Indoor robot path planning method and device and electronic equipment

Abstract

The invention discloses an indoor robot path planning scheme, and belongs to the technical field of intelligent hardware, and the method comprises the steps: obtaining the current position information, target position information and indoor dynamic obstacle behavior information of a robot through a plurality of sensors disposed on the robot; predicting the behavior intention of the dynamic obstacle according to the dynamic obstacle behavior information; generating a plurality of candidate paths according to the behavior intention of the dynamic obstacle, the current position information of the robot and the target position information; selecting an optimal path from the plurality of candidate paths through a multi-objective optimization algorithm; and controlling the robot to operate according to the optimal path. According to the indoor robot path planning scheme provided by the invention, the real-time path planning efficiency, safety and flexibility of the robot in a complex dynamic environment can be improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent hardware technology, and in particular to an indoor robot path planning method and device, and electronic equipment. Background Art

[0002] With the development of robotics technology, more and more robots are entering the indoor field, such as service robots, indoor transfer robots, etc. For indoor robots, due to the complex and changeable environment, more accurate indoor positioning and path planning are required. Existing indoor robot path planning algorithms, such as RRT (Rapid Random Exploration Tree), can handle path planning tasks in static environments, but lack sufficient flexibility when facing obstacles in dynamic environments.

[0003] It can be seen that the goal is to urgently require technical personnel in this field to provide a flexible and safe indoor robot path planning solution. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide an indoor robot path planning method and device, and electronic equipment, which can solve the problems of poor flexibility and low safety of robot path planning in the prior art.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An embodiment of the present invention provides an indoor robot path planning method, which is applied to the robot, wherein the method includes:

[0007] Acquiring the current position information, target position information and indoor dynamic obstacle behavior information of the robot through a plurality of sensors provided on the robot, wherein the behavior information includes: speed, acceleration and position information;

[0008] Predicting the behavior intention of the dynamic obstacle based on the dynamic obstacle behavior information;

[0009] Generate multiple candidate paths according to the behavior intention of the dynamic obstacle, the current position information of the robot and the target position information;

[0010] Selecting an optimal path from the multiple candidate paths by a multi-objective optimization algorithm;

[0011] The robot is controlled to run according to the optimal path.

[0012] Optionally, the step of selecting the optimal path from the multiple candidate paths by using a multi-objective optimization algorithm includes:

[0013] Calculate the cost corresponding to each candidate path according to a preset cost function; wherein the cost includes: the candidate path length cost, the interaction cost of the robot with the dynamic obstacle under the candidate path, and the safety cost;

[0014] The candidate path with the minimum cost is determined as the optimal path.

[0015] Optionally, the step of respectively calculating the cost corresponding to each candidate path according to a preset cost function includes:

[0016] For each candidate path, determining the total length of the candidate path, the distance between the robot and the dynamic obstacle, the safety distance between the robot and the dynamic obstacle, and a preset safety distance;

[0017] Calculating a candidate path length cost according to the total length of the candidate path and a first weight coefficient;

[0018] Calculating the interaction cost between the robot and the dynamic obstacle on the candidate path according to the distance between the robot and the dynamic obstacle and the second weight coefficient;

[0019] Calculating the safety cost of the candidate path according to the safety distance between the robot and the dynamic obstacle, the preset safety distance and a third weight coefficient;

[0020] The sum of the candidate path length cost, the interaction cost and the security cost is determined as the cost corresponding to the candidate path.

[0021] Optionally, after the step of controlling the robot to travel along the optimal path, the method further comprises:

[0022] monitoring the behavioral intention of the dynamic obstacle;

[0023] When the behavior intention of the dynamic obstacle changes, determining behavior intention change information, wherein the behavior intention change information includes: a distance change value between the robot and the dynamic obstacle, and a path direction adjustment angle value;

[0024] The motion path of the robot is modified according to the behavior intention change information and the preset control equation.

[0025] Optionally, the step of modifying the operation path of the robot according to the behavior intention change information and a preset control equation includes:

[0026] Calculate the robot control signal at the current moment according to the behavior intention change information and the preset control equation;

[0027] Calculating a filtered robot control signal according to the current robot control signal, the previous robot control signal and a preset smoothing factor;

[0028] The robot is controlled to operate according to the filtered robot control signal.

