WO2022166397A1 - 目标对象的躲避方法及装置、存储介质、电子装置 - Google Patents

目标对象的躲避方法及装置、存储介质、电子装置 Download PDF

Info

Publication number
WO2022166397A1
WO2022166397A1 PCT/CN2021/137063 CN2021137063W WO2022166397A1 WO 2022166397 A1 WO2022166397 A1 WO 2022166397A1 CN 2021137063 W CN2021137063 W CN 2021137063W WO 2022166397 A1 WO2022166397 A1 WO 2022166397A1
Authority
WO
WIPO (PCT)
Prior art keywords
dimensional point
robot
surface model
moving part
target object
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2021/137063
Other languages
English (en)
French (fr)
Inventor
霍江浩
常新伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dreame Innovation Technology Suzhou Co Ltd
Original Assignee
Dreame Innovation Technology Suzhou Co Ltd
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 Dreame Innovation Technology Suzhou Co Ltd filed Critical Dreame Innovation Technology Suzhou Co Ltd
Publication of WO2022166397A1 publication Critical patent/WO2022166397A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three-dimensional [3D] modelling for computer graphics
    • G06T17/05—Geographic models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1656—Program controls characterised by programming, planning systems for manipulators
    • B25J9/1664—Program controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
    • B25J9/1666—Avoiding collision or forbidden zones
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1674—Program controls characterised by safety, monitoring, diagnostic
    • B25J9/1676—Avoiding collision or forbidden zones
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras

