WO2023130755A1 - 路径规划方法、电子设备、计算机程序产品及存储介质 - Google Patents

路径规划方法、电子设备、计算机程序产品及存储介质 Download PDF

Info

Publication number
WO2023130755A1
WO2023130755A1 PCT/CN2022/117288 CN2022117288W WO2023130755A1 WO 2023130755 A1 WO2023130755 A1 WO 2023130755A1 CN 2022117288 W CN2022117288 W CN 2022117288W WO 2023130755 A1 WO2023130755 A1 WO 2023130755A1
Authority
WO
WIPO (PCT)
Prior art keywords
motion
robot
speed
preset
trajectory
Prior art date
Application number
PCT/CN2022/117288
Other languages
English (en)
French (fr)
Inventor
孙喜庆
奉飞飞
唐剑
Original Assignee
美的集团(上海)有限公司
美的集团股份有限公司
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 美的集团(上海)有限公司, 美的集团股份有限公司 filed Critical 美的集团(上海)有限公司
Publication of WO2023130755A1 publication Critical patent/WO2023130755A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle

Definitions

  • the present application relates to the technical field of robots, in particular to a path planning method, electronic equipment, computer program products and storage media.
  • the present application proposes a route planning method, electronic equipment, computer program products and storage media to solve the above technical problems.
  • the first technical solution adopted by this application is to provide a path planning method, the method comprising: obtaining motion state information of the robot at different positions, and obtaining a plurality of motion state information; Based on the multiple motion state information and the target position of the robot, plan multiple motion trajectories; evaluate the multiple motion trajectories based on at least one preset evaluation rule, and select an adapted motion trajectory; based on the adapted Motion track, control the robot to move.
  • the second technical solution adopted by this application is to provide an electronic device, which includes a sampling module, a planning module, an evaluation module and a control module; the sampling module is used to obtain the motion state of the robot, A plurality of motion state information is obtained; the planning module is used to plan a plurality of motion trajectories based on the plurality of motion state information and the target position of the robot; the evaluation module is used to evaluate the The multiple motion trajectories are evaluated, and an adapted motion trajectory is selected; the control module is used to control the robot to move based on the adapted motion trajectory.
  • the third technical solution adopted by this application is to provide an electronic device, the electronic device includes a processor and a memory connected to the processor, wherein the memory stores program instructions;
  • the processor is configured to execute the program instructions stored in the memory to implement the path planning method as described above.
  • the fourth technical solution adopted by this application is to provide a computer program product, including computer program instructions, the computer program instructions enable a computer to implement the path planning method as described above.
  • the fifth technical solution adopted by this application is to provide a computer-readable storage medium, the computer-readable storage medium stores program instructions, and when the program instructions are executed, the above-mentioned path planning method.
  • the path planning method obtains multiple motion state information by acquiring motion state information of a robot at different positions; based on multiple motion state information and robot Based on the target position, plan multiple motion trajectories; evaluate multiple motion trajectories based on preset evaluation rules, and select an adapted motion trajectory; control the robot to move based on the adapted motion trajectory.
  • the robot's motion trajectory can be planned according to the robot's motion state information, and the motion trajectory can be evaluated according to multiple preset evaluation rules to select the most suitable motion trajectory, which can effectively improve the robot's motion. efficiency.
  • FIG. 1 is a schematic flow chart of the first embodiment of the path planning method provided by the present application.
  • FIG. 2 is a schematic flowchart of a second embodiment of the path planning method provided by the present application.
  • Fig. 3 is a schematic diagram of obtaining multiple accelerations in Fig. 2;
  • FIG. 4 is a schematic flowchart of a third embodiment of the path planning method provided by the present application.
  • Fig. 5 is a schematic diagram of obtaining multiple variable accelerations in Fig. 4;
  • FIG. 6 is a schematic flowchart of a fourth embodiment of the path planning method provided by the present application.
  • FIG. 7 is a schematic flowchart of a fifth embodiment of the path planning method provided by the present application.
  • FIG. 8 is a schematic flowchart of a sixth embodiment of the path planning method provided by the present application.
  • FIG. 9 is a schematic flowchart of a seventh embodiment of the path planning method provided by the present application.
  • FIG. 10 is a schematic structural diagram of an embodiment of an electronic device provided by the present application.
  • Fig. 11 is a schematic structural diagram of an embodiment of a computer-readable storage medium provided by the present application.
  • DWA Dynamic Window Approach
  • the future motion state of the robot can be accurately expressed, which limits the further application of the DWA algorithm.
  • FIG. 1 is a schematic flowchart of a first embodiment of a path planning method provided in this application.
  • the path planning method described in the embodiment of the present application is applied to an electronic device, and the electronic device of the present application can be a server, or a system in which the server and the electronic device cooperate with each other; the electronic device can also be set in the robot , to plan the trajectory of the robot.
  • the robot path planning method of the present application can be applied to an electronic device, and the path planning method specifically includes the following steps:
  • the motion state of the robot is obtained to obtain the historical motion state and/or the current motion state of the robot, and multiple motion states of the robot are obtained based on the historical motion state and/or the current motion state of the robot information, wherein the motion state information is the motion state information that the robot may exist in a certain period of time in the future.
  • the motion state information includes but not limited to position information, speed information, speed change information, sampling time, etc. of the robot, wherein the speed information includes but not limited to linear velocity and/or angular velocity.
  • S12 Planning multiple motion trajectories based on multiple motion state information and target positions of the robot.
  • the motion trajectory is planned, and multiple planned motion trajectories are obtained.
  • the simulation time can be set in the electronic device.
  • the simulation time is the time for planning the motion trajectory.
  • the simulation time can be adjusted according to the application scenario of the robot. If the simulation time is too long, the planned motion trajectory will deviate from the global planning route. If the simulation time is too short, it will easily lead to frequent path planning and cause the robot to oscillate.
  • S13 Evaluate multiple motion trajectories based on at least one preset evaluation rule, and select an adapted motion trajectory.
  • the multiple motion trajectories are evaluated based on preset evaluation rules, so as to select a motion trajectory that is compatible with the preset evaluation rules.
  • the preset evaluation rules may include the azimuth evaluation function, the fit degree of the global planning route, weight parameters, etc.
  • the azimuth evaluation function is used to evaluate whether the motion trajectory is toward the target position, and the degree of fit of the global planning route is used to limit the The degree of fit between the motion trajectory and the global planning route, and the weight parameters are used to control the speed of the robot;
  • the preset evaluation rules can also include whether there are obstacles on the motion trajectory, the distance between the motion trajectory and the obstacle, etc.
  • the preset The evaluation rules are not specifically limited. Based on the preset evaluation rules, an adapted motion trajectory is selected. The adapted motion trajectory should ensure that the robot can reasonably avoid obstacles and move continuously during motion. The robot can reach the target position at a faster speed and reduce the The oscillation phenomenon of the robot during the movement improves the movement efficiency of the robot.
  • the robot After selecting the adapted motion trajectory, the robot can be controlled to move according to the adapted motion trajectory. In the process of the robot reaching the target position, each local trajectory of the global planning route is planned until the robot reaches the target position.
  • the motion state of the robot is acquired to obtain multiple motion state information; multiple motion trajectories are planned based on multiple motion state information and the target position of the robot; multiple motion trajectories are calculated based on at least one preset evaluation rule Evaluate and select an adapted motion trajectory; based on the adapted motion trajectory, control the robot to move.
  • the motion track of the robot can be planned according to the motion state information of the robot, and the efficiency of the motion of the robot can be improved.
  • Fig. 2 is a schematic flowchart of the second embodiment of the path planning method provided by the present application
  • Fig. 3 is a schematic diagram of obtaining multiple accelerations in Fig. 2
  • Fig. 4 is a schematic diagram of obtaining multiple variable accelerations in Fig. 2 schematic diagram.
  • the motion state information includes speed change parameters
  • step S11 further includes the following steps:
  • a parameter sampling space is constructed.
  • the sampling range of the speed change parameter may be limited.
  • the restriction condition may be but not limited to one or more of the speed limit of the robot, the motor torque limit of the robot, the obstacle avoidance limit of the robot, and the like.
  • the speed change parameter may be, but not limited to, acceleration and/or acceleration.
  • the acceleration sampling space may include acceleration a, acceleration-a and 0 three types of acceleration
  • the electronic device can sample the robot's acceleration, deceleration, and constant speed three types of motion states at each sampling time.
  • the acceleration can be but not limited to 1.
  • variable acceleration sampling space may include variable acceleration j , variable acceleration-j and 0 three kinds of variable acceleration
