制或查找的分支点级别达到阈值。具体查找到几级分支点可根据具体任务、地形等因素灵活设置，本申请对此不作限制。最多查找到几级分支点为设定阈值，每个优先级任务的设定可能不同，到达阈值后则控制可能无法满足，回到一级分支点重新判断是否可进行控制，若当前情况无法进行控制，则先采用追击，但计算是实时的，且目标在地图中位置一直在变化，在某一时刻将可能实现对目标的控制。在查找判断某个分支点是否有成员可在所述分支点对目标进行控制时，若该分支点在之前已经被查找判断过，则不再进一步查找判断。
假设当前任务为对目标O1进行追捕，对于目标O1，假设在追捕候选团队中判定处于空闲状态的成员满足一个或多个成员可在tC3时间内到达C3点，一个或多个成员可在tB2时间内到达B2点，一个或多个成员可在tA3时间内到达A3点，一个或多个成员可在tB4时间内到达B4点，则对 目标O1的控制也就可以完成了；tC3、tB2、tA3及tB4均为目标赶到相应分支点的最短时间。
进一步地，本实施例中对控制目标的任务划分优先级，将控制目标的任务分为N个优先级，具体的优先级如何划分及执行该任务时各成员所需具备素质及装备可根据实际情况确定，本申请对此不作限制。需说明的是，优先级划分越多，目标等级分割的越细，智能化更高，但也要取决于实际情况，过细的话意义不大，造成初始的优先级定义会比较复杂。
在具体实施中，根据识别的目标分析并估算本次控制任务需要的成员数量和/或需要携带的装备的数量。例如本次任务为对目标进行抓捕，如果识别出对方可能有枪支或其他武器，则确定需要携带能制约对方的武器装备等；如果识别出对方为一个或多个可疑机器人，则根据大数据库或者智能分析判定出这个/这些机器人的弱点以及制服其的方法，如确定如何最容易摧毁其行动能力，如何能最容易切断其供电，如何能干扰其启动自爆装置等等，进而确定出能制约该机器人能力的成员。
例如，假设判定当前任务优先级为2级，且需要具备某些能力才能够完成控制，比如完成抓捕(如需要最高速度至少在2*v以上，需要携带武器等等)。
进一步地，上述步骤22、步骤24中为一级分支点、二级分支点等选择成员的过程中，优先选择空闲状态的成员，若当前空闲成员中没有可以在目标赶到该点前到达该点，则从当前正在执行的较低优先级任务中的成员中选择至少一名执行该任务，可优先从执行最低优先级任务的成员中选择。若各低优先级的任务中没有成员可在所述目标以当前最大速度到达所述分支点之前到达则查找所述分支点的下一级分支点。
进一步地，上述过程中当选中某个成员执行对目标的控制任务后更新该成员的状态并记录其执行的任务的优先级。
更进一步地，为每个任务设置阈值，可以是同一优先级的任务其阈值相同，所述阈值表示执行该控制任务时其完成可能性不能低于该设置阈值。当从较低优先级的任务中选择成员加入当前任务时，判断若被选中成员退出所述较低优先级的任务后，所述较低优先级的任务完成可能性是否仍不低于其设定阈值，若是则通知被选中成员退出所述正在执行的较低优先级的任务而加入当前任务，否则被选中成员不退出所述较低优先级的任务。
当从执行最低优先级任务的成员中无法选择成员加入当前任务，则从次低优先级的任务中判断是否可以选择成员加入当前任务；以此类推，直到找到可以加入当前任务的成员，或是查找完所有正在执行的低级别优先级的任务后仍没有足够的成员加入当前任务则判断下一级分支节点是否可以进行控制(如封锁)。
进一步地，上述过程中，若被选中的成员位于被派至的一级分支点与目标之间，或是目标位于被选中的成员与被派至的一级分支点之间，则确认并通知所述成员在目标到达所述一级分支点之前到达该分支点即可，而不用在最短时间内赶到所述一级分支点。
如图1所示，假设对一级分支点C3选择成员时，若被选中成员在O1与C3之间，则控制端(如云端)确认该成员视目标移动情况而移动，若目标往B3移动，则控制端确认并通知该成员可紧随目标向C3移动或在原地监视，若目标向C3方向移动，则控制端确认并通知该成员也向C3移动，各成员则根据接收的指令进行移动，确保在目标到达C3前到达C3。假设对一级分支点B3选择成员时，被选中成员位于O1与C3之间，则控制端(如云端)确认并通知该成员越过目标到达O1与B3之间，然后视目标移动情况而移动，但若目标往B3方向移动，则确认并通知成员在目标到达B3之前到达B3，而接收指令的各成员则根据指令进行移动。
若对第i级分支点进行成员选择时，i≥2，被选中的成员位于第i级分 支点与第i﹣1级分支点之间，则确认并通知所述成员优先地往第i﹣1级分支点移动，而不用先到达所述第i级分支点，例如针对二级分支点B2选择成员时，为B2选择的成员位于B2与B3之间，则确认并通知该成员向B3移动而不用先到达B2，接收通知的各成员则根据指令进行移动。