Definitions

  • the present invention relates to the field of communications, and in particular, to a method and device for avoiding a target object, a storage medium, and an electronic device.
  • robots have now been applied to various fields of use in all walks of life.
  • avoiding obstacles is a very important technology in robotics, and it is very important for the application of robots in various environments.
  • the robot is regarded as a large block, so that the block does not touch obstacles, so that the robot can pass safely and complete the work of the robot.
  • the terrain is complex, there are many obstacles, and the passages for robots to pass are narrow.
  • the robot can no longer be regarded as a big block.
  • the robot needs to flexibly adjust its own parts so that the robot can safely pass through the complex and narrow passages. If the robot is also understood as a whole block, it is difficult for the robot to pass through areas with complex terrain, and related technologies cannot adjust the parts of the robot so that the robot can successfully avoid obstacles.
  • the purpose of the present invention is to provide a method and device for avoiding a target object, a storage medium, and an electronic device, so as to at least solve the problem in the related art that the components of the robot cannot be adjusted so that the robot can successfully avoid obstacles.
  • a method for avoiding a target object includes: determining a target object that a robot needs to avoid in a traveling area; acquiring a first three-dimensional point-surface model of the target object, and acquiring a second three-dimensional point-surface model corresponding to each moving part of the robot, wherein the robot is provided with a plurality of moving parts; respectively determining the first three-dimensional point-surface model and a plurality of the second three-dimensional points Whether any second 3D point-surface model in the surface model intersects; if there is an intersection, adjust the target moving part corresponding to the second 3D point-surface model that intersects with the first 3D point-surface model to Make the robot successfully avoid the target object.
  • acquiring the second three-dimensional point-surface model corresponding to each moving part of the robot includes: determining the position information of each moving part, the part structure of each moving part, and determining the position information of each moving part after the current moment.
  • the control instruction sequence of the robot within the preset time period, the control instruction sequence of the robot, wherein the control instruction sequence is used to indicate the operations to be performed by the robot at different times within the preset time period;
  • the component structure and the control instruction sequence determine a second three-dimensional point-surface model corresponding to each moving component, so as to obtain a plurality of second three-dimensional point-surface models corresponding to the plurality of moving components.
  • determining the position information of each moving part includes: acquiring the positioning and map construction information detected by the perception intelligence algorithm of the robot; The obtained rotation angle of each moving part, and the data detected by the inertial measurement unit of the robot is obtained; according to the positioning and map construction information, the rotation angle and the data determine the each movement The location information of the part.
  • determining the position information of each moving part according to the positioning and map construction information, the rotation angle and the data includes: performing a Kalman filter on the positioning and map construction information, the The rotation angle and the data are operated to obtain an operation result; the position information of each moving part is determined according to the operation result.
  • determining, respectively, whether the first three-dimensional point-surface model and any second three-dimensional point-surface model in the plurality of second three-dimensional point-surface models intersect including: for any second three-dimensional point and surface model; A surface model, according to a convex hull intersection algorithm to determine whether the first three-dimensional point-surface model and the any second three-dimensional point-surface model intersect at the different times.
  • adjusting the target moving part corresponding to the second three-dimensional point-surface model that intersects with the first three-dimensional point-surface model, so that the robot successfully avoids the target object includes: adjusting in one of the following ways: The target moving part, so that the robot successfully avoids the target object: raising the target moving part to the target position, prohibiting the moving of the target moving part, and adjusting the moving direction of the target moving part.
  • the method further includes: when there is no intersection.
  • the robot is instructed to sequentially execute the control instruction sequence within the preset time period.
  • a device for avoiding a target object includes: a first determining module, configured to determine a target object that the robot needs to avoid in a travel area; an acquisition module, configured to Acquiring a first three-dimensional point-surface model of the target object, and acquiring a second three-dimensional point-surface model corresponding to each moving part of the robot, wherein the robot is provided with a plurality of moving parts; the second determining module, using respectively determine whether the first three-dimensional point-surface model and any second three-dimensional point-surface model in the plurality of second three-dimensional point-surface models intersect; the adjustment module is used for adjusting and The first three-dimensional point-surface model has a target moving part corresponding to the intersecting second three-dimensional point-surface model, so that the robot can successfully avoid the target object.
  • a computer-readable storage medium is provided, and a computer program is stored in the storage medium, wherein the computer program is configured to execute any of the above when running.
  • an electronic device comprising a memory and a processor, the memory having a computer program stored therein, the processor being configured to run the computer program to execute any of the above The evasion method of the target object described in item.
  • the present invention has the following beneficial effects: when the target object that the robot needs to avoid in the travel area is determined, the first three-dimensional point-surface model of the target object can be obtained, and the robot's first three-dimensional point-surface model can be obtained. the second three-dimensional point-surface model corresponding to each moving part, and then determine whether the first three-dimensional point-surface model intersects with any second three-dimensional point-surface model among the plurality of second three-dimensional point-surface models, if If there is an intersection, then adjust the target moving part corresponding to the second three-dimensional point-and-surface model that intersects with the first three-dimensional point-and-surface model, so that the robot successfully avoids the target object. Therefore, the problem in the related art that the parts of the robot cannot be adjusted so that the robot can successfully avoid obstacles is solved, the robot can be flexibly controlled to avoid obstacles, and the robot can be applied in some scenes with complex terrain and many obstacles.
  • Fig. 1 is a hardware structure block diagram of a robot of a method for avoiding a target object according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a method for avoiding a target object according to an embodiment of the present invention
  • FIG. 3 is a schematic flowchart of a method for avoiding a target object according to an embodiment of the present invention
  • FIG. 4 is a structural block diagram of a device for avoiding a target object according to an embodiment of the present invention.
  • FIG. 1 is a hardware structural block diagram of a robot of a method for avoiding a target object according to an embodiment of the present invention.
  • the robot may include one or more (only one is shown in FIG. 1 ) processors 102 (the processors 102 may include, but are not limited to, a Microprocessor Unit (MPU) or a programmable logic device for short) (Programmable logic device, abbreviated as PLD) etc.
  • MPU Microprocessor Unit
  • PLD programmable logic device
  • the above-mentioned robot may also include a transmission device 106 and an input and output device 108 for communication functions.
  • a transmission device 106 and an input and output device 108 for communication functions.
  • the structure shown in Fig. 1 is only for illustration, and it does not limit the structure of the above-mentioned robot.
  • the robot may also include more or less components than those shown in Fig. 1, or have different components than those shown in Fig. 1 Equivalent function or a different configuration with more functions than shown in Figure 1.
  • the memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer programs corresponding to the method for avoiding the target object in the embodiment of the present invention. Executing various functional applications and data processing implements the above-mentioned methods.
  • Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.
  • memory 104 may further include memory located remotely from processor 102, which may be connected to the robot through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the transmission device 106 is used to receive or transmit data via the network.
  • the specific example of the above-mentioned network may include the wireless network provided by the communication provider of the robot.
  • the transmission device 106 includes a network adapter (Network Interface Controller, NIC for short), which can be connected to other network devices through a base station so as to communicate with the Internet.
  • the transmission device 106 may be a radio frequency (Radio Frequency, RF for short) module, which is used to communicate with the Internet in a wireless manner.
  • RF Radio Frequency
  • FIG. 2 is a flowchart of the method for avoiding the target object according to an embodiment of the present invention. As shown in FIG. 2 , the flow includes the following steps:
  • Step S202 determining the target object that the robot needs to avoid in the travel area
  • Step S204 acquiring a first three-dimensional point-surface model of the target object, and acquiring a second three-dimensional point-surface model corresponding to each moving part of the robot, wherein the robot is provided with a plurality of moving parts;
  • Step S206 respectively determining whether the first three-dimensional point-surface model intersects with any second three-dimensional point-surface model in the plurality of second three-dimensional point-surface models;
  • Step S208 if there is an intersection, adjust the target moving part corresponding to the second three-dimensional point-surface model intersecting with the first three-dimensional point-surface model, so that the robot successfully avoids the target object.
  • the first three-dimensional point-surface model of the target object can be obtained, and the second three-dimensional point-surface model, and then determine whether the first three-dimensional point-surface model and any second three-dimensional point-surface model in the plurality of second three-dimensional point-surface models intersect, and if there is an intersection, adjust the The first three-dimensional point-surface model has a target moving part corresponding to the intersecting second three-dimensional point-surface model, so that the robot can successfully avoid the target object. Therefore, the technical solutions of the embodiments of the present invention can adjust the components of the robot, so that the robot can successfully avoid obstacles, and then the robot can be applied in some scenes with complex terrain and many obstacles.
  • the robot in the embodiment of the present invention may be a biped robot, a three-legged robot, or a quadruped robot, which is not limited in the embodiment of the present invention.
  • step S204 acquiring the second three-dimensional point-surface model corresponding to each moving part of the robot can be realized by the following scheme: determining the position of each moving part information, the component structure of each moving part, and the control instruction sequence of the robot within a preset time period after the current moment, wherein the control instruction sequence is used to instruct the robot to operate at the preset time operations to be performed at different moments in a time period; according to the position information, the component structure and the control instruction sequence, determine the second three-dimensional point-surface model corresponding to each moving component, so as to obtain the multiple movements A plurality of second three-dimensional point-surface models corresponding to the component.
  • each moving part in the quadruped robot needs to determine the second three-dimensional point-surface model, and the process of determining the three-dimensional point-surface models of the four moving parts can be performed synchronously or It is carried out in sequence, and the moving parts can be understood as the structural parts of the legs and feet of the robot.