  • the electronic device can sample the motion states of the robot such as variable acceleration, uniform variable speed, and constant speed at each sampling time.
  • S22 Sampling is performed according to each preset sampling time in the parameter sampling space, and speed change parameters of multiple preset sampling periods are obtained.
  • samples of a plurality of speed change parameters are collected according to each preset sampling time, so as to obtain speed change parameters of a plurality of preset sampling periods.
  • the preset sampling time can be set according to the application scenario and daily movement conditions of the robot.
  • the path planning method of the present application is based on multiple speed change parameters sampled in the parameter sampling space to obtain the speed change status of the robot, and based on the speed change status to simulate the robot's motion trajectory in a period of time in the future, the obtained motion trajectory includes
  • the acceleration or deceleration motion of the robot is different from the uniform motion simulated in the prior art, which enriches the motion trajectory of the robot and improves the flexibility of the robot motion.
  • the path planning method further includes: converting the speed change parameters of multiple preset sampling periods into speed parameters of multiple preset sampling periods, based on the speed Parameters plan the motion trajectory.
  • speed change diagrams of multiple preset sampling periods may be drawn based on multiple accelerations, as shown in FIG. 3 .
  • the motion conditions of the robot on the partial route can be simulated to calculate the trajectory of the robot on the partial route.
  • the acceleration change diagrams of multiple preset sampling periods can be drawn correspondingly based on multiple variable accelerations, and then the speed change diagrams of multiple preset sampling periods can be drawn, as shown in Fig. 4.
  • the motion condition of the robot on the local route can be simulated to calculate the motion trajectory of the robot on the local route.
  • variable acceleration sampling can obtain a richer robot motion trajectory, and its motion trajectory includes not only the acceleration or deceleration of the robot, but also forward and backward movement. This enables the robot to move flexibly when facing sudden obstacles, and effectively improves the flexibility of the robot movement.
  • acceleration sampling or variable acceleration sampling can be selected according to the robot application scene and past motion conditions. When the robot application scene is complex, variable acceleration sampling can be performed. When the robot application scene is simple, in order to reduce During the calculation process, acceleration sampling can be performed.
  • FIG. 5 is a schematic flowchart of a third embodiment of the path planning method provided by the present application.
  • the preset evaluation rules include curvature evaluation rules
  • step S13 includes the following steps:
  • the multiple motion trajectories are evaluated based on the preset evaluation rules, so as to select the optimal motion trajectory that best matches the preset evaluation rules. Specifically, each motion trajectory is fitted to obtain an arc spline corresponding to the motion trajectory.
  • the track points of the motion track are mapped to the arc spline, and the curvature of each track point in the arc spline is calculated.
  • the curvature change rate is calculated based on the curvatures of the front and rear track points, and the maximum curvature and/or maximum curvature change rate of all track points are obtained.
  • S34 Evaluate multiple motion trajectories based on the maximum curvature and/or the maximum curvature change rate, and select the motion trajectory with the maximum curvature or the minimum maximum curvature change rate.
  • the maximum curvature of the motion trajectory is obtained to evaluate it, and the maximum curvature is used as the curvature cost parameter of the motion trajectory; in another embodiment, the maximum curvature change rate of the motion trajectory is obtained to evaluate it , taking the maximum rate of curvature change as the curvature cost parameter of the trajectory.
  • the motion trajectory with the smallest curvature cost parameter can be selected, that is, the motion trajectory with the largest curvature and/or the smallest maximum curvature change rate, so as to filter out relatively smooth trajectories among the multiple motion trajectories.
  • each motion trajectory is fitted to obtain the arc spline of the motion trajectory; the trajectory points of the motion trajectory are mapped to the arc spline, and each trajectory in the arc spline is calculated The curvature of the point; obtain the maximum curvature and/or maximum curvature change rate from the curvature of all track points; evaluate multiple motion trajectories based on the maximum curvature and/or maximum curvature change rate, and select the maximum curvature and/or maximum curvature change rate Minimal motion trajectories.
  • relatively smooth trajectories in the motion trajectories can be screened out by calculating the maximum curvature and/or the maximum curvature change rate of the motion trajectories, so as to improve the smoothness of the robot movement.
  • FIG. 6 is a schematic flowchart of a fourth embodiment of a path planning method provided by the present application.
  • the speed change parameter includes a variable speed
  • the preset sampling period includes a first sampling period and a second sampling period
  • the preset evaluation rule includes a speed evaluation rule
  • step S13 also includes the following steps:
  • each motion trajectory includes a plurality of preset sampling periods
  • the preset sampling period includes a first sampling period and a second sampling period
  • the first sampling period and the second sampling period are the front and rear sampling periods
  • the first sampling period is obtained The first variable acceleration of the second sampling period and the second variable acceleration of the second sampling period.
  • S42 Based on the first variable acceleration, the second variable acceleration, and a speed evaluation rule, output a speed cost parameter for each preset sampling period.
  • the speed evaluation rule is obtained, and when the first variable acceleration and the second variable acceleration match the speed evaluation rule, the speed cost parameter of each preset sampling period is output.
  • an average value of the speed cost parameters of all preset sampling periods is obtained as an average speed cost parameter of the motion trajectory.
  • the first variable acceleration of the first sampling period and the second variable acceleration of the second sampling period are obtained; based on the first variable acceleration, the second variable acceleration and the speed evaluation rule, each preset sampling period is output The speed cost parameter; based on the speed cost parameters of all preset sampling periods, the average speed cost parameter of the motion trajectory is obtained; multiple motion trajectories are evaluated based on the average speed cost parameter of the motion trajectory, and the motion trajectory with the smallest average speed cost parameter is selected .
  • the trajectory with relatively smooth speed change in the motion trajectory can be screened out by calculating the change of the variable acceleration in each preset sampling period in the motion trajectory, so as to further improve the smoothness of the robot movement.
  • the speed evaluation rule includes: in response to the first variable acceleration and the second variable acceleration being the first value, the speed cost parameter of the preset sampling period is the first value; in response to the first variable acceleration or the second variable acceleration being the first value A value, the speed cost parameter of the preset sampling period is the first speed cost parameter; in response to neither the first variable acceleration nor the second variable acceleration being the first value, the speed cost parameter of the preset sampling period is the first speed cost parameter , where the first speed cost parameter is smaller than the second speed cost parameter.
  • the first value can be but not limited to 0, the first speed cost parameter can be but not limited to 100, the second speed cost parameter can be but not limited to 200, and the user can set the first value according to the application scenario of the robot.
  • the value, the first speed cost parameter and the second speed cost parameter are adjusted accordingly, and the values of the first value, the first speed cost parameter and the second speed cost parameter are not specifically limited here.
  • the accelerations in the first sampling period and the second sampling period of the motion trajectory remain unchanged, that is, the robot may be in a state of uniform velocity or uniform acceleration.
  • the speed penalty parameter of the preset sampling period is 0.
  • the robot in the first sampling period or the second sampling period of the motion track is in the state of variable speed motion, that is, the robot may experience in the first sampling period and the second sampling period From acceleration to constant speed, from constant speed to acceleration, from deceleration to constant speed, and from constant speed to deceleration, at this time, the speed cost parameter of the preset sampling period is 100.
  • the robot in the first sampling period and the second sampling period of the motion track is in the variable speed motion state, that is, the robot may be in the first sampling period and the second sampling period.
  • the period goes through the process from acceleration to deceleration, and from deceleration to acceleration.
  • the speed cost parameter of the preset sampling period is 200.
  • the average speed cost parameters of the motion trajectory can be obtained, and the motion trajectory can be evaluated based on the average speed cost parameters of all motion trajectories to filter out relatively smooth speed changes. motion track.
  • FIG. 7 is a schematic flowchart of a fifth embodiment of the path planning method provided by the present application.
  • the preset evaluation rules include effective distance evaluation rules
  • step S13 also includes the following steps:
  • the multiple motion trajectories are evaluated based on the preset evaluation rules, so as to select the optimal motion trajectory that best matches the preset evaluation rules. Specifically, the straight-line distance between the starting position of the robot and the target position may be obtained.
  • the arc lengths of multiple motion trajectories are further obtained, and the difference between the arc lengths of multiple motion trajectories and the straight-line distance is calculated.
  • cost l is the distance cost parameter