进一步地，当选择的成员到达对应分支点时若目标还未到达，则确认并通知所述成员向目标位置继续前进，直到与目标会合并完成控制工作(如抓捕)，任务结束，控制端(如云端)确认并通知参与控制成员的进入空闲状态。
进一步地，控制过程中一旦有成员控制(如封锁)了更高一级的分支点，则控制端(如云端)确认此分支点分出的低一级的分支点控制可以取消，成员可以释放，确认并通知成员变成空闲状态或恢复其之前状态(如之前正在执行某个较低优先级的任务)。此例中，对于目标O1，假设最初判定无法控制B3点，而转向控制二级分支点B2，A3，B4，然后，由于目标移动慢于预期，控制B4点的成员到达B4点后继续向目标前进，并先于目标到达B3点，此时，控制端(如云端)保留此路控制成员，而确认释放任务为控制B2和A3的成员，并通知控制B2和A3的成员被释放。
进一步地，云端计算和控制团队分析都是按照一定频率实时进行的，因此团队成员也可能随时发生变化。例如对于目标O1，假设最初无法控制B3点，但在O1B3之间突然有一个个体成员完成了其之前的任务，处于了空闲状态，且满足此任务的条件集合，则该成员立刻被分配到此任务的控制团队中，也就使得之前去控制二级分支点B2，A3，B4的成员都可以立刻被释放。
以上方案中，云端共享目标实时坐标，图像或实时视频给整个控制团队，且团队成员间信息完全共享。
如果最终的控制任务没有控制成功，如需要对目标进行抓捕时目标冲 破控制并逃脱，则控制端(如云端)确认各成员只要先追击，同时控制端实时按照如上步骤重新计算控制并建立新的控制团队即可，直到目标被控制(如被抓捕)。
本实施例方案采用多级分支点逐级判定是否可控制目标，并根据当前的控制状态动态调整控制团队的方法，通过云端计算的实时进行，可在保证控制的前提下尽量降低人员投入，一旦高一级分支点被控制则立刻释放低一级分支点的控制，且即使目标突破了控制，云端也可立刻计算出新的控制方式和新的控制团队。组内成员的信息始终同步，直到任务完成或终止。该方案的自动化程度和智能水平远超当前的控制方式，将是未来发展的一个方向。
在发现并锁定目标后，云端根据各个因素分析并确定此任务的优先级，之后根据优先级、当前目标的实时速度、地图信息、周围一定范围内进行控制的机器人/警察当前状态，确定控制团队，并根据智能算法确定并告知每个成员各自的行进路线，在控制(如包围和逮捕)目标的过程中根据当前全局状态统一协调并实时动态维护控制团队，如有必要则由云端控制加入新的成员或者在满足某些条件时释放当前部分成员，始终保持组内成员的信息同步，直到任务完成或终止，在高效执行任务的前提下又不会浪费多余的控制资源，且如果控制团队全部为机器人或者以机器人为主，则能够降低人员风险。
本方案利用多级分支点逐级判定是否可控制目标，并根据当前的控制状态动态调整进行控制成员的方法，可在保证控制的前提下尽量降低人员投入，一旦高一级分支点被控制则立刻释放低一级分支点的控制，且即使目标突破了控制，云端也可立刻计算出新的控制方式和新的控制团队。组内成员的信息始终同步，直到任务完成或终止。
实施例二
基于同一发明构思，本申请实施例中还提供了一种对目标进行控制的装置，本实施例中控制装置的实施可以参见实施例一中控制方法的实施，重复之处不再赘述。如图3所示，该装置包括：目标获取模块，控制模块及通知模块；
目标获取模块，用于获取待控制目标当前所处位置；
控制模块，用于根据目标当前所处位置确定对所述目标进行控制的成员及各成员应到达位置和时间；所述位置为可对目标进行控制的位置；所述选择的成员部分或全部为机器人。这里的控制可以是封锁、追击、追捕或解救等。
通知模块，用于针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员。
进一步地，所述目标获取模块获取目标当前所处位置包括：获取所述目标在地图上的当前位置，以及对所述目标进行控制的至少一级分支点，所述至少一级分支点为所述成员可对所述目标进行控制的位置；还用于当某级分支点无法进行控制时确定该分支点的下一级分支点，即当某个一级分支点无法进行控制时确定所述一级分支点的二级分支点，当某个二级分支点无法进行控制时确定所述二级分支点的三级分支点。
所述控制模块根据目标当前所处位置确定对目标进行控制的成员及各成员应到达位置具体包括：针对确定出的各一级分支点，判断是否有至少一位成员可在目标以当前最大速度达到该分支点之前到达，即计算成员以其平均速度到达所述分支点的时间是否不超过目标以当前最大速度达到该分支点的时间，是则为所述一级分支点选择成员并确定各成员到达对应一级分支点的时间，该时间应当不晚于目标到达该分支点的时间。