  • the technical solution of the embodiment of the present invention is: for a robot with environment perception capability, collision detection is performed on areas or obstacles that cannot be touched by various parts during the robot's traveling process, and the moving parts of the robot are detected according to the detection results. Make timely adjustments to ensure the safety of quadruped robots walking in complex ground environments.
  • the embodiment of the present invention realizes the precise obstacle avoidance of the robot through the first three-dimensional point-surface model of the target object (obstacle or the area that the robot cannot touch) and the second three-dimensional point-surface model corresponding to each moving part of the robot.
  • the embodiment of the present invention needs to acquire the first three-dimensional point-surface model of the target object and the second three-dimensional point-surface model corresponding to each moving part of the robot, wherein each moving part of the robot corresponds to a first three-dimensional point-surface model.
  • a plurality of second three-dimensional point-surface models are acquired.
  • control instruction sequence is used to instruct the robot to perform operations at different times within a preset time period, and a series of sequences within a preset time period after the current moment can be obtained from the robot control algorithm.
  • the control instruction sequence, the above-mentioned control instruction sequence is usually 5 to 1000 sequences.
  • the second three-dimensional point and surface model corresponding to each moving part can be determined, and then a plurality of second three-dimensional point surfaces corresponding to multiple moving parts can be obtained.
  • Model It should be noted that, the above-mentioned method for obtaining the second three-dimensional point-surface model is to inversely calculate the second three-dimensional point-surface model corresponding to the above-mentioned moving component at each moment in the control command sequence through the position information and component structure of the moving component.
  • determining the position information of each moving part includes: acquiring the positioning and map construction information detected by the perception intelligence algorithm of the robot; The rotation angle of each moving part detected by the encoder, and the data detected by the inertial measurement unit of the robot; according to the positioning and map construction information, the rotation angle and the data determine the rotation angle.
  • the position information of each moving part is described.
  • the position information of each moving part needs to be acquired.
  • the positioning and map construction information detected by the robot, the rotation angle of each moving part of the robot and the inertial data of the robot (equivalent to that detected by the inertial measurement unit of the above embodiment).
  • the data can be detected and acquired by the robot's perception intelligence algorithm, the rotation angle of each moving part of the robot can be detected and acquired by the encoder set on each moving part, and the inertial data of the robot can be detected. It can be detected by the inertial measurement unit of the robot.
  • the robot inertial data is the data about the current moment action or action of the robot. According to the positioning and map construction information, the rotation angle of each moving part of the robot and the inertial data of the robot can determine the position information of each moving part of the robot.
  • determining the position information of each moving part according to the positioning and map construction information, the rotation angle and the data may be implemented by the following scheme: The positioning and map construction information, the rotation angle and the data are calculated to obtain the calculation result; the position information of each moving part is determined according to the calculation result.
  • the positioning and map construction information, the rotation angle of each moving part of the robot and the inertial data of the robot can be calculated by Kalman filter to obtain the position information of each moving part of the robot.
  • the Kalman filter is used to filter the above-mentioned positioning and map construction information, the rotation angle of each moving part of the robot, and the inertial data of the robot, to filter out the above-mentioned positioning and map construction information, and the rotation of each moving part of the robot. Angles and disturbances in the robot inertial data.
  • the above-mentioned positioning and map construction information, the rotation angle of each moving part of the robot and the inertial data of the robot are optimally estimated through the linear system state equation in the Kalman filter, and then the position information of each moving part of the robot is obtained.
  • step S206 respectively determining whether the first three-dimensional point-surface model and any second three-dimensional point-surface model of the plurality of second three-dimensional point-surface models intersect, can be achieved by the following scheme: for any second three-dimensional point-surface model, according to a convex hull intersection algorithm, determine whether the first three-dimensional point-surface model and the any second three-dimensional point-surface model intersect at the different times.
  • the embodiment of the present invention determines the first three-dimensional point-surface model at the different times by using a convex hull intersection algorithm Whether the model and any of the second three-dimensional point-surface models intersect, and then determine whether there is an obstacle and whether the robot can pass.
  • the first three-dimensional point-surface model and the plurality of second three-dimensional point-surface models are actually sets of spatial coordinates of points. Each model corresponds to a set of spatial coordinates of points, wherein the above-mentioned points refer to points on a part of the target object or each moving part of the robot.
  • the convex hull intersection algorithm is used to calculate the set of spatial coordinates of points on the target object corresponding to the first three-dimensional point-surface model and the set of spatial coordinates of each moving part of the robot corresponding to any second three-dimensional point-surface model. , it can be determined whether the first three-dimensional point-surface model and any of the second three-dimensional point-surface models intersect.
  • determining whether the first three-dimensional point-surface model and any of the second three-dimensional point-surface models intersect is actually a kind of prediction for whether the robot collides with the obstacles at the target position after the robot is about to reach the target position. sentence.
  • the above-mentioned method for obtaining the second three-dimensional point-surface model is to inversely calculate the second three-dimensional point-and-surface model corresponding to the above-mentioned moving part at each moment in the control command sequence by using the position information of the moving part and the structure of the part.
  • adjusting the target moving part corresponding to the second three-dimensional point-surface model that intersects with the first three-dimensional point-surface model, so that the robot successfully avoids the target object includes: adjusting in one of the following ways: The target moving part, so that the robot successfully avoids the target object: raising the target moving part to the target position, prohibiting the moving of the target moving part, and adjusting the moving direction of the target moving part.
  • the adjustment methods for adjusting the multiple moving parts of the robot may include but are not limited to the following: (1) Height adjustment, the specific implementation method is that the target moving part can be adjusted to the target position (the obstacle At the lower position, the target moving part and the obstacle are staggered up and down); (2) Prohibition of movement, the specific implementation method is to prohibit the movement of the target moving part (the passage is narrow, if the target moving part moves, it will collide with the obstacle) (3) Adjustment of the moving direction, the specific implementation is to adjust the moving direction of the target moving part (the robot chooses another channel to pass through); (4) The foothold adjustment, the specific implementation is to adjust the foothold of the mobile part of the robot Adjust forward left or right to avoid obstacles.
  • height adjustment may be performed first, and if obstacles still cannot be avoided, you may try to settle on the ground Adjust, if you still can't avoid obstacles, you can try to prohibit movement.
  • step S206 After step S206 is performed, that is, after determining whether the first 3D point-surface model and any second 3D point-surface model of the plurality of second 3D point-surface models intersect, respectively, the method further includes: In the case that there is no intersection, the robot is instructed to sequentially execute the control instruction sequence within the preset time period.
  • the robot may execute the sequence of control instructions in the preset time period in sequence.
  • the present invention also provides an optional embodiment for explaining the above technical solution.
  • FIG. 3 is a schematic flowchart of a method for avoiding a target object according to an embodiment of the present invention, as shown in FIG. 3 :
  • S302 Receive the environmental information sent by the upper-layer perception algorithm, the above-mentioned environmental information includes 2D map and three-dimensional environmental information, as well as the position information of the robot, and the item information (equivalent to the target object of the above-mentioned embodiment) that requires the robot to accurately avoid obstacles;
  • S308 establish a second three-dimensional point-surface model corresponding to each moving part of the robot, and obtain a plurality of the second three-dimensional point-surface models;
  • S310 Determine whether there is an intersection between the first three-dimensional point-and-surface model and any second three-dimensional point-and-surface model in the plurality of second three-dimensional point-and-surface models;
  • the first three-dimensional point-surface model of the target object can be obtained, and the second three-dimensional point-surface model, and then determine whether the first three-dimensional point-surface model and any second three-dimensional point-surface model in the plurality of second three-dimensional point-surface models intersect, and if there is an intersection, adjust the The first three-dimensional point-surface model has a target moving part corresponding to the intersecting second three-dimensional point-surface model, so that the robot can successfully avoid the target object. Therefore, the technical solutions of the embodiments of the present invention can adjust the components of the robot, so that the robot can successfully avoid obstacles, and then the robot can be applied in some scenes with complex terrain and many obstacles.
  • a device for avoiding a target object is also provided, and the device for avoiding a target object is used to implement the above embodiments and preferred implementations, and what has been described will not be repeated.
  • the term "module” may be a combination of software and/or hardware that implements a predetermined function.
  • the apparatus described in the following embodiments is preferably implemented in software, implementations in hardware, or a combination of software and hardware, are also possible and contemplated.
  • FIG. 4 is a structural block diagram of a device for avoiding a target object according to an optional embodiment of the present invention, as shown in FIG. 4 :
  • the first determination module 40 is used to determine the target object that the robot needs to avoid in the travel area
  • an acquisition module 42 configured to acquire a first three-dimensional point-surface model of the target object, and acquire a second three-dimensional point-surface model corresponding to each moving part of the robot, wherein the robot is provided with a plurality of moving parts;
  • the second determination module 44 is configured to respectively determine whether the first three-dimensional point-surface model intersects with any second three-dimensional point-and-surface model in the plurality of second three-dimensional point-and-surface models;
  • the adjustment module 46 is configured to adjust the target moving part corresponding to the second three-dimensional point-surface model intersecting with the first three-dimensional point-surface model in the case of intersection, so that the robot can successfully avoid the target object .
  • the first three-dimensional point-surface model of the target object can be obtained, and the second three-dimensional point-surface model, and then determine whether the first three-dimensional point-surface model and any second three-dimensional point-surface model in the plurality of second three-dimensional point-surface models intersect, and if there is an intersection, adjust the The first three-dimensional point-surface model has a target moving part corresponding to the intersecting second three-dimensional point-surface model, so that the robot can successfully avoid the target object. Therefore, the technical solutions of the embodiments of the present invention can adjust the components of the robot, so that the robot can successfully avoid obstacles, and then the robot can be applied in some scenes with complex terrain and many obstacles.