  • lab is the straight-line distance between the starting position and the target position
  • dab is the arc length of the motion trajectory.
  • S54 Evaluate multiple motion trajectories based on the distance cost parameters of the motion trajectories, and select the motion trajectory with the smallest distance cost parameter.
  • multiple motion trajectories are evaluated to filter out trajectories with high motion efficiency.
  • the straight-line distance between the starting position of the robot and the target position is obtained; the arc length of the motion trajectory is obtained, and the difference between the arc length and the straight-line distance is calculated; the difference between the arc length and the straight-line distance and the arc length are calculated Ratio to get the distance cost parameter of the motion trajectory.
  • the trajectory with high movement efficiency can be selected out of the movement trajectory by calculating the arc length of the movement trajectory and the straight-line distance between the starting point position and the target position, so as to improve the efficiency of the robot movement.
  • the method for evaluating multiple motion trajectories of a robot can be a combination of the fourth embodiment, the fifth embodiment and the sixth embodiment of the path planning method of the present application, so as to screen out those with good ride comfort and high efficiency.
  • the motion track can also be any combination of the fourth embodiment, the fifth embodiment and the sixth embodiment of the present application.
  • FIG. 8 is a schematic flowchart of a sixth embodiment of a path planning method provided by the present application. As shown in Figure 8, the path planning method also includes the following steps:
  • S61 Obtain a motion map of the robot, and obtain location information of the robot.
  • S62 Plan a global motion path based on the motion map, location information, and target location.
  • the global motion path of the robot from the starting position to the target position can be planned.
  • S63 Establish a robot motion model based on the global motion path.
  • the robot motion model Based on the robot motion model, construct an acceleration sampling space or a variable acceleration sampling space and perform sampling, convert the collected acceleration or variable acceleration into a speed change map of the robot in a period of time in the future, and substitute the speed into the robot motion model for prediction. Simulation within the design time, and then plan multiple motion trajectories for each dynamic key point.
  • the motion trajectory adapted to the preset evaluation rules is obtained, which is the optimal motion trajectory of the dynamic key point, and the robot will be controlled to move according to the motion trajectory of the dynamic key point and proceed to the next dynamic Path planning of key points until the robot reaches the goal position.
  • the motion map of the robot is obtained, and the position information of the robot is obtained; based on the motion map, position information and target position, the global motion path is planned; based on the global motion path, the robot motion model is established; based on the robot motion model, Obtain the motion trajectory adapted to the preset evaluation rules, and control the robot to move.
  • the local movement trajectory of the robot can be planned by constructing an acceleration sampling space or a variable acceleration sampling space, which enriches the movement trajectory of the robot and improves the flexibility of the robot movement.
  • the path planning method is applied to an electronic device, and the electronic device can be installed in the robot or can be an external device.
  • the electronic device can be built into the robot.
  • the robot obtains the cleaning instruction, it obtains the indoor map and current location information, plans the global motion path and establishes a motion model, and constructs an acceleration sampling space or a variable acceleration sampling space for acceleration or cleaning. Sampling with variable acceleration, and simulating multiple sets of local motion trajectories with the sampled speed, selecting the appropriate local motion trajectories, and controlling the robot to move according to the planned local motion trajectories.
  • the electronic device can also be applied to other household robots, service robots, and other robots that need path planning, and the application scenarios of the electronic device are not specifically limited here.
  • Fig. 9 is a schematic structural diagram of the first embodiment of the electronic device provided by the present application
  • Fig. 10 is a schematic structural diagram of the second embodiment of the electronic device provided by the present application.
  • the electronic device includes a memory 52 and a processor 51 connected to each other.
  • the memory 52 is used to store program instructions for implementing the path planning method described in any one of the above embodiments.
  • the processor 51 is used to execute program instructions stored in the memory 52 .
  • the processor 51 may also be referred to as a CPU (Central Processing Unit, central processing unit).
  • the processor 51 may be an integrated circuit chip and has signaling processing capabilities.
  • the processor 51 can also be a general-purpose processor, a digital signaling processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP digital signaling processor
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate array
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the memory 52 can be a memory stick, a TF card, etc., and can store all information in the electronic device, including input raw data, computer programs, intermediate running results and final running results are all stored in the memory. It deposits and retrieves information according to the location specified by the controller. With the memory, the string matching prediction device has the memory function to ensure normal operation.
  • the memory of the string matching prediction device can be divided into main memory (internal memory) and auxiliary memory (external memory) according to the purpose of memory, and there is also a method of classification into external memory and internal memory. External storage is usually magnetic media or optical discs, which can store information for a long time.
  • Memory refers to the storage unit on the motherboard, which is used to store data and programs currently being executed, but it is only used to store programs and data temporarily, and the data will be lost when the power is turned off or cut off.
  • an electronic device including a sampling module 53 , a planning module 54 , an evaluation module 55 and a control module 56 .
  • the sampling module 53 is used to obtain the motion state of the robot, and obtains a plurality of motion state information according to the motion state of the robot;
  • the planning module 54 is used to plan a plurality of motion trajectories based on a plurality of motion state information and the target position of the robot;
  • the evaluation module 55 It is used for evaluating multiple motion trajectories based on at least one preset evaluation rule, and selecting an adapted motion trajectory;
  • the control module 56 is used for controlling the robot to move based on the adapted motion trajectory.
  • the disclosed methods and devices may be implemented in other ways.
  • the device implementations described above are only illustrative.
  • the division of modules or units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • a unit described as a separate component may or may not be physically separated, and a component shown as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
  • the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a system server, or a network device, etc.) or a processor (processor) execute all or part of the steps of the methods in various embodiments of the present application.
  • FIG. 11 is a schematic structural diagram of an embodiment of a computer-readable storage medium provided by the present application.
  • the computer-readable storage medium of the present application stores a program file 61 capable of realizing all the above-mentioned path planning methods, wherein the program file 61 can be stored in the above-mentioned storage medium in the form of a software product, including several instructions to make a computer A device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) executes all or part of the steps of the methods in various embodiments of the present application.
  • a device which may be a personal computer, a server, or a network device, etc.
  • processor processor
  • the aforementioned storage device includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc and other media that can store program codes. , or electronic devices such as computers, servers, mobile phones, and tablets.
  • a computer program product or computer program comprising computer instructions stored in a computer readable storage medium.
  • the processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the steps in the foregoing method embodiments.
  • the above-mentioned functions are implemented in the form of software functions and sold or used as independent products, they can be stored in a storage medium that can be read by a mobile terminal, that is, the application also provides a storage device that stores program data, so The above program data can be executed to implement the methods of the above embodiments, and the storage device can be, for example, a U disk, an optical disk, a server, and the like. That is to say, the present application may be embodied in the form of a software product, which includes several instructions for enabling an intelligent terminal to execute all or part of the steps of the method described in each embodiment.
  • first and second are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, features defined as “first” and “second” may explicitly or implicitly include at least one of these features. In the description of the present application, “plurality” means at least two, such as two, three, etc., unless otherwise specifically defined.
  • a "computer-readable medium” may be any device that can contain, store, communicate, propagate or transmit a program for use in or in conjunction with an instruction execution system, device or device.
  • computer-readable media include the following: electrical connection with one or more wires (electronic device), portable computer disk case (magnetic device), random access memory (RAM), Read Only Memory (ROM), Erasable and Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM).
  • the computer-readable medium may even be paper or other suitable medium on which the program can be printed, as it may be possible, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or other suitable processing if necessary.
  • the program is processed electronically and stored in computer memory.