[0029] An embodiment of the present invention further provides an indoor robot path planning device, which is applied to a robot, wherein the device comprises:

[0030] An acquisition module, used to acquire the current position information, target position information and indoor dynamic obstacle behavior information of the robot through a plurality of sensors provided on the robot, wherein the behavior information includes: speed, acceleration and position information;

[0031] A prediction module, used to predict the behavior intention of the dynamic obstacle based on the dynamic obstacle behavior information;

[0032] A generation module, used to generate multiple candidate paths according to the behavior intention of the dynamic obstacle, the current position information of the robot and the target position information;

[0033] A selection module, configured to select an optimal path from the plurality of candidate paths by using a multi-objective optimization algorithm;

[0034] A control module is used to control the robot to run according to the optimal path.

[0035] Optionally, the selection module includes:

[0036] The first submodule is used to calculate the cost corresponding to each candidate path according to a preset cost function; wherein the cost includes: the candidate path length cost, the interaction cost of the robot with the dynamic obstacle under the candidate path, and the safety cost;

[0037] The second submodule is used to determine the candidate path with the minimum cost as the optimal path.

[0038] Optionally, the first submodule includes:

[0039] A first unit is used to determine, for each candidate path, a total length of the candidate path, a distance between the robot and the dynamic obstacle, a safety distance between the robot and the dynamic obstacle, and a preset safety distance;

[0040] A second unit is used to calculate the candidate path length cost according to the total length of the candidate path and the first weight coefficient;

[0041] A third unit is used to calculate the interaction cost between the robot and the dynamic obstacle on the candidate path according to the distance between the robot and the dynamic obstacle and the second weight coefficient;

[0042] A fourth unit, configured to calculate a safety cost of the candidate path according to a safety distance between the robot and the dynamic obstacle, the preset safety distance, and a third weight coefficient;

[0043] The fifth unit is used to determine the sum of the candidate path length cost, the interaction cost and the security cost as the cost corresponding to the candidate path.

[0044] Optionally, the device further comprises:

[0045] A monitoring module, configured to monitor the behavior intention of the dynamic obstacle after the control module controls the robot to travel along the optimal path;

[0046] A change information determination module, used to determine behavior intention change information when the behavior intention of the dynamic obstacle changes, wherein the behavior intention change information includes: a distance change value between the robot and the dynamic obstacle, and a path direction adjustment angle value;

[0047] The modification module is used to modify the motion path of the robot according to the behavior intention change information and the preset control equation.

[0048] Optionally, the modification module includes:

[0049] The third submodule is used to calculate the robot control signal at the current moment according to the behavior intention change information and the preset control equation;

[0050] A fourth submodule, used for calculating a filtered robot control signal according to the current robot control signal, the previous robot control signal and a preset smoothing factor;

[0051] The fifth submodule is used to control the operation of the robot according to the filtered robot control signal.

[0052] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of any one of the above-mentioned indoor robot path planning methods.

[0053] An embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of any one of the above-mentioned indoor robot path planning methods are implemented.

[0054] The indoor robot path planning scheme provided by the embodiment of the present invention obtains the robot's current position information, target position information and indoor dynamic obstacle behavior information through multiple sensors set on the robot; predicts the behavior intention of the dynamic obstacle based on the dynamic obstacle behavior information; generates multiple candidate paths based on the behavior intention of the dynamic obstacle, the robot's current position information and the target position information; selects the optimal path from the multiple candidate paths through a multi-objective optimization algorithm; and controls the robot to run according to the optimal path. The indoor robot path planning scheme introduces obstacle intention recognition, motion prediction, path generation and dynamic obstacle avoidance adjustment, so that the robot can effectively judge whether to avoid dynamic obstacles in a dynamic environment, generate the optimal path and dynamically adjust it according to the real-time environment, which can improve the robot's real-time path planning efficiency, safety and flexibility in complex dynamic environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flowchart showing the steps of an indoor robot path planning method according to an embodiment of the present application;

[0056] Figure 2 is a flowchart showing the steps of an indoor robot path planning method according to an embodiment of the present application;

[0057] Figure 3 It is a structural block diagram of an indoor robot path planning device according to an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0059] The present invention provides an indoor robot path planning and obstacle avoidance method based on social behavior interaction. By introducing obstacle intention recognition and motion prediction, the robot can make decisions on whether to avoid or not according to the behaviors of pedestrians or other obstacles in a dynamic environment, generate an optimal path and dynamically adjust the path.