  • the acquisition module 42 is also used to determine the position information of each moving part, the part structure of each moving part, and the control instruction sequence of the robot within a preset time period after the current moment. , wherein the control instruction sequence is used to instruct the robot to perform operations at different times within the preset time period; according to the position information, the component structure and the control instruction sequence determine the A second three-dimensional point-surface model corresponding to one moving part is used to obtain a plurality of second three-dimensional point-surface models corresponding to the plurality of moving parts.
  • each moving part in the quadruped robot needs to determine the second three-dimensional point-surface model, and the process of determining the three-dimensional point-surface models of the four moving parts can be performed synchronously or It is carried out in sequence, and the moving parts can be understood as the structural parts of the legs and feet of the robot.
  • the technical solution of the embodiment of the present invention is: for a robot with environment perception capability, collision detection is performed on areas or obstacles that cannot be touched by various parts during the robot's traveling process, and the moving parts of the robot are detected according to the detection results. Make timely adjustments to ensure the safety of quadruped robots walking in complex ground environments.
  • the embodiment of the present invention realizes the precise obstacle avoidance of the robot through the first three-dimensional point-surface model of the target object (obstacle or the area that the robot cannot touch) and the second three-dimensional point-surface model corresponding to each moving part of the robot.
  • the embodiment of the present invention needs to acquire the first three-dimensional point-surface model of the target object and the second three-dimensional point-surface model corresponding to each moving part of the robot, wherein each moving part of the robot corresponds to a first three-dimensional point-surface model.
  • a plurality of second three-dimensional point-surface models are acquired.
  • control instruction sequence is used to instruct the robot to perform operations at different times within a preset time period, and a series of sequences within a preset time period after the current moment can be obtained from the robot control algorithm.
  • the control instruction sequence, the above-mentioned control instruction sequence is usually 5 to 1000 sequences.
  • the second three-dimensional point and surface model corresponding to each moving part can be determined, and then a plurality of second three-dimensional point surfaces corresponding to multiple moving parts can be obtained.
  • Model the above-mentioned method for obtaining the second three-dimensional point-surface model is to inversely calculate the second three-dimensional point-surface model corresponding to the above-mentioned moving component at each moment in the control command sequence through the position information and component structure of the moving component. That is to say, the control command sequence of the robot is a plurality of commands for controlling the robot based on the second three-dimensional point-surface model within the preset time period after the current moment. Set the second three-dimensional point-surface model in the time period.
  • the acquisition module 42 is also used to acquire the positioning and map construction information detected by the perception intelligence algorithm of the robot, and to acquire the each movement detected by the encoder provided on each of the moving parts.
  • the rotation angle of the component is obtained, and the data detected by the inertial measurement unit of the robot is obtained; the position information of each moving component is determined according to the positioning and map construction information, the rotation angle and the data.
  • the position information of each moving part needs to be acquired.
  • the positioning and map construction information can be detected and acquired by the robot's perception intelligence algorithm, the rotation angle of each moving part of the robot can be detected and acquired by the encoder set on each moving part, and the inertial data of the robot can be detected. It can be detected by the inertial measurement unit of the robot.
  • the robot inertial data is the data about the current moment action or action of the robot.
  • the position information of each moving part of the robot is determined according to the positioning and map construction information, the rotation angle of each moving part of the robot and the inertial data of the robot.
  • the acquisition module 42 is further configured to perform operations on the positioning and map construction information, the rotation angle and the data through the Kalman filter to obtain an operation result; determine the each movement according to the operation result.
  • the location information of the part is further configured to perform operations on the positioning and map construction information, the rotation angle and the data through the Kalman filter to obtain an operation result; determine the each movement according to the operation result.
  • the location information of the part is further configured to perform operations on the positioning and map construction information, the rotation angle and the data through the Kalman filter to obtain an operation result; determine the each movement according to the operation result.
  • the location information of the part is further configured to perform operations on the positioning and map construction information, the rotation angle and the data through the Kalman filter to obtain an operation result; determine the each movement according to the operation result. The location information of the part.
  • the positioning and map construction information, the rotation angle of each moving part of the robot and the inertial data of the robot can be calculated by Kalman filter to obtain the position information of each moving part of the robot.
  • the Kalman filter is used to filter the above-mentioned positioning and map construction information, the rotation angle of each moving part of the robot, and the inertial data of the robot, to filter out the above-mentioned positioning and map construction information, and the rotation of each moving part of the robot. Angles and disturbances in the robot inertial data.
  • the above-mentioned positioning and map construction information, the rotation angle of each moving part of the robot and the inertial data of the robot are optimally estimated through the linear system state equation in the Kalman filter, and then the position information of each moving part of the robot is obtained.
  • the second determining module 44 is further configured to, for the any second three-dimensional point-surface model, determine the first three-dimensional point-surface model and the any second three-dimensional point-surface model at the different times according to the convex hull intersection algorithm. Whether there is an intersection of the 3D point-surface model.
  • the present invention determines the first three-dimensional point-surface model and the second three-dimensional point-surface model at the different times through a convex hull intersection algorithm. Whether there is any intersection of the second three-dimensional point-surface models, it is further determined whether there is an obstacle and whether the robot can pass. It should be noted that, in the present invention, the first three-dimensional point-surface model and the plurality of second three-dimensional point-surface models are actually sets of spatial coordinates of points.
  • Each model corresponds to a set of spatial coordinates of points, wherein the above-mentioned points refer to points on a part of the target object or each moving part of the robot.
  • the convex hull intersection algorithm is used to calculate the set of spatial coordinates of points on the target object corresponding to the first three-dimensional point-surface model and the set of spatial coordinates of each moving part of the robot corresponding to any second three-dimensional point-surface model. , it can be determined whether the first three-dimensional point-surface model and any of the second three-dimensional point-surface models intersect.
  • determining whether the first three-dimensional point-surface model and any of the second three-dimensional point-surface models intersect is actually a kind of prediction for whether the robot collides with the obstacles at the target position after the robot is about to reach the target position. sentence.
  • the above-mentioned method for obtaining the second three-dimensional point-surface model is to inversely calculate the second three-dimensional point-and-surface model corresponding to the above-mentioned moving part at each moment in the control command sequence by using the position information of the moving part and the structure of the part.
  • the adjustment module 46 is further configured to adjust the target moving part in one of the following ways, so that the robot successfully avoids the target object: adjusting the target moving part to the target position, prohibiting the target The moving part moves and adjusts the moving direction of the target moving part.
  • the adjustment methods for adjusting the multiple moving parts of the robot may include but are not limited to the following: (1) Height adjustment, the specific implementation method is that the target moving part can be adjusted to the target position (the obstacle At the lower position, the target moving part and the obstacle are staggered up and down); (2) Prohibition of movement, the specific implementation method is to prohibit the movement of the target moving part (the passage is narrow, if the target moving part moves, it will collide with the obstacle) (3) Adjustment of the moving direction, the specific implementation is to adjust the moving direction of the target moving part (the robot chooses another channel to pass through); (4) The foothold adjustment, the specific implementation is to adjust the foothold of the mobile part of the robot Adjust forward left or right to avoid obstacles.
  • height adjustment may be performed first, and if obstacles still cannot be avoided, you may try to settle on the ground Adjust, if you still can't avoid obstacles, you can try to prohibit movement.
  • the adjustment module 46 is further configured to instruct the robot to execute the sequence of control instructions within the preset time period in sequence when there is no intersection.
  • the robot may execute the sequence of control instructions in the preset time period in sequence.
  • the above modules can be implemented by software or hardware, and the latter can be implemented in the following ways, but not limited to this: the above modules are all located in the same processor; or, the above modules can be combined in any combination The forms are located in different processors.
  • Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored in the storage medium, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.
  • the above-mentioned storage medium may be configured to store a computer program for executing the following steps:
  • the above-mentioned storage medium may include, but is not limited to: U disk, read-only memory ROM, random access memory RAM, removable hard disk, magnetic disk or optical disk and other media that can store computer programs.
  • An embodiment of the present invention also provides an electronic device, comprising a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any of the above method embodiments.
  • the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.
  • the above-mentioned processor may be configured to execute the following steps through a computer program:
  • An embodiment of the present invention also provides a robot, comprising a plurality of moving parts and a controller, and the controller is configured to execute the steps in any one of the above method embodiments.
  • modules or steps of the present invention can be implemented by a general-purpose computing device, which can be centralized on a single computing device, or distributed in a network composed of multiple computing devices Alternatively, they may be implemented in program code executable by a computing device, such that they may be stored in a storage device and executed by the computing device, and in some cases, in a different order than here
  • the steps shown or described are performed either by fabricating them separately into individual integrated circuit modules, or by fabricating multiple modules or steps of them into a single integrated circuit module.
  • the present invention is not limited to any particular combination of hardware and software.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Mechanical Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Robotics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Remote Sensing (AREA)
  • Computer Graphics (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Manipulator (AREA)