若在一个或多个所述一级分支点没有成员可对目标进行控制，即没有 一位成员可在目标到达前赶到该分支点，所述控制模块进一步查找所述一级分支点的各下一级分支点即二级分支点，判断是否有成员可对各二级分支点进行控制，即针对每个二级分支点，是否有至少一位成员可在目标以当前最大速度到达该二级分支点之前赶到所述二级分支点，若能则选择至少一位成员并确定各成员到达对应二级分支点的时间，该时间应当不晚于目标以当前最大速度到达该分支点的时间；否则对于在目标到达前没有成员可以到达的分支点继续查找下一级的分支点，直到在所述分支点可完成对目标的控制或查找的分支点级别达到阈值。在查找判断某个分支点是否有成员可在所述分支点对目标进行控制时，若该分支点在之前已经被查找判断过，则不再进一步查找判断。
控制模块在为各分支点选择成员时，为不同的分支点选择不同的成员。
最多查找到几级分支点为设定阈值，每个优先级任务的设定可能不同，到达阈值后则控制可能无法满足，回到一级分支点进行判断是否可完成控制，若当前情况无法进行控制，则先采用追击，但计算是实时的，且目标在地图中位置一直在变化，在某一时刻将可能实现对目标的控制，如封锁。
进一步地，所述装置还包括设置模块；
所述设置模块用于为各任务划分优先级；
所述控制模块选择成员时优先选择处于空闲状态的成员；
所述控制模块还用于为某个分支点选择执行控制的成员时，若处于空闲状态的成员中没有一位能在目标赶到该分支点之前赶到该分支点，则从比当前任务优先级低的任务中选择至少一位成员执行对所述分支点的控制；若各低优先级的任务中没有成员可在所述目标以当前最大速度到达所述分支点之前到达则查找所述分支点的下一级分支点。
进一步地，所述设置模块还用于为各任务设置阈值，可以是同一优先级的任务其阈值相同，所述阈值表示执行该控制任务时该任务完成可能性 不能低于该设置阈值。
进一步地，所述控制模块确定成员应到达的位置时，若被选中的成员位于一级分支点与目标之间，如图1所示，假设被选中成员在O1与C3之间，则确认所述成员跟随目标移动或待在原地监视目标，而不用先赶到所述一级分支点；若对第i级分支点进行成员选择时，i≥2，被选中的成员位于第i级分支点与第i﹣1级分支点之间，则确认所述成员优先地往第i﹣1级分支点移动，而不用先到达所述第i级分支点，例如针对二级分支点B2选择成员时，为B2选择的成员位于B2与B3之间，则该成员向B3移动而不用先到达B2。
所述控制模块还用于当从较低优先级的任务中选择成员时，判断若选择的所述成员退出正在执行的任务后，所述较低优先级的任务的完成可能性是否仍不低于其设置阈值，若是则确定所述成员退出正在执行的任务而加入所述当前任务，以及所述成员应赶到的分支点及时间，否则确定所述成员不退出正在执行的较低优先级任务。
进一步地，所述控制模块还用于当选择的成员到达对应分支点时若目标还未到达，确定所述成员向目标位置继续前进，直到与目标会合并完成控制，任务结束，并更新参与控制的成员进入空闲状态或恢复之前的状态。
所述通知模块还用于通知所述成员向目标位置继续前进，直到与目标会合并完成控制，并于任务结束后通知所有执行控制任务的成员进入空闲状态或恢复之前的状态。
所述控制模块还用于在控制过程中若有成员控制了更高一级的分支点，则确定取消对所述分支点分出的低一级的分支点的控制，并释放所述低一级的分支点的成员，更新所述低一级的分支点的成员的状态为空闲状态或恢复其之前状态。
所述通知模块还用于当某个或多个分支点的成员被释放时通知所述成 员进入空闲状态或恢复之前的状态。
实施例三
基于同一发明构思，本申请实施例中还提供了一种对目标进行控制的设备，本实施例中控制设备的实施可以参见实施例一中控制方法的实施，重复之处不再赘述。如图4所示，包括处理器及通信组件；
处理器，用于获取待控制目标当前所处位置；以及用于根据目标当前所处位置确定对所述目标进行控制的成员及各成员应到达位置和时间；所述位置为可对目标进行控制的位置；所述选择的成员部分或全部为机器人。这里的控制可以是封锁或追击。
通信组件，用于针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员。
进一步地，所述处理器获取待控制目标当前所处位置包括：获取所述目标在地图上的当前位置，以及对所述目标进行控制的至少一级分支点，所述至少一级分支点为所述成员可对所述目标进行控制的位置；还用于当某级分支点无法进行控制时确定该分支点的下一级分支点，即当某个一级分支点无法进行控制时确定所述一级分支点的二级分支点，当某个二级分支点无法进行控制时确定所述二级分支点的三级分支点。
所述处理器根据目标当前所处位置确定对目标进行控制的成员及各成员应到达位置具体包括：针对确定出的各一级分支点，判断是否有至少一位成员可在目标以当前最大速度达到该分支点之前到达，即计算成员以其平均速度到达所述分支点的时间是否不超过目标以当前最大速度达到该分支点的时间，是则为所述一级分支点选择成员并确定各成员到达对应一级分支点的时间，该时间应当不晚于目标到达该分支点的时间。