Abstract

一种路径规划方法、电子设备、计算机程序产品及存储介质。该路径规划方法包括:获取机器人的运动状态,得到多个运动状态信息;基于多个运动状态信息和机器人的目标位置,规划多个运动轨迹;基于至少一个预设评估规则对多个运动轨迹进行评估,选择适配的运动轨迹;基于适配的运动轨迹,控制机器人进行运动。该方法可以根据机器人的运动状态信息规划机器人的运动轨迹,提高机器人运动的效率。

Description

路径规划方法、电子设备、计算机程序产品及存储介质
本申请要求于2022年01月10日提交的申请号为2022100240917,发明名称为“路径规划方法、电子设备、计算机程序产品及存储介质”的中国专利申请的优先权,其通过引用方式全部并入本申请。
【技术领域】
本申请涉及机器人技术领域,具体涉及一种路径规划方法、电子设备、计算机程序产品及存储介质。
【背景技术】
随着计算机、传感器和人工智能等技术的快速发展,机器人日趋完善,被广泛应用于家用服务、物流、探测、工业等领域中。其中,路径规划是机器人领域的关键技术之一,在面对环境未知的动态场景中,机器人需要在障碍物环境中寻找无障碍路径,以进行安全高效的移动行走。
【发明内容】
本申请提出了一种路径规划方法、电子设备、计算机程序产品及存储介质,以解决上述技术问题。
为解决上述技术问题,本申请采用的第一个技术方案是:提供一种路径规划方法,所述方法包括:获取所述机器人在不同位置的运动状态信息,得到多个运动状态信息;基于所述多个运动状态信息和所述机器人的目标位置,规划多个运动轨迹;基于至少一个预设评估规则对所述多个运动轨迹进行评估,选择适配的运动轨迹;基于所述适配的运动轨迹,控制机器人进行运动。
为解决上述技术问题,本申请采用的第二个技术方案是:提供一种电子设备,其中,包括采样模块、规划模块、评估模块和控制模块;所述采样模块用于获取机器人的运动状态,得到多个运动状态信息;所述规划模块用于基于所述多个运动状态信息和所述机器人的目标位置,规划多个运动轨迹;所述评估模块用于基于至少一个预设评估规则对所述多个运动轨迹进行评估,选择适配的运动轨迹;所述控制模块用于基于所述适配的运动轨迹,控制机器人进行运动。
为解决上述技术问题,本申请采用的第三个技术方案是:提供一种电子设备,所述电子设备包括处理器、与所述处理器连接的存储器,其中,所述存储器存储有程序指令;所述处理器用于执行所述存储器存储的程序指令以实现如上所述的路径规划方法。
为解决上述技术问题,本申请采用的第四个技术方案是:提供一种计算机程序产品,包括计算机程序指令,所述计算机程序指令使计算机实现如上所述的路径规划方法。
为解决上述技术问题,本申请采用的第五个技术方案是:提供一种计算机可读存储介质,所述计算机可读存储介质存储有程序指令,所述程序指令被执行时实现如上所述的路径规划方法。
本申请提出了一种路径规划方法、电子设备、计算机程序产品及存储介质,该路径规划方法通过获取机器人在不同位置的运动状态信息,得到多个运动状态信息;基于多个运动状态信息和机器人的目标位置,规划多个运动轨迹;基于预设评估规则对多个运动轨迹进行评估,选择适配的运动轨迹;基于适配的运动轨迹,控制机器人进行运动。通过本申请的方法,可以根据机器人的运动状态信息对机器人的运动轨迹进行规划,并且根据多个预设评估规则对运动轨迹进行评估以选择出最适配的运动轨迹,能有效提高机器人运动的效率。
【附图说明】
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。其中:
图1是本申请提供的路径规划方法第一实施例的流程示意图;
图2是本申请提供的路径规划方法第二实施例的流程示意图;
图3是图2中获取多个加速度的示意图;
图4是本申请提供的路径规划方法第三实施例的流程示意图;
图5是图4中获取多个变加速度的示意图;
图6是本申请提供的路径规划方法第四实施例的流程示意图;
图7是本申请提供的路径规划方法第五实施例的流程示意图;
图8是本申请提供的路径规划方法第六实施例的流程示意图;
图9是本申请提供的路径规划方法第七实施例的流程示意图;
图10是本申请提供的电子设备一实施例的结构示意图;
图11是本申请提供的计算机可读存储介质一实施例的结构示意图。
【具体实施方式】
为使本申请的上述目的、特征和优点能够更为明显易懂,下面结合附图,对本申请的具体实施方式做详细的说明。可以理解的是,此处所描述的具体实施例仅用于解释本申请,而非对本申请的限定。另外还需要说明的是,为了便于描述,附图中仅示出了与本申请相关的部分而非全部结构。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例,都属于本申请保护的范围。
本申请中的术语“第一”、“第二”等是用于区别不同对象,而不是用于描述特定顺序。此外,术语“包括”和“设置有”以及它们任何变形,意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元,而是可选地还包括没有列出的步骤或单元,或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本文中提及“实施例”意味着,结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例,也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是,本文所描述的实施例可以与其它实施例相结合。
动态窗口法(Dynamic Window Approach,DWA)是一种局部轨迹规划算法,DWA算法通过采集多组速度,并模拟机器人在未来一段时间内进行匀速运动所产生的运动轨迹,以获取最优运动轨迹对机器人的局部轨迹进行规划。
经发明人研究发现,在使用DWA算法对机器人进行路径规划时,由于在预测机器人的运动轨迹时采用了匀速运动模型,忽略了机器人处于加速或减速运动的可能,使得预测的运动轨迹不能更加全面地表达机器人未来的运动状态,限制了DWA算法的进一步应用。
请参见图1,图1是本申请提供的路径规划方法第一实施例的流程示意图。其中,本申请实施例所述的路径规划方法应用于一种电子设备,本申请的电子设备可以为服务器,也可以为由服务器和电子设备相互配合的系统;该电子设备还可以设置于机器人内,以对机器人的运动轨迹进行规划。
如图1所示,本申请的机器人的路径规划方法可应用于一种电子设备中,该路径规划方法具体包括以下步骤:
S11:获取机器人的运动状态,得到多个运动状态信息。
具体的,在本申请实施例中,获取机器人的运动状态,以获得机器人的历史运动状态和/或当前运动状态,基于机器人的历史运动状态和/或当前运动状态,获取机器人的多个运动状态信息,其中,运动状态信息为机器人在未来一段时间内可能存在的运动状态信息。该运动状态信息包括但不限于机器人的位置信息、速度信息、速度变化信息、采样时间等,其中,速度信息包括但不限于线速度和/或角速度等。
S12:基于多个运动状态信息和机器人的目标位置,规划多个运动轨迹。
获取电子地图,以根据机器人的当前位置和目标位置确定机器人的全局规划路线;获取机器人的多个运动状态信息后,可对机器人的运动状态进行预测,对机器人在全局规划路线上的局部位置的运动轨迹进行规划,获得多个规划的运动轨迹。
可选的,可在电子设备中设置仿真时间,仿真时间为规划运动轨迹的时间,仿真时间可以根据机器人的应用场景做调整,若仿真时间太长易导致规划的运动轨迹偏离全局规划路线,若仿真时间太短易导致频繁规划路径而引起机器人震荡。
S13:基于至少一个预设评估规则对多个运动轨迹进行评估,选择适配的运动轨迹。
在获得多个规划的运动轨迹后,基于预设评估规则对多个运动轨迹进行评估,以选择出与预设评估规则适配的运动轨迹。
具体的,预设评估规则可以包括方位角评价函数、全局规划路线贴合程度、权重参数等,方位角评价函数用于评价运动轨迹的是否朝向目标位置,全局规划路线贴合程度用于限制机器人运动轨迹于全局规划路线的贴合程度,权重参数用于控制机器人的速度;预设评估规则还可以包括运动轨迹上是否存在障碍物、运动轨迹与障碍物的距离等规则,在此对预设评估规则不做具体限定。基于预设评估规则,选择出适配的运动轨迹,该适配的运动轨迹应能保证机器人在运动时能够合理避障、连续运动,机器人能以较快速度到达目标位置,并尽可能地减少机器人在运动过程中的震荡现象,提高机器人的运动效率。
S14:基于适配的运动轨迹,控制机器人进行运动。
在选择适配的运动轨迹后,可以控制机器人按照适配的运动轨迹进行运动。在机器人达到目标位置的过程中,对全局规划路线的每个局部的运动轨迹进行规划,直至机器人到达目标位置。
在本申请实施例中,获取机器人的运动状态,得到多个运动状态信息;基于多个运动状态信息和机器人的目标位置,规划多个运动轨迹;基于至 少一个预设评估规则对多个运动轨迹进行评估,选择适配的运动轨迹;基于适配的运动轨迹,控制机器人进行运动。通过本实施例的方法,可以根据机器人的运动状态信息规划机器人的运动轨迹,提高机器人运动的效率。
请参见图2-4,图2是本申请提供的路径规划方法第二实施例的流程示意图,图3是图2中获取多个加速度的示意图,图4是图2中获取多个变加速度的示意图。如图2所示,运动状态信息包括速度变化参数,步骤S11进一步包括以下步骤:
S21:构建参数采样空间。
获取机器人在未来一段时间的多个速度变化参数后,构建参数采样空间。可选的,为了提高机器人运动的可行性,可以对速度变化参数的采样范围进行限制。限制条件可以但不局限于机器人的速度限制、机器人的电机力矩限制、机器人的避障限制等中的一种或多种。