[0060] The indoor robot path planning solution provided in the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0061] As attached Figure 1 As shown, the indoor robot path planning method of the embodiment of the present application includes the following steps:

[0062] Step 101: Acquire the robot's current position information, target position information, and indoor dynamic obstacle behavior information through multiple sensors provided on the robot.

[0063] The behavior information includes speed, acceleration and position information. The current position information of the indoor robot can be determined by the positioning module, and the target position information is the end point of the robot's mission.

[0064] The indoor robot path planning method provided in the embodiment of the present application is applied to an indoor robot, which is an omnidirectional mobile robot that can move freely on the x and y planes and has the ability to rotate on the z axis. The indoor robot is provided with multiple sensor modules, including but not limited to laser radar, camera and multi-sensor fusion module, which are used to obtain static obstacle information and dynamic obstacle behavior information in the environment in real time. The indoor robot is provided with a control module (also referred to as a robot processor), which executes a path planning algorithm based on social behavior interaction, combines obstacle intention prediction and path cost optimization, dynamically adjusts the robot's motion primitives, and realizes path planning and obstacle avoidance.

[0065] Step 102: predicting the behavior intention of the dynamic obstacle based on the dynamic obstacle behavior information.

[0066] In the actual implementation process, the intention recognition algorithm based on the Bayesian reasoning model can be used according to the behavior information of dynamic obstacles to predict the behavior intention of the obstacle. The same behavior intention can determine whether the dynamic obstacle should be avoided in this path planning.

[0067] In the actual implementation process, there may be multiple dynamic obstacles indoors. During path planning, it is possible to determine whether each dynamic obstacle needs to be avoided, and finally generate a candidate path based on the behavioral intentions of each dynamic obstacle.

[0068] Step 103: Generate multiple candidate paths based on the behavior intention of the dynamic obstacle, the current position information of the robot and the target position information.

[0069] Based on the predicted behavior of obstacles, the system generates multiple candidate paths.

[0070] Step 104: Select the optimal path from multiple candidate paths through a multi-objective optimization algorithm.

[0071] An alternative method of selecting the best path from multiple candidate paths through a multi-objective optimization algorithm may be as follows:

[0072] First, the cost corresponding to each candidate path is calculated according to the preset cost function;

[0073] The costs include: the candidate path length cost, the robot's interaction cost with dynamic obstacles on the candidate path, and the safety cost.

[0074] Secondly, the candidate path with the minimum cost is determined as the optimal path.

[0075] An exemplary method of calculating the cost corresponding to each candidate path according to a preset cost function may include the following sub-steps:

[0076] S1: for each candidate path, determine the total length of the candidate path, the distance between the robot and the dynamic obstacle, the safety distance between the robot and the dynamic obstacle, and the preset safety distance;

[0077] S2: Calculate the candidate path length cost according to the total length of the candidate path and the first weight coefficient;

[0078] S3: Calculate the interaction cost between the robot and the dynamic obstacle on the candidate path based on the distance between the robot and the dynamic obstacle and the second weight coefficient;

[0079] S4: Calculate the safety cost of the candidate path according to the safety distance between the robot and the dynamic obstacle, the preset safety distance and the third weight coefficient;

[0080] S5: Determine the sum of the candidate path length cost, the interaction cost, and the security cost as the cost corresponding to the candidate path.