若在一个或多个所述一级分支点没有成员可对目标进行控制，即没有一位成员可在目标到达前赶到该分支点，所述处理器进一步查找所述一级 分支点的各下一级分支点即二级分支点，判断是否有成员可对各二级分支点进行控制，即针对每个二级分支点，是否有至少一位成员可在目标以当前最大速度到达该二级分支点之前赶到所述二级分支点，若能则选择至少一位成员并确定各成员到达对应二级分支点的时间，该时间应当不晚于目标到达该分支点的时间。
在查找判断某个分支点是否有成员可在所述分支点对目标进行控制时，若该分支点在之前已经被查找判断过，则不再进一步查找判断。
处理器在为各分支点选择成员时，为不同的分支点选择不同的成员。
进一步地，所述设备还包括设置组件；
所述设置组件用于为各任务划分优先级；
所述处理器选择成员时优先选择处于空闲状态的成员；
所述处理器还用于为某个分支点选择执行控制的成员时，若处于空闲状态的成员中没有一位能在目标赶到该分支点之前赶到该分支点，则从比当前任务优先级低的任务中选择至少一位成员执行对所述分支点的控制；若各低优先级的任务中没有成员可在所述目标以当前最大速度到达所述分支点之前到达则查找所述分支点的下一级分支点。
进一步地，所述设置组件还用于为各任务设置阈值，可以是同一优先级的任务其阈值相同，所述阈值表示执行该控制任务时该任务完成可能性不能低于该设置阈值。
所述处理器还用于当从较低优先级的任务中选择成员时，判断若选择的所述成员退出正在执行的任务后，所述较低优先级的任务的完成可能性是否仍不低于其设置阈值，若是则确定所述成员退出正在执行的任务而加入所述当前任务，以及所述成员应赶到的分支点及时间，否则确定所述成员不退出正在执行的较低优先级任务。
进一步地，所述处理器确定成员应到达的位置时，若被选中的成员位 于一级分支点与目标之间，如图1所示，假设被选中成员在O1与C3之间，则确认所述成员跟随目标移动或待在原地监视目标，而不用先赶到所述一级分支点；若对第i级分支点进行成员选择时，i≥2，被选中的成员位于第i级分支点与第i﹣1级分支点之间，则确认所述成员优先地往第i﹣1级分支点移动，而不用先到达所述第i级分支点，例如针对二级分支点B2选择成员时，为B2选择的成员位于B2与B3之间，则该成员向B3移动而不用先到达B2。
进一步地，所述处理器还用于当选择的成员到达对应分支点时若目标还未到达，确定并通知所述成员向目标位置继续前进，直到与目标会合并完成控制，任务结束，并更新参与控制的成员进入空闲状态或恢复之前的状态。
所述通信组件还用于通知所述成员向目标位置继续前进，直到与目标会合并完成控制，并于任务结束后通知所有执行控制任务的成员进入空闲状态或恢复之前的状态。
所述处理器还用于在控制过程中若有成员控制了更高一级的分支点，则确定取消对所述分支点分出的低一级的分支点的控制，并释放所述低一级的分支点的成员，更新所述低一级的分支点的成员的状态为空闲状态或恢复其之前状态。
所述通信组件还用于当某个或多个分支点的成员被释放时通知所述成员进入空闲状态或恢复之前的状态。
实施例四
基于同一发明构思，本申请实施例中还提供了一种计算机可读存储介质，所述计算机可读存储介质存储计算机指令，所述计算机指令用于使所述计算机执行前述实施例一方法中的各个步骤。
采用本申请方案，在发现并锁定目标后，通过云端的计算实时调配成员对目标进行控制，如封锁或追击。由于本申请中采用控制的成员部分或全部为机器人，尽可能地降低了由于人工控制造成的局限性。
进一步地，本方案利用多级分支点逐级判定是否可控制目标，并根据当前的控制状态动态调整进行控制成员的方法，可在保证控制的前提下尽量降低人员投入，一旦高一级分支点被控制则立刻释放低一级分支点的控制，且即使目标突破了控制，云端也可立刻计算出新的控制方式和新的控制团队。组内成员的信息始终同步，直到任务完成或终止。
进一步地，云端根据各个因素分析并确定此任务的优先级，之后根据优先级、当前目标的实时速度、地图信息、周围一定范围内执行控制的成员当前状态，如可以是机器人/警察当前状态，确定控制团队，并根据智能算法确定并告知每个成员各自的行进路线，在对目标进行控制(如包围和逮捕)的过程中根据当前全局状态统一协调并实时动态维护控制组，如有必要则由云端控制加入新的成员或者在满足某些条件时释放当前部分成员，始终保持组内成员的信息同步，直到任务完成或终止，在高效执行任务的前提下又不会浪费多余的控制资源，且如果控制团队全部为机器人或者以机器人为主，则能够降低人员风险。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流 程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本申请的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本申请范围的所有变更和修改。