Abstract

本发明提供了一种目标对象的躲避方法及装置、存储介质、电子装置，上述方法包括：确定机器人在行进区域内需要躲避的目标对象；获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。采用上述技术方案，能调整机器人的部件，使得机器人能够成功躲避障碍物。

Description

目标对象的躲避方法及装置、存储介质、电子装置 技术领域
本发明涉及通信领域，具体而言，涉及一种目标对象的躲避方法及装置、存储介质、电子装置。
背景技术
随着机器人技术的快速发展，机器人现在已经被应用到用于了各行各业的使用中各个领域。在机器人的使用过程中，机器人躲避障碍物是机器人技术中一项很重要的技术，对机器人在各种环境的应用非常重要。在目前的相关技术中，可以理解成是将机器人当成一个大方块，让这个方块不碰到障碍物，使得机器人可以安全通行，完成机器人工作。但是，在一些复杂的环境以及特殊领域中，地形复杂，障碍物多，机器人所要经过的通道狭窄。在上述机器人应用场景中，就不可以再将机器人当成一个大方块，机器人需要灵活调整自身部件，机器人才能安全通过复杂、狭窄的通道。如果还将机器人理解为是一个整体的方块，机器人就很难通过地形复杂的区域，相关技术不能调整机器人的部件，使得机器人能够成功躲避障碍物的问题。
因此，有必要对相关技术予以改良以克服相关技术中的所述缺陷。
发明内容
本发明的目的在于提供一种目标对象的躲避方法及装置、存储介质、电子装置，以至少解决相关技术中不能调整机器人的部件，使得机器人能够成功躲避障碍物的问题。
本发明的目的是通过以下技术方案实现：
根据本发明的一个可选实施例，提供了一种目标对象的躲避方法，所述方法包括：确定机器人在行进区域内需要躲避的目标对象；获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。
可选的，获取所述机器人的每一个移动部件对应的第二三维点面模型，包括：确定所述每一个移动部件的位置信息，所述每一个移动部件的部件结构，以及在当前时刻之后的预设时间段内，所述机器人的控制指令序列，其中，所述控制指令序列用于指示所述机器人在所述预设时间段内的不同时刻待执行的操作；根据所述位置信息，所述部件结构以及所述控制 指令序列确定所述每一个移动部件对应的第二三维点面模型，以得到所述多个移动部件对应的多个第二三维点面模型。
可选的，确定所述每一个移动部件的位置信息，包括：获取所述机器人的感知智能算法所检测到的定位与地图构建信息，获取所述每一个移动部件上分别设置的编码器所检测到的所述每一个移动部件的转动角度，以及获取所述机器人的惯性测量单元所检测到的数据；根据所述定位与地图构建信息，所述转动角度以及所述数据确定所述每一个移动部件的位置信息。
可选的，根据所述定位与地图构建信息，所述转动角度以及所述数据确定所述每一个移动部件的位置信息，包括：通过卡尔曼滤波器对所述定位与地图构建信息，所述转动角度以及所述数据进行运算，得到运算结果；根据所述运算结果确定所述每一个移动部件的位置信息。
可选的，分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交，包括：对于所述任一第二三维点面模型，根据凸包相交算法确定在所述不同时刻所述第一三维点面模型和所述任一第二三维点面模型是否存在相交。
可选的，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象，包括：通过以下方式之一调整所述目标移动部件，以使所述机器人成功躲避所述目标对象：将所述目标移动部件调高至目标位置、禁止所述目标移动部件移动、调整所述目标移动部件的移动方向。
可选的，分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交之后，所述方法还包括：在不存在相交的情况下，指示所述机器人依次执行所述预设时间段内的所述控制指令序列。
根据本发明的又一个可选实施例，提供了一种目标对象的躲避装置，所述方法包括：第一确定模块，用于确定机器人在行进区域内需要躲避的目标对象；获取模块，用于获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；第二确定模块，用于分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；调整模块，用于在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。
根据本发明的又一个可选实施例，提供了一种计算机可读的存储介质，所述存储介质中存储有计算机程序，其中，所述计算机程序被设置为运行时执行以上任一项中所述的目标对象的躲避方法。
根据本发明的又一个可选实施例，提供了一种电子装置，包括存储器和处理器，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行以上任一项中所述的目标对象的躲避方法。
与相关技术相比，本发明具有如下有益效果：由于可以在确定机器人在行进区域内需要躲避的目标对象的情况下，获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，然后分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交，如果存在相交的情况，那么调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，从而使得所述机器人成功躲避所述目标对象。因此，解决了相关技术中不能调整机器人的部件，使得机器人能够成功躲避障碍物的问题，可以实现灵活的控制机器人躲避障碍物，进而可以将机器人应用在一些地形复杂，障碍物多的场景中。
附图说明
此处所说明的附图用来提供对本发明的进一步理解，构成本发明的一部分，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：
图1是本发明实施例的一种目标对象的躲避方法的机器人的硬件结构框图；
图2是根据本发明实施例的一种目标对象的躲避方法的流程图；
图3是根据本发明实施例的一种目标对象的躲避方法的流程示意图；
图4为根据本发明实施例的一种目标对象的躲避装置的结构框图。
具体实施方式
下文中将参考附图并结合实施例来详细说明本发明。需要说明的是，在不冲突的情况下，本发明中的实施例及实施例中的特征可以相互组合。
需要说明的是，本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
本发明实施例所提供的方法实施例可以在机器人或者类似的运算装置中执行。以运行在机器人上为例，图1是本发明实施例的一种目标对象的躲避方法的机器人的硬件结构框图。如图1所示，机器人可以包括一个或多个(图1中仅示出一个)处理器102(处理器102可以包括但不限于微处理器(Microprocessor Unit,简称是MPU)或可编程逻辑器件(Programmable logic device,简称是PLD)等的处理装置和用于存储数据的存储器104，可选地，上述机器人还可以包括用于通信功能的传输设备106以及输入输出设备108。本领域普通技术人员可以理解，图 1所示的结构仅为示意，其并不对上述机器人的结构造成限定。例如，机器人还可包括比图1中所示更多或者更少的组件，或者具有与图1所示等同功能或比图1所示功能更多的不同的配置。
存储器104可用于存储计算机程序，例如，应用软件的软件程序以及模块，如本发明实施例中的目标对象的躲避方法对应的计算机程序，处理器102通过运行存储在存储器104内的计算机程序，从而执行各种功能应用以及数据处理，即实现上述的方法。存储器104可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器104可进一步包括相对于处理器102远程设置的存储器，这些远程存储器可以通过网络连接至机器人。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
传输设备106用于经由网络接收或者发送数据。上述的网络具体实例可包括机器人的通信供应商提供的无线网络。在一个实例中，传输设备106包括一个网络适配器(Network Interface Controller，简称为NIC)，其可通过基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中，传输设备106可以为射频(Radio Frequency，简称为RF)模块，其用于通过无线方式与互联网进行通讯。
在本实施例中提供了一种运行于上述目标对象的躲避方法，图2是根据本发明实施例的目标对象的躲避方法的流程图，如图2所示，该流程包括如下步骤：
步骤S202，确定机器人在行进区域内需要躲避的目标对象；
步骤S204，获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；
步骤S206，分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；
步骤S208，在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。
通过上述技术方案，由于可以在确定机器人在行进区域内需要躲避的目标对象的情况下，获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，然后分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交，如果存在相交的情况，那么调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，从而使得所述机器人成功躲避所述目标对象。因此，本发明实施例的技术方案能调整机器人的部件，使得机器人能够成功躲避障碍物，进而可以将机器人应用在一些地形复杂，障碍物多的场景中。
需要说明的是，本发明实施例的机器人可以是双足机器人，三足机器人，还可以是四足机器人，本发明实施例对此不进行限定。
步骤S204的实现方法有多种，在一个可选实施例中，获取所述机器人的每一个移动部件对应的第二三维点面模型，可以通过以下方案实现：确定所述每一个移动部件的位置信息，所述每一个移动部件的部件结构，以及在当前时刻之后的预设时间段内，所述机器人的控制指令序列，其中，所述控制指令序列用于指示所述机器人在所述预设时间段内的不同时刻待执行的操作；根据所述位置信息，所述部件结构以及所述控制指令序列确定所述每一个移动部件对应的第二三维点面模型，以得到所述多个移动部件对应的多个第二三维点面模型。
可以理解的是，以四足机器人为例，四足机器人中的每一个移动部件都需要确定第二三维点面模型，四个移动部件的三维点面模型的确定过程可以是同步进行，也可以是依次进行，移动部件可以理解为是机器人上腿部和足部的结构件。
需要说明的是，本发明实施例的技术方案：对于有环境感知能力的机器人，在机器人的行进过程中各个部件不能触碰的区域或者障碍物进行碰撞检测，并依据检测结果对机器人的移动部件做及时的调整，以保证四足机器人在复杂地面环境中行走的安全性。本发明实施例通过目标对象(障碍物或者机器人不能触碰的区域)的第一三维点面模型，以及机器人的每一个移动部件对应的第二三维点面模型来实现机器人的精确避障。为实现上述目的，本发明实施例需要获取目标对象的第一三维点面模型，以及机器人的每一个移动部件对应的第二三维点面模型，其中，机器人的每一个移动部件都对应的一个第二三维点面模型，本发明实施例会获取到多个第二三维点面模型。
为了确定到机器人的每一个移动部件对应的第二三维点面模型，需要获取到每一个移动部件的位置信息，每一个移动部件的部件结构，以及在当前时刻之后的预设时间段内，机器人的控制指令序列。需要说明的是，所述控制指令序列是用于指示所述机器人在预设时间段内的不同时刻待执行的操作，可以从机器人控制算法中拿取当前时刻之后预设时间段内的一系列控制指令序列，上述控制指令序列通常为5～1000个序列。通过机器人的每一个移动部件位置信息、部件结构以及控制指令序列就可以确定每一个移动部件对应的第二三维点面模型，进而就可以得到多个移动部件分别对应的多个第二三维点面模型。需要说明的是，上述得到第二三维点面模型的方法是通过移动部件的位置信息和部件结构反算出控制指令序列中每个时刻上述移动部件对应的第二三维点面模型。