可选地,该速度变化参数可以但不局限于加速度和/或变加速度。
在一实施方式中,速度变化参数为加速度、参数采样空间为加速度采样空间时,为了减少电子设备的采样工作量,提高电子设备的采样效率,加速度采样空间中可以包括加速度a,加速度-a和0三种加速度,电子设备可在每个采样时间对机器人的加速、减速、和匀速三类运动状态进行采样。具体的,为了避免机器人加速度过大导致的避障困难,加速度可以但不局限于1。
在另一实施方式中,速度变化参数为变加速度、参数采样空间为变加速度采样空间时,为了减少电子设备的采样工作量,提高电子设备的采样效率,变加速度采样空间中可以包括变加速度j,变加速度-j和0三种变加速度,电子设备可在每个采样时间对机器人的变加速、匀变速、和匀速等运动状态进行采样。
S22:在参数采样空间内按照每个预设采样时间进行采样,获取多个预设采样周期的速度变化参数。
在构建的参数采样空间内,按照每个预设采样时间采集多个速度变化参数的样本,以获取多个预设采样周期的速度变化参数。预设采样时间可根据机器人的应用场景、日常运动状况进行设置。
在本申请实施例中,通过构建参数采样空间;在参数采样空间内按照每个预设采样时间进行采样,获取多个预设采样周期的速度变化参数。本申请的路径规划方法基于在参数采样空间采样得到的多个速度变化参数以获取机器人的速度变化状况,并基于速度变化状况模拟机器人在未来一段时间内的运动轨迹,所获得的运动轨迹包含了机器人的加速或减速运动,区别于现有技术模拟的匀速运动,丰富了机器人的运动轨迹,提高机器人 运动的灵活性。
可选地,在获取多个预设采样周期的速度变化参数后,该路径规划方法还包括:将多个预设采样周期的速度变化参数转化为多个预设采样周期的速度参数,基于速度参数规划所述运动轨迹。
具体的,在一实施方式中,速度变化参数为加速度时,可基于多个加速度绘制多个预设采样周期的速度变化图,如图3所示。根据电子设备获取的多个预设采样周期的速度变化图,可对机器人在该局部路线上的运动状况进行仿真模拟,以推算机器人在该局部路线上的运动轨迹。
在另一实施方式中,速度变化参数为变加速度时,可基于多个变加速度相应地绘制多个预设采样周期的加速度变化图,进而绘制多个预设采样周期的速度变化图,如图4所示。根据获取的多个预设采样周期的速度变化图,可对机器人在该局部路线上的运动状况进行仿真模拟,以推算机器人在该局部路线上的运动轨迹。
如图5所示的速度变化图,与进行加速度采样相比,进行变加速度采样可以获得更丰富的机器人运动轨迹,其运动轨迹不仅包含了机器人的加速或减速运动,还包含了前进和后退,使得机器人能在面对突发障碍时能够灵活运动,有效提高了机器人运动的灵活性。在具体的实施方式中,可根据机器人应用场景和以往的运动状况选择进行加速度采样或变加速度采样,当机器人的应用场景复杂时,可进行变加速度采样,当机器人的应用场景简单时,为了减少计算过程,可进行加速度采样。
请参见图5,图5是本申请提供的路径规划方法第三实施例的流程示意图。如图5所示,预设评估规则包括曲率评估规则,步骤S13包括以下步骤:
S31:对每个运动轨迹进行拟合,获取运动轨迹的圆弧样条。
获取多个运动轨迹后,基于预设评估规则对多个运动轨迹进行评估,以选择出与预设评估规则最为适配的最优的运动轨迹。具体的,对每个运动轨迹进行拟合,以获得与该运动轨迹对应的圆弧样条。
S32:将运动轨迹的轨迹点映射到圆弧样条内,计算在圆弧样条内的每个轨迹点的曲率。
获取圆弧样条后,将该运动轨迹的轨迹点映射到圆弧样条内,并计算在圆弧样条内的每个轨迹点的曲率。
S33:从所有的轨迹点的曲率获取最大曲率和/或最大曲率变化率。
获取该运动轨迹对应的所有轨迹点的曲率后,基于前后轨迹点的曲率计算曲率变化率,并获取所有轨迹点的最大曲率和/或最大曲率变化率。
S34:基于最大曲率和/或最大曲率变化率对多个运动轨迹进行评估,选 择最大曲率或最大曲率变化率最小的运动轨迹。
在一实施方式中,获取该运动轨迹的最大曲率对其进行评估,将最大曲率作为该运动轨迹的曲率代价参数;在另一实施方式中,获取该运动轨迹的最大曲率变化率对其进行评估,将最大曲率变化率作为该运动轨迹的曲率代价参数。
获取多个运动轨迹的曲率代价参数后,可选择出曲率代价参数最小的运动轨迹,即最大曲率和/或最大曲率变化率最小的运动轨迹,以筛选出多个运动轨迹中相对平顺的轨迹。
在本申请实施例中,对每个运动轨迹进行拟合,获取运动轨迹的圆弧样条;将运动轨迹的轨迹点映射到圆弧样条内,计算在圆弧样条内的每个轨迹点的曲率;从所有的轨迹点的曲率获取最大曲率和/或最大曲率变化率;基于最大曲率和/或最大曲率变化率对多个运动轨迹进行评估,选择最大曲率和/或最大曲率变化率最小的运动轨迹。通过本实施例的方法,可以通过计算运动轨迹的最大曲率和/或最大曲率变化率将运动轨迹中相对平顺的轨迹筛选出来,提高机器人运动的平顺性。
请参见图6,图6是本申请提供的路径规划方法第四实施例的流程示意图。如图6所示,所述速度变化参数包括变加速度,预设采样周期包括第一采样周期和第二采样周期,所述预设评估规则包括速度评估规则,步骤S13还包括以下步骤:
S41:获取第一采样周期的第一变加速度及第二采样周期的第二变加速度。
具体的,每个运动轨迹包括有多个预设采样周期,预设采样周期包括第一采样周期和第二采样周期,第一采样周期和第二采样周期为前后采样周期,获取第一采样周期的第一变加速度及第二采样周期的第二变加速度。
S42:基于第一变加速度、第二变加速度和速度评估规则,输出每个预设采样周期的速度代价参数。
获取第一变加速度和第二变加速度后,获取速度评估规则,当第一变加速度和第二变加速度与速度评估规则匹配时,输出每个预设采样周期的速度代价参数。
S43:基于所有预设采样周期的速度代价参数,获取运动轨迹的平均速度代价参数。
基于该运动轨迹的所有预设采样周期的速度代价参数,获取所有预设采样周期的速度代价参数的平均值,作为该运动轨迹的平均速度代价参数。
S44:基于运动轨迹的平均速度代价参数对多个运动轨迹进行评估,选择平均速度代价参数最小的运动轨迹。
获取多个运动轨迹的平均速度代价参数,对多个运动轨迹进行评估,选择平均速度代价参数最小的运动轨迹,以筛选出多个运动轨迹中速度变化相对平顺的轨迹。
在本申请实施例中,获取第一采样周期的第一变加速度及第二采样周期的第二变加速度;基于第一变加速度、第二变加速度和速度评估规则,输出每个预设采样周期的速度代价参数;基于所有预设采样周期的速度代价参数,获取运动轨迹的平均速度代价参数;基于运动轨迹的平均速度代价参数对多个运动轨迹进行评估,选择平均速度代价参数最小的运动轨迹。通过本实施例的方法,可以通过计算运动轨迹中每个预设采样周期的变加速度变化情况将运动轨迹中速度变化相对平顺的轨迹筛选出来,进一步提高机器人运动的平顺性。
进一步地,速度评估规则包括:响应于第一变加速度和第二变加速度为第一数值,预设采样周期的速度代价参数为第一数值;响应于第一变加速度或第二变加速度为第一数值,预设采样周期的速度代价参数为第一速度代价参数;响应于第一变加速度和第二变加速度均不为第一数值,预设采样周期的速度代价参数为第一速度代价参数,其中,第一速度代价参数小于第二速度代价参数。
在本实施例中,第一数值可以但不局限于0,第一速度代价参数可以但不局限于100,第二速度代价参数可以但不局限于200,用户可根据机器人的应用场景对第一数值、第一速度代价参数和第二速度代价参数作相应调整,在此对第一数值、第一速度代价参数和第二速度代价参数的数值不做具体限定。
具体的,当第一变加速度和第二变加速度为0时,则该运动轨迹的第一采样周期和第二采样周期内的加速度不变,即机器人可能处于匀速或匀加速运动状态,此时,该预设采样周期的速度代价参数为0。
当第一变加速度或第二变加速度为0时,则该运动轨迹的第一采样周期或第二采样周期的机器人处于变速运动状态,即机器人可能在第一采样周期和第二采样周期中经历从加速到匀速、从匀速到加速、从减速到匀速、从匀速到减速的过程,此时,该预设采样周期的速度代价参数为100。
当第一变加速度和第二变加速度均不为0时,则该运动轨迹的第一采样周期和第二采样周期的机器人均处于变速运动状态,即机器人可能在第一采样周期和第二采样周期中经历从加速到减速、从减速到加速的过程,此时该预设采样周期的速度代价参数为200。
获取该运动轨迹每个预设采样周期的速度代价参数后,可获取该运动轨迹的平均速度代价参数,并基于所有运动轨迹的平均速度代价参数对运 动轨迹进行评估,以筛选出速度变化相对平顺的运动轨迹。
请参见图7,图7是本申请提供的路径规划方法第五实施例的流程示意图。如图7所示,预设评估规则包括有效距离评估规则,步骤S13还包括以下步骤:
S51:获取机器人的起点位置和目标位置的直线距离。
获取多个运动轨迹后,基于预设评估规则对多个运动轨迹进行评估,以选择出与预设评估规则最为适配的最优的运动轨迹。具体的,可获取机器人的起点位置和目标位置的直线距离。
S52:获取运动轨迹的弧长,并计算弧长和直线距离的差值。
获取机器人的直线距离后,进一步获取多个运动轨迹的弧长,并计算多个运动轨迹的弧长与直线距离的差值。
S53:计算弧长和直线距离的差值与弧长的比值,以获取运动轨迹的距离代价参数。
计算多个运动轨迹的弧长和直线距离的差值与弧长的比值,并将比值作为多个运动轨迹的距离代价参数,如下式所示:
Figure PCTCN2022117288-appb-000001
其中,cost l为距离代价参数,l ab为起点位置和目标位置的直线距离,d ab为运动轨迹的弧长。