[0081] The default cost function C path Taking into account the path length, interaction cost with obstacles and safety, the specific formula is:

[0082] C path =λ1C length +λ2C interaction +λ3C safety

[0083] in, represents the total length of the candidate paths, represents the cost of the distance change between the robot and the dynamic obstacle (also known as the interaction cost between the robot and the dynamic obstacle under the candidate path), where d(s i , o i (t)) represents the distance between the robot and the dynamic obstacle, and ∈ is a small constant to prevent the denominator from being zero. Indicates the safe distance between the robot and dynamic obstacles, d safe The safety distance is set to ensure that the robot always maintains a sufficient distance from the obstacle. λ1, λ2, and λ3 are the first weight coefficient, the second weight coefficient, and the third weight coefficient, respectively. The sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1. The specific values ​​of the three can be flexibly set by those skilled in the art, and are not specifically limited in the embodiments of the present application.

[0084] Step 105: Control the robot to run along the optimal path.

[0085] Steps 101 to 105 are the process of path planning for the indoor robot. In the actual implementation process, when the obstacle behavior intention changes, the robot control system adjusts the robot path through the feedback control mechanism and dynamically modifies the motion primitives according to the changes in the obstacles to ensure the smoothness and safety of the obstacle avoidance behavior.

[0086] In an optional embodiment, after controlling the robot to travel along the optimal path, the following steps may also be included:

[0087] Step 1: Monitor the behavioral intention of dynamic obstacles;

[0088] Step 2: When the behavior intention of the dynamic obstacle changes, determine the behavior intention change information;

[0089] Among them, the behavior intention change information includes: the distance change value between the robot and the dynamic obstacle, and the path direction adjustment angle value.

[0090] Step 3: Modify the robot's motion path based on the behavior intention change information and preset control equations.

[0091] An exemplary method of modifying the robot's running path according to the behavior intention change information and the preset control equation may be as follows:

[0092] Calculate the robot control signal at the current moment based on the behavior intention change information and the preset control equation;

[0093] The filtered robot control signal is calculated according to the robot control signal at the current moment, the robot control signal at the previous moment and a preset smoothing factor; and the robot operation is controlled according to the filtered robot control signal.

[0094] The preset control equation can be:

[0095] U control =K d ·Δd+K θ ·θ

[0096] Where Δd = d new -d old represents the change in the distance between the robot and the obstacle, and θ is the angle value for adjusting the path direction. K d K is the distance control gain, which is used to adjust the safe distance from obstacles. θ Direction control gain, used to adjust the direction of the robot path;

[0097] When modifying the robot's running path, the robot control system smoothes the output of the feedback controller by introducing a low-pass filter to avoid frequent path adjustments caused by sensor noise or sudden changes in obstacles. The formula for the low-pass filter is:

[0098] U filtered =γ·U previous +(1-γ)·U current

[0099] Among them, U filtered is the filtered control signal; γ is the smoothing factor, ranging from [0,1];

[0100] U previous and U current are the robot control signals at the previous moment and the current moment respectively. previous and U current They are all calculated through preset control equations, and are just robot control signals at different times.

[0101] The indoor robot path planning scheme provided in the embodiment of the present application obtains the robot's current position information, target position information, and indoor dynamic obstacle behavior information through multiple sensors set on the robot; predicts the behavior intention of the dynamic obstacle based on the dynamic obstacle behavior information; generates multiple candidate paths based on the behavior intention of the dynamic obstacle, the robot's current position information, and the target position information; selects the optimal path from the multiple candidate paths through a multi-objective optimization algorithm; and controls the robot to run according to the optimal path. The indoor robot path planning scheme introduces obstacle intention recognition, motion prediction, path generation, and dynamic obstacle avoidance adjustment, so that the robot can effectively judge whether to avoid dynamic obstacles in a dynamic environment, generate the optimal path, and dynamically adjust it according to the real-time environment, which can improve the robot's real-time path planning efficiency, safety, and flexibility in complex dynamic environments.

[0102] The following is a specific example to illustrate the indoor robot path planning method provided in the embodiment of the present application.

[0103] The indoor robot path planning method provided in the embodiment of the present application comprises the following steps:

[0104] Step 201: Environmental perception and intention prediction.

[0105] Obtain the robot's current position in real time through sensor modules (such as lidar, camera, etc.) start , target position s goal And the location information of dynamic obstacles i (t).