Claims (21)

  1. 一种对目标进行控制的方法，其特征在于，包括如下步骤：
    获取目标当前所处位置；
    根据所述目标当前所处位置确定对所述目标实施控制的成员及各成员应到达位置及时间，针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员；所述位置为可对所述目标进行控制的位置；所述成员部分或全部为机器人。
  2. 如权利要求1所述的方法，其特征在于：
    所述获取目标当前所处位置具体包括，获取所述目标在地图上的当前位置，以及至少一级分支点，所述至少一级分支点为所述成员可对所述目标实施控制的位置；
    针对各一级分支点，判断是否有至少一位成员可在目标以当前最大速度达到所述分支点之前到达，是则为所述一级分支点选择至少一位成员并通知各选择的成员在目标以当前最大速度达到该分支点之前到达所述一级分支点，且为不同的一级分支点选择不同的成员。
  3. 如权利要求2所述的方法，其特征在于，
    若在一个或多个所述一级分支点没有成员可对目标进行控制，即没有成员可在所述目标到达所述分支点之前到达该分支点，则查找所述一级分支点的下一级分支点即二级分支点，并判断各二级分支点是否有成员可在目标以当前最大速度达到该分支点之前到达相应分支点，若能则通知被选择的成员在目标达以当前最大速度到达该分支点之前到达所述分支点，否则对于在目标到达前没有成员可以到达的分支点继续查找下一级的分支点，直到在所述分支点可完成对目标的控制或查找的分支点级别达到阈值，所述为分支点选择成员时为不同的分支点选择不同的成员；
    在对某个分支点进行查找判断时，若所述分支点已经被查找判断过则 不再继续查找判断。
  4. 如权利要求2或3所述的方法，其特征在于，
    对任务进行优先级划分；所述选择成员时优先选择空闲状态的成员，若对于某个分支点，处于空闲状态的成员中没有一位能在目标赶到该分支点之前赶到该分支点，则从比当前优先级低的任务中选择至少一位成员执行对所述分支点的控制；若各低优先级的任务中均没有成员可在所述目标以当前最大速度到达所述分支点之前到达则查找所述分支点的下一级分支点。
  5. 如权利要求4所述的方法，其特征在于，
    为各任务设置阈值，当从较低优先级的任务中选择成员时，若所述成员退出正在执行的所述较低优先级的任务而加入当前任务，所述较低优先级的任务的完成可能性仍不低于其设置阈值则选择所述成员退出正在执行的所述较低优先级任务而加入当前任务，否则所述成员不退出当前正在执行的较低优先级任务。
  6. 如权利要求2或3所述的方法，其特征在于，
    当选择的成员到达对应分支点时若目标还未到达，则通知所述成员向目标位置继续前进，直到与目标会合并完成控制，任务结束，参与控制的成员进入空闲状态或恢复其之前状态。
  7. 如权利要求2或3所述的方法，其特征在于，
    所述控制过程中若有成员控制了更高一级的分支点，则确认取消对所述分支点分出的低一级的分支点的控制，并释放所述低一级的分支点的成员，所述成员变成空闲状态或恢复其之前状态。
  8. 如权利要求2或3所述的方法，其特征在于，
    若被选中的成员位于被派至的一级分支点与目标之间，或是目标位于被选中的成员与被派至的一级分支点之间，则确认并通知所述成员在目标到 达所述一级分支点之前到达该分支点即可，而不用在最短时间内赶到所述一级分支点；
    若对第i级分支点进行成员选择时，被选中的成员位于第i级分支点与第i﹣1级分支点之间，则确认并通知所述成员优先地往第i﹣1级分支点移动，而不用先到达所述第i级分支点；所述i≥2。
  9. 一种对目标进行控制的装置，其特征在于，所述装置包括：目标获取模块，控制模块及通知模块；
    目标获取模块，用于获取目标当前所处位置；
    控制模块，用于根据目标当前所处位置确定对所述目标控制的成员及各成员应到达位置及时间；所述位置为可对目标进行控制的位置；所述选择的成员部分或全部为机器人；
    通知模块，用于针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员。
  10. 如权利要求9所述的装置，其特征在于，
    所述目标获取模块获取目标当前所处位置包括：获取所述目标在地图上的当前位置，以及至少一级分支点，所述至少一级分支点为所述成员可对所述目标进行控制的位置；
    所述控制模块根据目标当前所处位置确定对目标进行控制的成员及各成员应到达位置具体包括：针对确定出的各一级分支点，判断是否有至少一位成员可在目标以当前最大速度达到该分支点之前到达，是则为所述一级分支点选择成员并确定各成员到达对应一级分支点的时间，该时间应当不晚于目标到达该分支点的时间；
    所述控制模块为不同的分支点选择不同的成员。
  11. 如权利要求10所述的装置，其特征在于，
    所述控制模块还用于在一个或多个所述一级分支点没有成员可对目标 进行控制，即没有成员可在所述目标到达所述分支点之前到达所述分支点，进一步查找所述一级分支点的各下一级分支点即二级分支点，判断是否有成员可在各二级分支点对目标进行控制，若能则选择至少一位成员并确定各成员到达对应二级分支点的时间，该时间不晚于目标以当前最大速度到达该分支点的时间；否则对于在目标到达前没有成员可以到达的分支点继续查找下一级的分支点，直到在所述分支点可完成对目标的控制或查找的分支点级别达到阈值；
    所述控制模块在对某个分支点进行查找判断时，若该分支点已经被查找判断过则不再继续查找判断；
    所述控制模块为不同的分支点选择不同的成员。
  12. 如权利要求10或11所述的装置，其特征在于，
    所述装置还包括设置模块，用于为各任务划分优先级；
    所述控制模块选择成员时优先选择处于空闲状态的成员；
    所述控制模块还用于为某个分支点选择执行控制的成员时，若处于空闲状态的成员中没有一位能在目标赶到该分支点之前赶到所述分支点，则从比当前任务优先级低的任务中选择至少一位成员执行对所述分支点的控制；若各低优先级的任务中没有成员可在所述目标以当前最大速度到达所述分支点之前到达则查找所述分支点的下一级分支点。