S54:基于运动轨迹的距离代价参数对多个运动轨迹进行评估,选择距离代价参数最小的运动轨迹。
基于获取的多个运动轨迹的距离代价参数,对多个运动轨迹进行评估,以筛选出具有高运动效率的轨迹。
在本申请实施例中,获取机器人的起点位置和目标位置的直线距离;获取运动轨迹的弧长,并计算弧长和直线距离的差值;计算弧长和直线距离的差值与弧长的比值,以获取运动轨迹的距离代价参数。通过本实施例的方法,可以通过计算运动轨迹的弧长和起点位置与目标位置的直线距离将运动轨迹中运动效率高的轨迹筛选出来,提高机器人运动的效率。
可选地,对机器人的多个运动轨迹进行评估的方法可以是本申请路径规划方法的第四实施例、第五实施例和第六实施例的结合,以筛选出平顺性好、效率高的运动轨迹,还可以是本申请第四实施例、第五实施例和第六实施例中的任意组合。
请参见图8,图8是本申请提供的路径规划方法第六实施例的流程示意图。如图8所示,该路径规划方法还包括以下步骤:
S61:获取机器人的运动地图,以及获取机器人的位置信息。
具体的,在对机器人进行路径规划时,需获取机器人的运动地图,运动地图中应包含有若干障碍物的位置信息;还需获取机器人的尺寸大小和机器人当前的位置信息。
S62:基于运动地图、位置信息和目标位置,规划全局运动路径。
基于获取的运动地图、位置信息和目标位置,可规划出机器人从起点位置到目标位置的全局运动路径。
S63:基于全局运动路径,建立机器人运动模型。
基于获取的全局运动路径,以机器人当前位置为中心,提取出全局运动路径中的若干个动态关键点,并建立机器人运动模型。获取机器人运动模型后,对若干个动态关键点进行若干次局部的路径规划。
S64:基于机器人运动模型,获取与预设评估规则适配的运动轨迹,并控制机器人进行运动。
基于机器人运动模型,构建加速度采样空间或变加速度采样空间并进行采样,将采集到的加速度或变加速度转化成机器人在未来一段时间内的速度变化图,将速度代入至机器人运动模型中,进行预设时间内的仿真模拟,进而规划出每个动态关键点的多个运动轨迹。根据预设评估规则,获取与预设评估规则适配的运动轨迹,即为该动态关键点的最优的运动轨迹,将控制机器人按照该动态关键点的运动轨迹进行运动,并进行下一动态关键点的路径规划,直到机器人到达目标位置。
在本申请实施例中,获取机器人的运动地图,以及获取机器人的位置信息;基于运动地图、位置信息和目标位置,规划全局运动路径;基于全局运动路径,建立机器人运动模型;基于机器人运动模型,获取与预设评估规则适配的运动轨迹,并控制机器人进行运动。通过本实施例的方法,可以通过构建加速度采样空间或变加速度采样空间对机器人局部的运动轨迹进行规划,丰富了机器人的运动轨迹,提高机器人运动的灵活性。
具体的,该路径规划方法应用于电子设备中,该电子设备可以设置于机器人内,也可以为外置设备。可选地,该电子设备可以内置于机器人中,当机器人获取到清洁指令时,获取室内地图和当前位置信息,规划全局运动路径并建立运动模型,构建加速度采样空间或变加速度采样空间进行加速度或变加速度采样,并将采样得到的速度模拟多组局部运动轨迹,选择出适配的局部运动轨迹,并控制机器人按照规划的局部运动轨迹进行运动。该电子设备还可以应用于其他家用机器人、服务机器人等需要进行路径规划的机器人,在此对电子设备的应用场景不做具体限定。
请参见图9-10,图9是本申请提供的电子设备第一实施例的结构示意 图,图10是本申请提供的电子设备第二实施例的结构示意图。如图9所示,电子设备包括相互连接的存储器52和处理器51。
存储器52用于存储实现上述任意一实施例所述的路径规划方法的程序指令。
处理器51用于执行存储器52存储的程序指令。
其中,处理器51还可以称为CPU(Central Processing Unit,中央处理单元)。处理器51可能是一种集成电路芯片,具有信令的处理能力。处理器51还可以是通用处理器、数字信令处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
存储器52可以为内存条、TF卡等,可以存储电子设备中全部信息,包括输入的原始数据、计算机程序、中间运行结果和最终运行结果都保存在存储器中。它根据控制器指定的位置存入和取出信息。有了存储器,串匹配预测装置才有记忆功能,才能保证正常工作。串匹配预测装置的存储器按用途存储器可分为主存储器(内存)和辅助存储器(外存),也有分为外部存储器和内部存储器的分类方法。外存通常是磁性介质或光盘等,能长期保存信息。内存指主板上的存储部件,用来存放当前正在执行的数据和程序,但仅用于暂时存放程序和数据,关闭电源或断电,数据会丢失。
如图10所示,在一个实施例中,提供了一种电子设备,包括采样模块53、规划模块54、评估模块55和控制模块56。采样模块53用于获取机器人的运动状态,并根据机器人的运动状态得到多个运动状态信息;规划模块54用于基于多个运动状态信息和机器人的目标位置,规划多个运动轨迹;评估模块55用于基于至少一个预设评估规则对多个运动轨迹进行评估,选择适配的运动轨迹;控制模块56用于基于适配的运动轨迹,控制机器人进行运动。
在本申请所提供的几个实施例中,应该理解到,所揭露的方法和装置,可以通过其它的方式实现。例如,以上所描述的设备实施方式仅仅是示意性的,例如,模块或单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方, 或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施方式方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或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中,包括若干指令用以使得一台计算机设备(可以是个人计算机,系统服务器,或者网络设备等)或处理器(processor)执行本申请各个实施方式方法的全部或部分步骤。
请参阅图11,图11是本申请提供的计算机可读存储介质一实施例的结构示意图。本申请的计算机可读存储介质存储有能够实现上述所有路径规划方法的程序文件61,其中,该程序文件61可以以软件产品的形式存储在上述存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)或处理器(processor)执行本申请各个实施方式方法的全部或部分步骤。而前述的存储装置包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质,或者是计算机、服务器、手机、平板等电子设备。
在一个实施例中,提供了一种计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该计算机设备执行上述各方法实施例中的步骤。
另外,上述功能如果以软件功能的形式实现并作为独立产品销售或使用时,可存储在一个移动终端可读取存储介质中,即,本申请还提供一种存储有程序数据的存储装置,所述程序数据能够被执行以实现上述实施例的方法,该存储装置可以为如U盘、光盘、服务器等。也就是说,本申请可以以软件产品的形式体现出来,其包括若干指令用以使得一台智能终端执行各个实施例所述方法的全部或部分步骤。
此外,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第 一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本申请的描述中,“多个”的含义是至少两个,例如两个,三个等,除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为,表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的机构、片段或部分,并且本申请的优选实施方式的范围包括另外的实现,其中可以不按所示出或讨论的顺序,包括根据所涉及的功能按基本同时的方式或按相反的顺序,来执行功能,这应被本申请的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤,例如,可以被认为是用于实现逻辑功能的可执行指令的定序列表,可以具体实现在任何计算机可读介质中,以供指令执行系统、装置或设备(可以是个人计算机,服务器,网络设备或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用,或结合这些指令执行系统、装置或设备而使用。就本说明书而言,"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下:具有一个或多个布线的电连接部(电子装置),便携式计算机盘盒(磁装置),随机存取存储器(RAM),只读存储器(ROM),可擦除可编辑只读存储器(EPROM或闪速存储器),光纤装置,以及便携式光盘只读存储器(CDROM)。另外,计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质,因为可以例如通过对纸或其他介质进行光学扫描,接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序,然后将其存储在计算机存储器中。
以上所述仅为本申请的实施方式,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (12)