[0106] Use the intention recognition algorithm based on the Bayesian reasoning model to predict the behavior intention I of the obstacle, that is, whether to avoid it. The specific derivation formula is:

[0107]

[0108] Among them, B represents the behavior information of the obstacle, such as speed, acceleration, etc.

[0109] Step 202: Generate each candidate path and calculate the cost of each candidate path.

[0110] Based on the prediction of obstacle behavior, the system generates multiple candidate paths P k , and assign a cost function to each path.

[0111] Cost function C path Taking into account the path length, interaction cost with obstacles and safety, the specific formula is:

[0112] C path =1=λ1 C length +λ2 C interaction +λ3 C safety

[0113] in, represents the total length of the path, represents the distance change cost between the robot and the obstacle, where d(s i , o i (t)) represents the distance between the robot and the obstacle, and ∈ is a small constant to prevent the denominator from being zero. Represents the safe distance between the robot and the obstacle, where d safe is the set safety distance to ensure that the robot always maintains a sufficient distance from obstacles. λ1, λ2, λ3 are the corresponding weight coefficients. The path in this step refers to the candidate path.

[0114] Step 203: Multi-objective optimization path selection.

[0115] The system selects the optimal path through a multi-objective optimization algorithm, with the goal of minimizing the path cost:

[0116]

[0117] Step 204: Dynamic feedback control and planned path correction.

[0118] When the obstacle behavior intention changes, the system adjusts the robot path through the feedback control mechanism and dynamically modifies the motion primitives according to the changes in the obstacles to ensure the smoothness and safety of the obstacle avoidance behavior. The specific control equation is:

[0119] U control =K d ·Δd+K θ ·θ

[0120] Where Δd = d new -d oldrepresents the change in the distance between the robot and the obstacle, and θ is the angle of path direction adjustment. d K is the distance control gain, which is used to adjust the safe distance from obstacles. θ Direction control gain, used to adjust the direction of the robot path;

[0121] The system smoothes the output of the feedback controller by introducing a low-pass filter to avoid frequent path adjustments due to sensor noise or sudden changes in obstacles. The formula for the low-pass filter is:

[0122] U filtered =γ·U previous +(1-γ)·U current

[0123] Among them, U filtered is the filtered control signal; γ is the smoothing factor, ranging from [0,1]; U previous and U current They are the control signals of the previous moment and the current moment respectively.

[0124] The indoor robot path planning method provided in this specific example can significantly improve the obstacle avoidance efficiency of indoor robots in dynamic environments by introducing an obstacle avoidance method based on social behavior interaction, enabling them to interact naturally with pedestrians or other obstacles in dynamic environments. Specifically, the system can dynamically adjust the robot path by predicting the intention of obstacles in real time and combining a multi-objective optimization algorithm to ensure the safety of obstacle avoidance behavior and the efficiency of path planning. The dynamic feedback control mechanism ensures that the robot can dynamically correct the path according to the actual situation in an obstacle environment, avoid collision risks, and improve the robustness of path planning.

[0125] Figure 3 A structural block diagram of an indoor robot path planning device for implementing an embodiment of the present application.

[0126] The indoor robot path planning device provided in the embodiment of the present application is applied to the robot and includes the following functional modules:

[0127] The acquisition module 301 is used to acquire the current position information, target position information and indoor dynamic obstacle behavior information of the robot through multiple sensors provided on the robot, wherein the behavior information includes: speed, acceleration and position information;

[0128] A prediction module 302, configured to predict the behavior intention of the dynamic obstacle according to the dynamic obstacle behavior information;

[0129] A generation module 303, used to generate multiple candidate paths according to the behavior intention of the dynamic obstacle, the current position information of the robot and the target position information;

[0130] A selection module 304 is used to select an optimal path from the multiple candidate paths through a multi-objective optimization algorithm;

[0131] The control module 305 is used to control the robot to run according to the optimal path.

[0132] Optionally, the selection module includes:

[0133] The first submodule is used to calculate the cost corresponding to each candidate path according to a preset cost function; wherein the cost includes: the candidate path length cost, the interaction cost of the robot with the dynamic obstacle under the candidate path, and the safety cost;

[0134] The second submodule is used to determine the candidate path with the minimum cost as the optimal path.