  13. 如权利要求12所述的装置，其特征在于，
    所述设置模块还用于为各任务设置阈值；
    所述控制模块还用于当从较低优先级的任务中选择成员时，判断若选择的所述成员退出正在执行的任务后，所述较低优先级的任务的完成可能性是否仍不低于其设置阈值，若是则确定所述成员退出正在执行的任务而加入所述当前任务，以及所述成员应赶到的分支点及时间，否则确定所述成员不退出正在执行的较低优先级任务。
  14. 如权利要求10或11所述的装置，其特征在于，
    所述控制模块还用于当选择的成员到达对应分支点时若目标还未到达，确定所述成员向目标位置继续前进，直到与目标会合并完成控制，任务结束，并更新参与控制的成员进入空闲状态；
    所述通知模块还用于通知所述成员向目标位置继续前进，直到与目标会合并完成控制，并于任务结束后通知所有执行控制任务的成员进入空闲状态或恢复之前的状态。
  15. 如权利要求10或11所述的装置，其特征在于，
    所述控制模块还用于在控制过程中若有成员控制了更高一级的分支点，则确定取消对所述分支点分出的低一级的分支点的控制，并释放所述低一级的分支点的成员，更新所述低一级的分支点的成员的状态为空闲状态或恢复其之前状态；
    所述通知模块还用于当某个或多个分支点的成员被释放时通知所述成员进入空闲状态或恢复之前的状态。
  16. 一种对目标进行控制的设备，其特征在于，所述设备包括：包括处理器及通信组件；
    所述处理器，用于获取目标当前所处位置；以及用于根据目标当前所处位置确定对所述目标进行控制的成员及各成员应到达位置及时间；所述位置为可对目标进行控制的位置；所述选择的成员部分或全部为机器人；
    所述通信组件，用于针对每个被选择的成员，将该成员应到达的指定位置和时间通知至所述成员。
  17. 如权利要求16所述的设备，其特征在于，
    所述处理器获取目标当前所处位置包括：获取所述目标在地图上的当前位置，以及至少一级分支点，所述至少一级分支点为所述成员可对所述目标进行控制的位置；
    所述处理器根据目标当前所处位置确定对所述目标进行的控制成员及各成员应到达位置具体包括：针对确定出的各一级分支点，判断是否有至少一位成员可在目标以当前最大速度达到该分支点之前到达，是则为所述一级分支点选择至少一位成员并确定各成员到达对应一级分支点的时间，该时间应当不晚于目标到达该分支点的时间；
    所述处理器为不同的分支点选择不同的成员。
  18. 如权利要求17所述的设备，其特征在于，
    若在一个或多个所述一级分支点没有成员可对目标进行控制，即没有成员可在所述目标到达所述分支点之前到达所述分支点，所述处理器进一步查找所述一级分支点的各下一级分支点即二级分支点，判断是否有成员可在各二级分支点对目标进行控制，即针对每个二级分支点，是否有至少一位成员可在目标以当前最大速度到达该二级分支点之前赶到所述二级分支点，若能则选择至少一位成员并确定各成员到达对应二级分支点的时间，该时间应当不晚于目标到达该分支点的时间；否则对于在目标到达前没有成员可以到达的分支点继续查找下一级的分支点，直到在所述分支点可完成对目标的控制或查找的分支点级别达到阈值；
    所述处理器在对某个分支点进行查找判断时，若该分支点已经被查找判断过则不再继续查找判断；
    所述处理器为不同的分支点选择不同的成员。
  19. 如权利要求17或18所述的设备，其特征在于，
    所述设备还包括设置组件；
    所述设置组件用于为各任务划分优先级；
    所述处理器选择成员时优先选择处于空闲状态的成员；
    所述处理器还用于为某个分支点选择执行控制的成员时，若处于空闲状态的成员中没有一位能在目标赶到该分支点之前赶到该分支点，则从比当 前任务优先级低的任务中选择至少一位成员执行对所述分支点的控制；若各低优先级的任务中没有成员可在所述目标以当前最大速度到达所述分支点之前到达则查找所述分支点的下一级分支点。
  20. 如权利要求19所述的设备，其特征在于，
    所述设置组件还用于为各任务设置阈值；
    所述处理器还用于当从较低优先级的任务中选择成员时，判断若选择的所述成员退出正在执行的任务后，所述较低优先级的任务的完成可能性是否仍不低于其设置阈值，若是则确定所述成员退出正在执行的任务而加入所述当前任务，以及所述成员应赶到的分支点及时间，否则确定所述成员不退出正在执行的较低优先级任务。
  21. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储计算机指令，所述计算机指令用于使所述计算机执行所述权利要求1至8中任一项的各个步骤。
PCT/CN2016/110567 2016-12-17 2016-12-17 一种对目标进行控制的方法、控制装置及控制设备 WO2018107505A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/CN2016/110567 WO2018107505A1 (zh) 2016-12-17 2016-12-17 一种对目标进行控制的方法、控制装置及控制设备
CN201680002692.0A CN106716282B (zh) 2016-12-17 2016-12-17 一种对目标进行控制的方法、控制装置及控制设备
US16/428,996 US20190302779A1 (en) 2016-12-17 2019-06-01 Target control method, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/110567 WO2018107505A1 (zh) 2016-12-17 2016-12-17 一种对目标进行控制的方法、控制装置及控制设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/428,996 Continuation US20190302779A1 (en) 2016-12-17 2019-06-01 Target control method, device and system