在一个可选实施例中，确定所述每一个移动部件的位置信息，包括：获取所述机器人的感知智能算法所检测到的定位与地图构建信息，获取所述每一个移动部件上分别设置的编码器所检测到的所述每一个移动部件的转动角度，以及获取所述机器人的惯性测量单元所检测 到的数据；根据所述定位与地图构建信息，所述转动角度以及所述数据确定所述每一个移动部件的位置信息。
需要说明的是，为了确定机器人的每一个移动部件对应的第二三维点面模型，需要获取到每一个移动部件的位置信息。为了获取到每一个移动部件的位置信息，需要获取到机器人检测到的定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据(相当于上述实施例的惯性测量单元所检测到的数据)。需要说明的是，定位与地图构建信息可以通过机器人的感知智能算法所检测获取到，机器人的每一个移动部件的转动角度可以通过每一个移动部件上分别设置的编码器检测获取到，机器人惯性数据可以通过机器人的惯性测量单元检测获取到。其中，机器人惯性数据是关于机器人当前时刻行动或者动作的数据。根据定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据就可以确定机器人的每一个移动部件的位置信息。
在一个可选实施例中，根据所述定位与地图构建信息，所述转动角度以及所述数据确定所述每一个移动部件的位置信息，可以通过以下方案实现：通过卡尔曼滤波器对所述定位与地图构建信息，所述转动角度以及所述数据进行运算，得到运算结果；根据所述运算结果确定所述每一个移动部件的位置信息。
需要说明的是，本发明实施例可以通过卡尔曼滤波器对定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据进行运算，得到机器人的每一个移动部件的位置信息。本发明实施例通过卡尔曼滤波器对上述定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据进行滤波，滤除上述定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据中的干扰。同时通过卡尔曼滤波器中的线性系统状态方程对上述定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据进行最优估计，进而得到机器人的每一个移动部件的位置信息。
步骤S206的实现方案中，分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交，可以通过以下方案实现：对于所述任一第二三维点面模型，根据凸包相交算法确定在所述不同时刻所述第一三维点面模型和所述任一第二三维点面模型是否存在相交。
需要说明的是，在得到所述第一三维点面模型与多个所述第二三维点面模型之后，本发明实施例通过凸包相交算法确定在所述不同时刻所述第一三维点面模型和所述任一第二三维点面模型是否存在相交，进而判定是否存在障碍物，机器人是否可以通行。需要说明的是，本发明实施例得到所述第一三维点面模型与多个所述第二三维点面模型实际上都是关于点的空间坐标的集合。每一个模型对应一个关于点的空间坐标的集合，其中，上述点是指目标 对象或者机器人的每一个移动部件的一个部位上的点。通过凸包相交算法对第一三维点面模型对应的目标对象上关于点的空间坐标的集合和任一第二三维点面模型对应的机器人的每一个移动部件关于点的空间坐标的集合进行运算，就可以确定第一三维点面模型和所述任一第二三维点面模型是否存在相交。
需要说明的是，确定第一三维点面模型和所述任一第二三维点面模型是否存在相交，实际上对机器人将要到达目标位置后机器人和目标位置的障碍物是否相撞的一种预判。上述得到第二三维点面模型的方法是通过移动部件的位置信息和部件结构反算出控制指令序列中每个时刻上述移动部件对应的第二三维点面模型。也就是说，机器人根据所述控制指令序列将要到达的目标位置后机器人各个移动部件的第二三维点面模型与目标位置的障碍物的第一三维点面模型是否存在交集(模型对应的是关于点的空间坐标的集合)，如果存在交集，就说明机器人与障碍物可能相撞，就需要调整机器人和机器人的多个移动部件，使得调整后的各个移动部件的第二三维点面模型是否与目标位置的障碍物的第一三维点面模型不存在交集，进而机器人安全通过。
可选地，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象，包括：通过以下方式之一调整所述目标移动部件，以使所述机器人成功躲避所述目标对象：将所述目标移动部件调高至目标位置、禁止所述目标移动部件移动、调整所述目标移动部件的移动方向。
需要说明的是，机器人各个移动部件的第二三维点面模型与目标位置的障碍物的第一三维点面模型存在交集，就说明机器人与障碍物可能相撞，就需要调整机器人和机器人的多个移动部件，对于调整机器人的多个移动部件的调整方式可以但不限于包括以下几种：(1)高度调整，具体实现方式是可以将所述目标移动部件调高至目标位置(障碍物在较低的位置上，目标移动部件和障碍物上下错开)；(2)禁止移动，具体实现方式是禁止所述目标移动部件移动(通道狭窄，目标移动部件如果移动就会和障碍物相撞)；(3)移动方向调整，具体实现方式是调整所述目标移动部件的移动方向(机器人选择另一种通道通行)；(4)落脚点调整，具体实现方式是将机器人的移动部件的落脚点向左前或者右前调整，以躲避障碍物。
需要说明的是，上述四种调整方式可以结合使用，本发明实施例对此不进行限定，在一个可选的实施例中，可以先进行高度调整，如果仍然无法躲避障碍物，可以尝试落脚地调整，如果仍然无法躲避障碍物，可以尝试禁止移动。
在执行步骤S206之后，也就是分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交之后，所述方法还包括：在不存在相交的情况 下，指示所述机器人依次执行所述预设时间段内的所述控制指令序列。
需要说明的是，如果所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型不存在相交，也就是机器人各个移动部件的第二三维点面模型与目标位置的障碍物的第一三维点面模型不存在交集，就说明机器人与障碍物不会相撞，机器人可以通行。在上述情况中，机器人依次执行所述预设时间段内的所述控制指令序列即可。
为了更好的理解上述技术方案，本发明还提供了一种可选实施例，用于解释说明上述技术方案。
图3是根据本发明实施例的一种目标对象的躲避方法的流程示意图，如图3所示：
S302:接收上层感知算法发送的环境信息，上述环境信息包括2D地图和三维环境信息，以及机器人的位置信息、需要机器人精确避障的物品信息(相当于上述实施例的目标对象)；
S304:建立目标对象的第一三维点面模型；
S306:获取机器人每一个移动部件的位置信息、部件结构、控制指令序列；
S308:建立机器人的每一个移动部件对应的第二三维点面模型，得到多个所述第二三维点面模型；
S310:确定第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；
S312:如果存在相交，调整与第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象；
S314:如果不存在相交继续执行上述控制指令序列。
通过上述技术方案，由于可以在确定机器人在行进区域内需要躲避的目标对象的情况下，获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，然后分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交，如果存在相交的情况，那么调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，从而使得所述机器人成功躲避所述目标对象。因此，本发明实施例的技术方案能调整机器人的部件，使得机器人能够成功躲避障碍物，进而可以将机器人应用在一些地形复杂，障碍物多的场景中。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如只读存储器(Read-Only Memory，简称为ROM)、随机存取存储器(Random Access Memory， 简称为RAM)、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
在本实施例中还提供了一种目标对象的躲避装置，该目标对象的躲避装置用于实现上述实施例及优选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图4为根据本发明可选实施例的一种目标对象的躲避装置的结构框图，如图4所示：
第一确定模块40，用于确定机器人在行进区域内需要躲避的目标对象；
获取模块42，用于获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；
第二确定模块44，用于分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；
调整模块46，用于在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。
通过上述技术方案，由于可以在确定机器人在行进区域内需要躲避的目标对象的情况下，获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，然后分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交，如果存在相交的情况，那么调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，从而使得所述机器人成功躲避所述目标对象。因此，本发明实施例的技术方案能调整机器人的部件，使得机器人能够成功躲避障碍物，进而可以将机器人应用在一些地形复杂，障碍物多的场景中。
可选的，获取模块42还用于确定所述每一个移动部件的位置信息，所述每一个移动部件的部件结构，以及在当前时刻之后的预设时间段内，所述机器人的控制指令序列，其中，所述控制指令序列用于指示所述机器人在所述预设时间段内的不同时刻待执行的操作；根据所述位置信息，所述部件结构以及所述控制指令序列确定所述每一个移动部件对应的第二三维点面模型，以得到所述多个移动部件对应的多个第二三维点面模型。
可以理解的是，以四足机器人为例，四足机器人中的每一个移动部件都需要确定第二三维点面模型，四个移动部件的三维点面模型的确定过程可以是同步进行，也可以是依次进行，移动部件可以理解为是机器人上腿部和足部的结构件。
需要说明的是，本发明实施例的技术方案：对于有环境感知能力的机器人，在机器人的行进过程中各个部件不能触碰的区域或者障碍物进行碰撞检测，并依据检测结果对机器人的 移动部件做及时的调整，以保证四足机器人在复杂地面环境中行走的安全性。本发明实施例通过目标对象(障碍物或者机器人不能触碰的区域)的第一三维点面模型，以及机器人的每一个移动部件对应的第二三维点面模型来实现机器人的精确避障。为实现上述目的，本发明实施例需要获取目标对象的第一三维点面模型，以及机器人的每一个移动部件对应的第二三维点面模型，其中，机器人的每一个移动部件都对应的一个第二三维点面模型，本发明实施例会获取到多个第二三维点面模型。
为了确定到机器人的每一个移动部件对应的第二三维点面模型，需要获取到每一个移动部件的位置信息，每一个移动部件的部件结构，以及在当前时刻之后的预设时间段内，机器人的控制指令序列。需要说明的是，所述控制指令序列是用于指示所述机器人在预设时间段内的不同时刻待执行的操作，可以从机器人控制算法中拿取当前时刻之后预设时间段内的一系列控制指令序列，上述控制指令序列通常为5～1000个序列。通过机器人的每一个移动部件位置信息、部件结构以及控制指令序列就可以确定每一个移动部件对应的第二三维点面模型，进而就可以得到多个移动部件分别对应的多个第二三维点面模型。需要说明的是，上述得到第二三维点面模型的方法是通过移动部件的位置信息和部件结构反算出控制指令序列中每个时刻上述移动部件对应的第二三维点面模型。也即是说，机器人的控制指令序列是基于当前时刻之后预设时间段内的第二三维点面模型的控制机器人的多个指令，因此，可以通过上述控制指令序列反算出基于当前时刻之后预设时间段内的第二三维点面模型。
可选的，获取模块42还用于获取所述机器人的感知智能算法所检测到的定位与地图构建信息，获取所述每一个移动部件上分别设置的编码器所检测到的所述每一个移动部件的转动角度，以及获取所述机器人的惯性测量单元所检测到的数据；根据所述定位与地图构建信息，所述转动角度以及所述数据确定所述每一个移动部件的位置信息。