[0135] Optionally, the first submodule includes:

[0136] A first unit is used to determine, for each candidate path, a total length of the candidate path, a distance between the robot and the dynamic obstacle, a safety distance between the robot and the dynamic obstacle, and a preset safety distance;

[0137] A second unit is used to calculate the candidate path length cost according to the total length of the candidate path and the first weight coefficient;

[0138] A third unit is used to calculate the interaction cost between the robot and the dynamic obstacle on the candidate path according to the distance between the robot and the dynamic obstacle and the second weight coefficient;

[0139] A fourth unit, configured to calculate a safety cost of the candidate path according to a safety distance between the robot and the dynamic obstacle, the preset safety distance, and a third weight coefficient;

[0140] The fifth unit is used to determine the sum of the candidate path length cost, the interaction cost and the security cost as the cost corresponding to the candidate path.

[0141] Optionally, the device further comprises:

[0142] A monitoring module, configured to monitor the behavior intention of the dynamic obstacle after the control module controls the robot to travel along the optimal path;

[0143] A change information determination module, used to determine behavior intention change information when the behavior intention of the dynamic obstacle changes, wherein the behavior intention change information includes: a distance change value between the robot and the dynamic obstacle, and a path direction adjustment angle value;

[0144] The modification module is used to modify the motion path of the robot according to the behavior intention change information and the preset control equation.

[0145] Optionally, the modification module includes:

[0146] The third submodule is used to calculate the robot control signal at the current moment according to the behavior intention change information and the preset control equation;

[0147] A fourth submodule, used for calculating a filtered robot control signal according to the current robot control signal, the previous robot control signal and a preset smoothing factor;

[0148] The fifth submodule is used to control the operation of the robot according to the filtered robot control signal.

[0149] The indoor robot path planning device provided in the embodiment of the present application obtains the robot's current position information, target position information, and indoor dynamic obstacle behavior information through multiple sensors set on the robot; predicts the behavior intention of the dynamic obstacle based on the dynamic obstacle behavior information; generates multiple candidate paths based on the behavior intention of the dynamic obstacle, the robot's current position information, and the target position information; selects the optimal path from the multiple candidate paths through a multi-objective optimization algorithm; and controls the robot to run according to the optimal path. The indoor robot path planning device introduces obstacle intention recognition, motion prediction, path generation, and dynamic obstacle avoidance adjustment, so that the robot can effectively judge whether to avoid dynamic obstacles in a dynamic environment, generate the optimal path, and dynamically adjust it according to the real-time environment, which can improve the robot's real-time path planning efficiency, safety, and flexibility in complex dynamic environments.

[0150] In the present application embodiment Figure 3 The indoor robot path planning device shown is arranged in the control system of the indoor robot. The control system provided with the device may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0151] The embodiments of the present application provide Figure 3 The indoor robot path planning device shown can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0152] Optionally, an embodiment of the present application also provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the various processes performed by the above-mentioned indoor robot path planning device are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0153] It should be noted that the electronic device in the embodiment of the present application includes the server described above.

[0154] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0155] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0156] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A path planning method for an indoor robot, applied to a robot, characterized in that: The method comprises: Acquiring the current position information, target position information and indoor dynamic obstacle behavior information of the robot through a plurality of sensors provided on the robot, wherein the behavior information includes: speed, acceleration and position information; Predicting the behavior intention of the dynamic obstacle based on the dynamic obstacle behavior information; Generate multiple candidate paths according to the behavior intention of the dynamic obstacle, the current position information of the robot and the target position information; Selecting an optimal path from the multiple candidate paths by a multi-objective optimization algorithm; The robot is controlled to run according to the optimal path.

2. The method according to claim 1, characterized in that The step of selecting the optimal path from the multiple candidate paths by using a multi-objective optimization algorithm comprises: Calculate the cost corresponding to each candidate path according to a preset cost function; wherein the cost includes: the candidate path length cost, the interaction cost of the robot with the dynamic obstacle under the candidate path, and the safety cost; The candidate path with the minimum cost is determined as the optimal path.