Publications (1)

Publication Number Publication Date
WO2018107505A1 true WO2018107505A1 (zh) 2018-06-21

Family

ID=58906772

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/110567 WO2018107505A1 (zh) 2016-12-17 2016-12-17 一种对目标进行控制的方法、控制装置及控制设备

Country Status (3)

Country Link
US (1) US20190302779A1 (zh)
CN (1) CN106716282B (zh)
WO (1) WO2018107505A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220006978A1 (en) * 2020-07-01 2022-01-06 Toyota Jidosha Kabushiki Kaisha Information processing apparatus, information processing method, and moving object

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108009012B (zh) * 2017-12-14 2021-12-14 中南大学 一种基于任务模型的多智能体动态任务分配方法
CN108268038B (zh) * 2018-01-19 2021-04-20 广东美的智能机器人有限公司 多移动机器人的调度方法及系统
CN111083444B (zh) * 2019-12-26 2021-10-15 浙江大华技术股份有限公司 一种抓拍方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008097152A (ja) * 2006-10-06 2008-04-24 Nagoya Institute Of Technology 位置制御装置、位置制御方法及び位置制御プログラム
US20090012667A1 (en) * 2007-07-04 2009-01-08 Kosei Matsumoto Mobile device, moving system, moving method, and moving program
CN104834309A (zh) * 2015-04-10 2015-08-12 浙江工业大学 基于目标跟踪控制策略的单移动机器人最优巡回控制方法
CN105182973A (zh) * 2015-09-08 2015-12-23 郑州大学 多机器人追捕者围捕单移动目标的自适应围捕装置与方法