  1. 一种机器人的路径规划方法,其中,所述方法包括:
    获取所述机器人的运动状态,得到多个运动状态信息;
    基于所述多个运动状态信息和所述机器人的目标位置,规划多个运动轨迹;
    基于至少一个预设评估规则对所述多个运动轨迹进行评估,选择适配的运动轨迹;
    基于所述适配的运动轨迹,控制机器人进行运动。
  2. 根据权利要求1所述的路径规划方法,其中,
    所述运动状态信息包括速度变化参数,所述获取所述机器人的运动状态,得到多个所述运动状态信息包括:
    构建参数采样空间;
    在所述参数采样空间内按照每个预设采样时间进行采样,获取多个预设采样周期的所述速度变化参数。
  3. 根据权利要求2所述的路径规划方法,其中,所述获取多个预设采样周期的所述速度变化参数后,包括:
    将所述多个预设采样周期的速度变化参数转化为所述多个预设采样周期的速度参数,基于所述速度参数规划所述运动轨迹。
  4. 根据权利要求3所述的路径规划方法,其中,所述预设评估规则包括曲率评估规则;
    所述基于至少一个预设评估规则对所述多个运动轨迹进行评估,选择适配的运动轨迹包括:
    对每个所述运动轨迹进行拟合,获取所述运动轨迹的圆弧样条;
    将所述运动轨迹的轨迹点映射到所述圆弧样条内,计算在所述圆弧样条内的每个轨迹点的曲率;
    从所有的所述轨迹点的曲率获取最大曲率和/或最大曲率变化率;
    基于所述最大曲率和/或最大曲率变化率对所述多个运动轨迹进行评估,选择最大曲率和/或最大曲率变化率最小的运动轨迹。
  5. 根据权利要求3所述的路径规划方法,其中,所述速度变化参数包括变加速度,所述预设采样周期包括第一采样周期和第二采样周期,所述预设评估规则包括速度评估规则;
    所述基于至少一个预设评估规则对所述多个运动轨迹进行评估,选择适配的运动轨迹包括:
    获取所述第一采样周期的第一变加速度及所述第二采样周期的第二变加速度;
    基于所述第一变加速度、所述第二变加速度和所述速度评估规则,输出每个所述预设采样周期的速度代价参数;
    基于所有所述预设采样周期的速度代价参数,获取所述运动轨迹的平均速度代价参数;
    基于所述运动轨迹的平均速度代价参数对所述多个运动轨迹进行评估,选择平均速度代价参数最小的运动轨迹。
  6. 根据权利要求5所述的路径规划方法,其中,
    所述速度评估规则包括:
    响应于所述第一变加速度和所述第二变加速度为第一数值,所述预设采样周期的速度代价参数为第一数值;
    响应于所述第一变加速度或所述第二变加速度为第一数值,所述预设采样周期的速度代价参数为第一速度代价参数;
    响应于所述第一变加速度和所述第二变加速度均不为第一数值,所述预设采样周期的速度代价参数为第二速度代价参数,其中,所述第一速度代价参数小于所述第二速度代价参数。
  7. 根据权利要求3所述的路径规划方法,其中,所述预设评估规则包括有效距离评估规则;
    所述基于至少一个预设评估规则对所述多个运动轨迹进行评估,选择适配的运动轨迹包括:
    获取所述机器人的起点位置和所述目标位置的直线距离;
    获取所述运动轨迹的弧长,并计算所述弧长和所述直线距离的差值;
    计算所述弧长和所述直线距离的差值与所述弧长的比值,以获取所述运动轨迹的距离代价参数;
    基于所述运动轨迹的距离代价参数对所述多个运动轨迹进行评估,选择距离代价参数最小的运动轨迹。
  8. 根据权利要求1至7中任一项所述的路径规划方法,其中,所述路径规划方法还包括:
    获取所述机器人的运动地图,以及获取所述机器人的位置信息;
    基于所述运动地图、所述位置信息和所述目标位置,规划全局运动路径;
    基于所述全局运动路径,建立机器人运动模型;
    基于所述机器人运动模型,获取与所述预设评估规则适配的运动轨迹,并控制机器人进行运动。
  9. 一种电子设备,其中,包括:
    采样模块,用于获取机器人的运动状态,得到多个运动状态信息;
    规划模块,用于基于所述多个运动状态信息和所述机器人的目标位置,规划多个运动轨迹;
    评估模块,用于基于至少一个预设评估规则对所述多个运动轨迹进行评估,选择适配的运动轨迹;
    控制模块,用于基于所述适配的运动轨迹,控制机器人进行运动。
  10. 一种电子设备,其中,所述电子设备包括处理器、与所述处理器连接的存储器,其中,
    所述存储器存储有程序指令;
    所述处理器用于执行所述存储器存储的程序指令以实现权利要求1~8任一项所述的路径规划方法。
  11. 一种计算机程序产品,其中,包括计算机程序指令,所述计算机程序指令使计算机实现权利要求1~8任一项所述的路径规划方法。
  12. 一种计算机可读存储介质,其中,所述计算机可读存储介质存储有程序指令,所述程序指令被执行时实现权利要求1~8任一项所述的路径规划方法。
PCT/CN2022/117288 2022-01-10 2022-09-06 路径规划方法、电子设备、计算机程序产品及存储介质 WO2023130755A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210024091.7A CN114578808A (zh) 2022-01-10 2022-01-10 路径规划方法、电子设备、计算机程序产品及存储介质
CN202210024091.7 2022-01-10