3. The method according to claim 2, characterized in that The step of respectively calculating the cost corresponding to each candidate path according to a preset cost function includes: For each candidate path, determining the total length of the candidate path, the distance between the robot and the dynamic obstacle, the safety distance between the robot and the dynamic obstacle, and a preset safety distance; Calculating a candidate path length cost according to the total length of the candidate path and a first weight coefficient; Calculating the interaction cost between the robot and the dynamic obstacle on the candidate path according to the distance between the robot and the dynamic obstacle and the second weight coefficient; Calculating the safety cost of the candidate path according to the safety distance between the robot and the dynamic obstacle, the preset safety distance and a third weight coefficient; The sum of the candidate path length cost, the interaction cost and the security cost is determined as the cost corresponding to the candidate path.

4. The method according to claim 1, characterized in that: After the step of controlling the robot to travel along the optimal path, the method further comprises: monitoring the behavioral intention of the dynamic obstacle; When the behavior intention of the dynamic obstacle changes, determining behavior intention change information, wherein the behavior intention change information includes: a distance change value between the robot and the dynamic obstacle, and a path direction adjustment angle value; The motion path of the robot is modified according to the behavior intention change information and the preset control equation.

5. The method according to claim 4, characterized in that The step of modifying the operation path of the robot according to the behavior intention change information and the preset control equation comprises: Calculate the robot control signal at the current moment according to the behavior intention change information and the preset control equation; Calculating a filtered robot control signal according to the current robot control signal, the previous robot control signal and a preset smoothing factor; The robot is controlled to operate according to the filtered robot control signal.

6. An indoor robot path planning device, applied to a robot, characterized in that: The device comprises: An acquisition module, used to acquire the current position information, target position information and indoor dynamic obstacle behavior information of the robot through a plurality of sensors provided on the robot, wherein the behavior information includes: speed, acceleration and position information; A prediction module, used to predict the behavior intention of the dynamic obstacle based on the dynamic obstacle behavior information; A generation module, used to generate multiple candidate paths according to the behavior intention of the dynamic obstacle, the current position information of the robot and the target position information; A selection module, configured to select an optimal path from the plurality of candidate paths by using a multi-objective optimization algorithm; A control module is used to control the robot to run according to the optimal path.

7. The device according to claim 6, characterized in that The selection module comprises: The first submodule is used to calculate the cost corresponding to each candidate path according to a preset cost function; wherein the cost includes: the candidate path length cost, the interaction cost of the robot with the dynamic obstacle under the candidate path, and the safety cost; The second submodule is used to determine the candidate path with the minimum cost as the optimal path.

8. The device according to claim 7, characterized in that The first submodule includes: A first unit is used to determine, for each candidate path, a total length of the candidate path, a distance between the robot and the dynamic obstacle, a safety distance between the robot and the dynamic obstacle, and a preset safety distance; A second unit is used to calculate the candidate path length cost according to the total length of the candidate path and the first weight coefficient; A third unit is used to calculate the interaction cost between the robot and the dynamic obstacle on the candidate path according to the distance between the robot and the dynamic obstacle and the second weight coefficient; A fourth unit, configured to calculate a safety cost of the candidate path according to a safety distance between the robot and the dynamic obstacle, the preset safety distance, and a third weight coefficient; The fifth unit is used to determine the sum of the candidate path length cost, the interaction cost and the security cost as the cost corresponding to the candidate path.

9. The device according to claim 6, characterized in that The device also includes: A monitoring module, configured to monitor the behavior intention of the dynamic obstacle after the control module controls the robot to travel along the optimal path; A change information determination module, used to determine behavior intention change information when the behavior intention of the dynamic obstacle changes, wherein the behavior intention change information includes: a distance change value between the robot and the dynamic obstacle, and a path direction adjustment angle value; The modification module is used to modify the motion path of the robot according to the behavior intention change information and the preset control equation.

10. An electronic device, characterized in that: The electronic device includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction is executed by the processor to execute the steps of any one of the indoor robot path planning methods in claims 1-5.

Images