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1418026A1 (en) * 1995-09-11 2004-05-12 Kabushiki Kaisha Yaskawa Denki Control apparatus for robot
JP4298155B2 (ja) * 2000-11-17 2009-07-15 本田技研工業株式会社 距離測定装置、及び距離測定方法
EP1486300B1 (en) * 2002-03-15 2011-08-17 Sony Corporation Robot behavior control system, behavior control method, and robot device
JP2009288930A (ja) * 2008-05-28 2009-12-10 Murata Mach Ltd 自律移動体及びその移動制御方法
JP5126272B2 (ja) * 2010-03-31 2013-01-23 株式会社デンソー ナビゲーションシステム
CN104914865B (zh) * 2015-05-29 2017-10-24 国网山东省电力公司电力科学研究院 变电站巡检机器人定位导航系统及方法
CN105005305B (zh) * 2015-07-22 2018-07-31 上海思依暄机器人科技股份有限公司 受控机器人、遥控设备、机器人系统及所适用的方法
CN105578058A (zh) * 2016-02-03 2016-05-11 北京光年无限科技有限公司 一种面向智能机器人的拍摄控制方法、装置及机器人

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008097152A (ja) * 2006-10-06 2008-04-24 Nagoya Institute Of Technology 位置制御装置、位置制御方法及び位置制御プログラム
US20090012667A1 (en) * 2007-07-04 2009-01-08 Kosei Matsumoto Mobile device, moving system, moving method, and moving program
CN104834309A (zh) * 2015-04-10 2015-08-12 浙江工业大学 基于目标跟踪控制策略的单移动机器人最优巡回控制方法
CN105182973A (zh) * 2015-09-08 2015-12-23 郑州大学 多机器人追捕者围捕单移动目标的自适应围捕装置与方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220006978A1 (en) * 2020-07-01 2022-01-06 Toyota Jidosha Kabushiki Kaisha Information processing apparatus, information processing method, and moving object

Also Published As

Publication number Publication date
US20190302779A1 (en) 2019-10-03
CN106716282A (zh) 2017-05-24
CN106716282B (zh) 2019-06-11

Similar Documents

Publication Publication Date Title
WO2018107505A1 (zh) 一种对目标进行控制的方法、控制装置及控制设备
Zorbas et al. Energy efficient mobile target tracking using flying drones
Ouallane et al. Overview of road traffic management solutions based on IoT and AI
US7463948B2 (en) Robot control apparatus
CN109808709A (zh) 车辆行驶保障方法、装置、设备及可读存储介质
US20160117936A1 (en) Autonomous vehicle and method for coordinating the paths of multiple autonomous vehicles
US20060095160A1 (en) Robot controller
CN110737212B (zh) 无人机控制系统和方法
Kashino et al. Aerial wilderness search and rescue with ground support
US20180341814A1 (en) Multiple robots assisted surveillance system
Tang et al. A joint global and local path planning optimization for UAV task scheduling towards crowd air monitoring
Lauri et al. Multi-robot active information gathering with periodic communication
JP2020126634A (ja) 緊急車両をリアルタイムで検出し、緊急車両によって発生すると予想される状況に対処するための走行経路を計画する方法及び装置
WO2021082709A1 (zh) 水下清淤机器人路径规划方法、装置、机器人和存储介质
CN112947594B (zh) 一种面向无人机的航迹规划方法
KR20200033477A (ko) 순찰용 드론 관제 시스템, 방법, 및 상기 방법을 실행시키기 위한 컴퓨터 판독 가능한 프로그램을 기록한 기록 매체
Albert et al. Combined optimal control and combinatorial optimization for searching and tracking using an unmanned aerial vehicle
US11209796B2 (en) Surveillance system with intelligent robotic surveillance device
Singh et al. Fog-Centric Intelligent Surveillance System: A Novel Approach for Effective and Efficient Surveillance
Picard Trajectory coordination based on distributed constraint optimization techniques in unmanned air traffic management
Antoine et al. Real-time traffic flow-based traffic signal scheduling: A queuing theory approach
Kashino et al. An adaptive static-sensor network deployment strategy for detecting mobile targets
US10873471B1 (en) Measuring an area of interest based on a sensor task
WO2019183959A1 (zh) 航点的更新方法及可移动平台
Casbeer et al. Estimating the state of an intruder with a UAV and unattended ground sensors

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16923953

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 15/11/2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16923953

Country of ref document: EP

Kind code of ref document: A1