需要说明的是，为了确定到机器人的每一个移动部件对应的第二三维点面模型，需要获取到每一个移动部件的位置信息。为了获取到每一个移动部件的位置信息，需要获取到机器人检测到的定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据(所述数据)。需要说明的是，定位与地图构建信息可以通过机器人的感知智能算法所检测获取到，机器人的每一个移动部件的转动角度可以通过每一个移动部件上分别设置的编码器检测获取到，机器人惯性数据可以通过机器人的惯性测量单元检测获取到。其中，机器人惯性数据是关于机器人当前时刻行动或者动作的数据。根据定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据确定机器人的每一个移动部件的位置信息。
可选的，获取模块42还用于通过卡尔曼滤波器对所述定位与地图构建信息，所述转动角度以及所述数据进行运算，得到运算结果；根据所述运算结果确定所述每一个移动部件的位 置信息。
需要说明的是，本发明实施例可以通过卡尔曼滤波器对定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据进行运算，得到机器人的每一个移动部件的位置信息。本发明实施例通过卡尔曼滤波器对上述定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据进行滤波，滤除上述定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据中的干扰。同时通过卡尔曼滤波器中的线性系统状态方程对上述定位与地图构建信息，机器人的每一个移动部件的转动角度以及机器人惯性数据进行最优估计，进而得到机器人的每一个移动部件的位置信息。
可选的，第二确定模块44还用于对于所述任一第二三维点面模型，根据凸包相交算法确定在所述不同时刻所述第一三维点面模型和所述任一第二三维点面模型是否存在相交。
需要说明的是，在得到所述第一三维点面模型与多个所述第二三维点面模型之后，本发明通过凸包相交算法确定在所述不同时刻所述第一三维点面模型和所述任一第二三维点面模型是否存在相交，进而判定是否存在障碍物，机器人是否可以通行。需要说明的是，本发明得到所述第一三维点面模型与多个所述第二三维点面模型实际上都是关于点的空间坐标的集合。每一个模型对应一个关于点的空间坐标的集合，其中，上述点是指目标对象或者机器人的每一个移动部件的一个部位上的点。通过凸包相交算法对第一三维点面模型对应的目标对象上关于点的空间坐标的集合和任一第二三维点面模型对应的机器人的每一个移动部件关于点的空间坐标的集合进行运算，就可以确定第一三维点面模型和所述任一第二三维点面模型是否存在相交。
需要说明的是，确定第一三维点面模型和所述任一第二三维点面模型是否存在相交，实际上对机器人将要到达目标位置后机器人和目标位置的障碍物是否相撞的一种预判。上述得到第二三维点面模型的方法是通过移动部件的位置信息和部件结构反算出控制指令序列中每个时刻上述移动部件对应的第二三维点面模型。也就是说，机器人根据所述控制指令序列将要到达的目标位置后机器人各个移动部件的第二三维点面模型与目标位置的障碍物的第一三维点面模型是否存在交集(模型对应的是关于点的空间坐标的集合)，如果存在交集，就说明机器人与障碍物可能相撞，就需要调整机器人和机器人的多个移动部件，使得调整后的各个移动部件的第二三维点面模型是否与目标位置的障碍物的第一三维点面模型不存在交集，进而机器人安全通过。
可选的，调整模块46还用于通过以下方式之一调整所述目标移动部件，以使所述机器人成功躲避所述目标对象：将所述目标移动部件调高至目标位置、禁止所述目标移动部件移动、调整所述目标移动部件的移动方向。
需要说明的是，机器人各个移动部件的第二三维点面模型与目标位置的障碍物的第一三维点面模型存在交集，就说明机器人与障碍物可能相撞，就需要调整机器人和机器人的多个移动部件，对于调整机器人的多个移动部件的调整方式可以但不限于包括以下几种：(1)高度调整，具体实现方式是可以将所述目标移动部件调高至目标位置(障碍物在较低的位置上，目标移动部件和障碍物上下错开)；(2)禁止移动，具体实现方式是禁止所述目标移动部件移动(通道狭窄，目标移动部件如果移动就会和障碍物相撞)；(3)移动方向调整，具体实现方式是调整所述目标移动部件的移动方向(机器人选择另一种通道通行)；(4)落脚点调整，具体实现方式是将机器人的移动部件的落脚点向左前或者右前调整，以躲避障碍物。
需要说明的是，上述四种调整方式可以结合使用，本发明实施例对此不进行限定，在一个可选的实施例中，可以先进行高度调整，如果仍然无法躲避障碍物，可以尝试落脚地调整，如果仍然无法躲避障碍物，可以尝试禁止移动。
可选的，调整模块46还用于在不存在相交的情况下，指示所述机器人依次执行所述预设时间段内的所述控制指令序列。
需要说明的是，如果所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型不存在相交，也就是机器人各个移动部件的第二三维点面模型与目标位置的障碍物的第一三维点面模型不存在交集，就说明机器人与障碍物不会相撞，机器人可以通行。在上述情况中，机器人依次执行所述预设时间段内的所述控制指令序列即可。
需要说明的是，上述各个模块是可以通过软件或硬件来实现的，对于后者，可以通过以下方式实现，但不限于此：上述模块均位于同一处理器中；或者，上述各个模块以任意组合的形式分别位于不同的处理器中。
本发明的实施例还提供了一种计算机可读的存储介质，该存储介质中存储有计算机程序，其中，该计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
可选地，在本实施例中，上述存储介质可以被设置为存储用于执行以下步骤的计算机程序：
S1，确定机器人在行进区域内需要躲避的目标对象；
S2，获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；
S3，分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；
S4，在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型 所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器ROM、随机存取存储器RAM、移动硬盘、磁碟或者光盘等各种可以存储计算机程序的介质。
本发明的实施例还提供了一种电子装置，包括存储器和处理器，该存储器中存储有计算机程序，该处理器被设置为运行计算机程序以执行上述任一项方法实施例中的步骤。
可选地，上述电子装置还可以包括传输设备以及输入输出设备，其中，该传输设备和上述处理器连接，该输入输出设备和上述处理器连接。
可选地，在本实施例中，上述处理器可以被设置为通过计算机程序执行以下步骤：
S1，确定机器人在行进区域内需要躲避的目标对象；
S2，获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；
S3，分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；
S4，在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。
可选地，本实施例中的具体示例可以参考上述实施例及可选实施方式中所描述的示例，本实施例在此不再赘述。
本发明的实施例还提供了一种机器人，包括多个移动部件和控制器，该控制器用于执行上述任一项方法实施例中的步骤。
显然，本领域的技术人员应该明白，上述的本发明的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本发明不限制于任何特定的硬件和软件结合。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种目标对象的躲避方法，其特征在于，所述方法包括：
    确定机器人在行进区域内需要躲避的目标对象；
    获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；
    分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；
    在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。
  2. 如权利要求1所述的目标对象的躲避方法，其特征在于：获取所述机器人的每一个移动部件对应的第二三维点面模型，包括：
    确定所述每一个移动部件的位置信息，所述每一个移动部件的部件结构，以及在当前时刻之后的预设时间段内，所述机器人的控制指令序列，其中，所述控制指令序列用于指示所述机器人在所述预设时间段内的不同时刻待执行的操作；
    根据所述位置信息，所述部件结构以及所述控制指令序列确定所述每一个移动部件对应的第二三维点面模型，以得到所述多个移动部件对应的多个第二三维点面模型。
  3. 如权利要求2所述的目标对象的躲避方法，其特征在于：确定所述每一个移动部件的位置信息，包括：
    获取所述机器人的感知智能算法所检测到的定位与地图构建信息，获取所述每一个移动部件上分别设置的编码器所检测到的所述每一个移动部件的转动角度，以及获取所述机器人的惯性测量单元所检测到的数据；
    根据所述定位与地图构建信息，所述转动角度以及所述数据确定所述每一个移动部件的位置信息。
  4. 如权利要求3所述的目标对象的躲避方法，其特征在于：根据所述定位与地图构建信息，所述转动角度以及所述数据确定所述每一个移动部件的位置信息，包括：
    通过卡尔曼滤波器对所述定位与地图构建信息，所述转动角度以及所述数据进行运算，得到运算结果；
    根据所述运算结果确定所述每一个移动部件的位置信息。
  5. 如权利要求2所述的目标对象的躲避方法，其特征在于：分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交，包括：
    对于所述任一第二三维点面模型，根据凸包相交算法确定在所述不同时刻所述第一三维点面模型和所述任一第二三维点面模型是否存在相交。
  6. 如权利要求1所述的目标对象的躲避方法，其特征在于：调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象，包括：
    通过以下方式之一调整所述目标移动部件，以使所述机器人成功躲避所述目标对象：
    将所述目标移动部件调高至目标位置、禁止所述目标移动部件移动、调整所述目标移动部件的移动方向。
  7. 如权利要求2所述的目标对象的躲避方法，其特征在于：分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交之后，所述方法还包括：
    在不存在相交的情况下，指示所述机器人依次执行所述预设时间段内的所述控制指令序列。
  8. 一种目标对象的躲避装置，其特征在于，所述方法包括：
    第一确定模块，用于确定机器人在行进区域内需要躲避的目标对象；
    获取模块，用于获取所述目标对象的第一三维点面模型，以及获取所述机器人的每一个移动部件对应的第二三维点面模型，其中，所述机器人设置有多个移动部件；
    第二确定模块，用于分别确定所述第一三维点面模型与多个所述第二三维点面模型中的任一第二三维点面模型是否存在相交；
    调整模块，用于在存在相交的情况下，调整与所述第一三维点面模型存在相交的第二三维点面模型所对应的目标移动部件，以使所述机器人成功躲避所述目标对象。
  9. 一种计算机可读的存储介质，其特征在于，所述存储介质中存储有计算机程序，其中，所述计算机程序被设置为运行时执行所述权利要求1至7任一项中所述的方法。
  10. 一种电子装置，包括存储器和处理器，其特征在于，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行所述权利要求1至7任一项中所述的方法。
PCT/CN2021/137063 2021-02-08 2021-12-10 目标对象的躲避方法及装置、存储介质、电子装置 Ceased WO2022166397A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110180718.3A CN112991527B (zh) 2021-02-08 2021-02-08 目标对象的躲避方法及装置、存储介质、电子装置
CN202110180718.3 2021-02-08