Publications (1)

Publication Number Publication Date
WO2023130755A1 true WO2023130755A1 (zh) 2023-07-13

Family

ID=81769702

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/117288 WO2023130755A1 (zh) 2022-01-10 2022-09-06 路径规划方法、电子设备、计算机程序产品及存储介质

Country Status (2)

Country Link
CN (1) CN114578808A (zh)
WO (1) WO2023130755A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114578808A (zh) * 2022-01-10 2022-06-03 美的集团(上海)有限公司 路径规划方法、电子设备、计算机程序产品及存储介质
CN114995464B (zh) * 2022-07-19 2022-11-25 佛山市星曼信息科技有限公司 局部路径规划的控制方法及装置、机器人、存储介质
CN115328211B (zh) * 2022-10-17 2022-12-27 复亚智能科技(太仓)有限公司 一种无人机局部路径规划方法

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109343528A (zh) * 2018-10-30 2019-02-15 杭州电子科技大学 一种节能的无人机路径规划避障方法
CN109491376A (zh) * 2017-09-11 2019-03-19 百度(美国)有限责任公司 用于自动驾驶车辆的基于动态规划和梯度下降的决策和规划
CN110488843A (zh) * 2019-09-04 2019-11-22 深圳前海达闼云端智能科技有限公司 避障方法、移动机器人及计算机可读存储介质
US20200159225A1 (en) * 2018-11-16 2020-05-21 Uber Technologies, Inc. End-To-End Interpretable Motion Planner for Autonomous Vehicles
CN112325884A (zh) * 2020-10-29 2021-02-05 广西科技大学 一种基于dwa的ros机器人局部路径规划方法
CN112486183A (zh) * 2020-12-09 2021-03-12 上海机器人产业技术研究院有限公司 一种室内移动机器人的路径规划算法
CN113359721A (zh) * 2021-05-31 2021-09-07 西安交通大学 一种结合运动控制的改进a*的agv路径规划方法
CN113741486A (zh) * 2021-11-05 2021-12-03 中国科学院自动化研究所 基于多约束的空间机器人智能运动规划方法及系统
CN114578808A (zh) * 2022-01-10 2022-06-03 美的集团(上海)有限公司 路径规划方法、电子设备、计算机程序产品及存储介质

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100580592C (zh) * 2006-12-29 2010-01-13 中国科学院沈阳计算技术研究所有限公司 一种基于滤波技术的数控系统加减速控制方法
JP6247965B2 (ja) * 2014-03-12 2017-12-13 ファスフォードテクノロジ株式会社 半導体製造方法及びダイボンダ
CN109885891B (zh) * 2019-01-24 2022-09-30 中国科学院合肥物质科学研究院 一种智能车gpu并行加速轨迹规划方法
CN111752254A (zh) * 2019-03-28 2020-10-09 深圳市商汤科技有限公司 轨迹跟踪控制器的测试方法、装置、介质及设备
CN110703797B (zh) * 2019-10-21 2021-12-28 深圳市道通智能航空技术股份有限公司 无人机及其飞行轨迹的生成方法、计算机可读存储介质
CN111352416A (zh) * 2019-12-29 2020-06-30 的卢技术有限公司 一种基于运动模型的动态窗口局部轨迹规划方法及系统
CN111523643B (zh) * 2020-04-10 2024-01-05 商汤集团有限公司 轨迹预测方法、装置、设备及存储介质
CN112810630B (zh) * 2021-02-05 2022-03-04 山东大学 一种自动驾驶车辆轨迹规划方法及系统
CN113031525B (zh) * 2021-03-03 2022-06-21 福州大学 一种应用于数控加工的多项式加减速运动控制方法及设备
CN113386766B (zh) * 2021-06-17 2022-09-23 东风汽车集团股份有限公司 一种连续的、周期自适应同步的在线轨迹规划系统及方法
CN113386795B (zh) * 2021-07-05 2022-07-01 西安电子科技大学芜湖研究院 一种自动驾驶车辆智能决策及局部轨迹规划方法及其决策系统

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109491376A (zh) * 2017-09-11 2019-03-19 百度(美国)有限责任公司 用于自动驾驶车辆的基于动态规划和梯度下降的决策和规划
CN109343528A (zh) * 2018-10-30 2019-02-15 杭州电子科技大学 一种节能的无人机路径规划避障方法
US20200159225A1 (en) * 2018-11-16 2020-05-21 Uber Technologies, Inc. End-To-End Interpretable Motion Planner for Autonomous Vehicles
CN110488843A (zh) * 2019-09-04 2019-11-22 深圳前海达闼云端智能科技有限公司 避障方法、移动机器人及计算机可读存储介质
CN112325884A (zh) * 2020-10-29 2021-02-05 广西科技大学 一种基于dwa的ros机器人局部路径规划方法
CN112486183A (zh) * 2020-12-09 2021-03-12 上海机器人产业技术研究院有限公司 一种室内移动机器人的路径规划算法
CN113359721A (zh) * 2021-05-31 2021-09-07 西安交通大学 一种结合运动控制的改进a*的agv路径规划方法
CN113741486A (zh) * 2021-11-05 2021-12-03 中国科学院自动化研究所 基于多约束的空间机器人智能运动规划方法及系统
CN114578808A (zh) * 2022-01-10 2022-06-03 美的集团(上海)有限公司 路径规划方法、电子设备、计算机程序产品及存储介质

Also Published As

Publication number Publication date
CN114578808A (zh) 2022-06-03

Similar Documents

Publication Publication Date Title
WO2023130755A1 (zh) 路径规划方法、电子设备、计算机程序产品及存储介质
KR20180137562A (ko) 심층 신경망 기반의 큐-러닝을 위한 경험 기억을 프루닝하는 방법 및 장치
CN107199572B (zh) 一种基于智能声源定位与语音控制的机器人系统及方法
WO2021238303A1 (zh) 运动规划的方法与装置
WO2022063247A1 (zh) 神经网络结构搜索方法及装置
CN112686281A (zh) 基于时空注意力和多级lstm信息表达的车辆轨迹预测方法
JP7213943B2 (ja) 車載機器の音声処理方法、装置、機器及び記憶媒体
CN111325382B (zh) 停车场空闲车位预测方法、装置、电子设备及存储介质
WO2022198947A1 (zh) 密接人群识别方法、装置、电子设备及存储介质
CN109029419A (zh) 导航方法、装置、终端及计算机可读存储介质
WO2023217127A1 (zh) 一种因果关系确定方法及相关设备
JP2006078009A (ja) 空調負荷予測方法
JP2021060982A (ja) データ分析システム診断方法、データ分析システム最適化方法、デバイス及び媒体
CN116913266B (zh) 一种语音检测方法、装置、设备及存储介质
WO2020252925A1 (zh) 用户特征群中用户特征寻优方法、装置、电子设备及计算机非易失性可读存储介质
CN113132193A (zh) 智能设备的控制方法、装置、电子设备以及存储介质
WO2023143121A1 (zh) 一种数据处理方法及其相关装置
JP7446359B2 (ja) 交通データ予測方法、交通データ予測装置、電子機器、記憶媒体、コンピュータプログラム製品及びコンピュータプログラム
WO2023082850A1 (zh) 行人轨迹预测方法、装置及存储介质
CN115086375A (zh) 网联车辆运动状态信息延时补偿方法、装置、系统和介质
CN112612277B (zh) 车辆轨迹规划方法、装置、设备和计算机可读介质
Lee et al. REINDEAR: REINforcement learning agent for Dynamic system control in Edge-Assisted Augmented Reality service
CN111883126A (zh) 数据处理方式的选择方法、装置及电子设备
CN110533192A (zh) 强化学习方法、装置、计算机可读介质及电子设备
Ma et al. Improving model-based deep reinforcement learning with learning degree networks and its application in robot control

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: 22918210

Country of ref document: EP

Kind code of ref document: A1