Publications (1)

Publication Number Publication Date
WO2022166397A1 true WO2022166397A1 (zh) 2022-08-11

Family

ID=76393815

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/137063 Ceased WO2022166397A1 (zh) 2021-02-08 2021-12-10 目标对象的躲避方法及装置、存储介质、电子装置

Country Status (2)

Country Link
CN (2) CN114742960B (zh)
WO (1) WO2022166397A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114742960B (zh) * 2021-02-08 2025-11-25 魔法原子机器人科技(无锡)有限公司 目标对象的躲避方法及装置、存储介质、电子装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070271011A1 (en) * 2006-05-12 2007-11-22 Samsung Electronics Co., Ltd. Indoor map building apparatus, method, and medium for mobile robot
CN108733065A (zh) * 2017-09-29 2018-11-02 北京猎户星空科技有限公司 一种机器人的避障方法、装置及机器人
CN109407705A (zh) * 2018-12-14 2019-03-01 厦门理工学院 一种无人机躲避障碍物的方法、装置、设备和存储介质
CN111743464A (zh) * 2020-07-06 2020-10-09 追创科技(苏州)有限公司 一种基于线激光的避障方法及装置
CN112991527A (zh) * 2021-02-08 2021-06-18 追创科技(苏州)有限公司 目标对象的躲避方法及装置、存储介质、电子装置

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003136466A (ja) * 2001-10-25 2003-05-14 Murata Mach Ltd 産業用ロボットの制御装置
JP3985677B2 (ja) * 2002-12-25 2007-10-03 株式会社安川電機 水平多関節ロボットの干渉チェック装置および方法
US10705528B2 (en) * 2015-12-15 2020-07-07 Qualcomm Incorporated Autonomous visual navigation
CN107688342B (zh) * 2017-03-27 2019-05-10 平安科技（深圳）有限公司 机器人的避障控制系统及方法
CN108733045B (zh) * 2017-09-29 2022-01-04 北京猎户星空科技有限公司 机器人及其避障方法以及计算机可读存储介质
TW201931039A (zh) * 2018-01-12 2019-08-01 鴻海精密工業股份有限公司 能上下電梯的機械人以及利用該機械人收送物品的方法
CN109063635A (zh) * 2018-07-27 2018-12-21 平安科技（深圳）有限公司 一种设备控制方法、终端及计算机可读介质
CN110244717B (zh) * 2019-06-03 2020-08-07 武汉理工大学 基于既有三维模型的港口起重机攀爬机器人自动寻路方法
CN110271006A (zh) * 2019-07-19 2019-09-24 北京农业智能装备技术研究中心 机械臂视觉引导方法及装置
CN110632921B (zh) * 2019-09-05 2022-11-18 北京百度网讯科技有限公司 机器人路径规划方法、装置、电子设备和存储介质
CN110658819B (zh) * 2019-09-30 2022-04-15 北京猎户星空科技有限公司 一种避障方法、装置、电子设备和存储介质
CN110936383B (zh) * 2019-12-20 2022-11-18 上海有个机器人有限公司 一种机器人的障碍物避让方法、介质、终端和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070271011A1 (en) * 2006-05-12 2007-11-22 Samsung Electronics Co., Ltd. Indoor map building apparatus, method, and medium for mobile robot
CN108733065A (zh) * 2017-09-29 2018-11-02 北京猎户星空科技有限公司 一种机器人的避障方法、装置及机器人
CN109407705A (zh) * 2018-12-14 2019-03-01 厦门理工学院 一种无人机躲避障碍物的方法、装置、设备和存储介质
CN111743464A (zh) * 2020-07-06 2020-10-09 追创科技(苏州)有限公司 一种基于线激光的避障方法及装置
CN112991527A (zh) * 2021-02-08 2021-06-18 追创科技(苏州)有限公司 目标对象的躲避方法及装置、存储介质、电子装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHANG QIQIAN, XU WEIWEI;ZHANG HONGHAI;LI HAN: "The Obstacle-Avoidance Path Planning for UAV Based on IOCAD", JOURNAL OF NORTHWESTERN POLYTECHNICAL UNIVERSITY, XUBEI GONGYE DAXUE , SHAANXI, CN, vol. 38, no. 2, 30 April 2020 (2020-04-30), CN , pages 238 - 245, XP055955465, ISSN: 1000-2758, DOI: 10.1051/jnwpu/20203820238 *

Also Published As

Publication number Publication date
CN112991527B (zh) 2022-04-19
CN112991527A (zh) 2021-06-18
CN114742960A (zh) 2022-07-12
CN114742960B (zh) 2025-11-25

Similar Documents

Publication Publication Date Title
AU2022289723B2 (en) Guidance system to navigate intervening obstacles and methods for same
KR20200092857A (ko) 로봇의 이동 경로를 결정하는 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체
CN108733065B (zh) 一种机器人的避障方法、装置及机器人
CN110986953A (zh) 路径规划方法、机器人及计算机可读存储介质
CN116547113A (zh) 机器人系统的远程操作
WO2016103297A1 (ja) アーム型のロボットの障害物自動回避方法及び制御装置
CN112546630B (zh) 角色移动方法及装置
CN110940341A (zh) 路径规划方法、机器人及计算机可读存储介质
US20240025049A1 (en) Robot teleoperation method, robot and storage medium
CN112066994A (zh) 一种消防机器人局部自主导航方法及系统
CN115229789B (zh) 机器人的遥操作方法、机器人及存储介质
WO2022166397A1 (zh) 目标对象的躲避方法及装置、存储介质、电子装置
CN110658816B (zh) 一种基于智能组件的移动机器人导航与控制方法
CN113110459A (zh) 一种多足机器人运动规划方法
Pereira et al. Navigation of semi-autonomous service robots using local information and anytime motion planners
Grandi et al. Coordination and control of autonomous mobile robot groups using a hybrid technique based on particle swarm optimization and consensus
CN106647248B (zh) 一种确定串联机器人反解结果的方法及装置
Kohlbrecher et al. Overview of team vigir's approach to the virtual robotics challenge
Roditis et al. Maintaining static stability and continuous motion in rough terrain hexapod locomotion without terrain mapping
CN113791620B (zh) 动态自适应定位方法、定位系统、机器人及存储介质
Kim et al. Transformable Gaussian Reward Function for Socially-Aware Navigation with Deep Reinforcement Learning
HN et al. Autonomous quadruped robot equipped with obstacle detection
CN112445211B (zh) 机器人的控制方法和装置、存储介质及电子装置
Jung et al. Implementation of symmetrical rank based formation for multiple robots
CN114839987B (zh) 机器人的移动控制方法、装置、设备及存储介质

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: 21924390

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21924390

Country of ref document: EP

Kind code of ref document: A1