Path planning method and system based on geometric grid map and electromagnetic map

Abstract

The invention relates to robot path planning, in particular to a path planning method and device based on a geometric grid map and an electromagnetic map. According to the method and device, corresponding information of an electromagnetic map and a geometric grid map is collected at the same time, obstacle avoidance and path planning can be conducted in the geometric grid map, and the signal intensity of a signal source is measured and calculated in the electromagnetic map. An electromagnetic map is arranged in route planning parameters, so that the robot can integrate electromagnetic signals and obstacles to achieve an optimal solution of a data acquisition task when the robot performs automatic navigation data acquisition, and therefore, route obstacle avoidance planning can be achieved while the signal intensity is ensured, a starting point and an ending point do not need to be given, and the cost is reduced. The method can combine signals and obstacles to actively select route points which collect data blocks and are easy to reach.

Description

Technical Field

[0001] The present invention relates to the field of robot path planning, and in particular to a path planning method and system based on a geometric grid map and an electromagnetic map. Background Art

[0002] With the continuous development of robotics technology, robots are increasingly used in various industries, thus having to adapt to a wider range of environments and scenarios. In order to enable robots to better adapt to the environment, make up for the shortcomings of humans, and obtain richer data to improve the decision-making ability of robots, robot autonomous data collection technology has been developed.

[0003] When performing data collection tasks, if the robot is as close to the sensor as possible, the data collection speed will be increased, but it may cause slow movement. Similarly, if the robot chooses an obstacle-free area, the movement speed will be increased, but data may not be collected. Therefore, the data collection robot needs to consider both the electromagnetic map and the grid map, and actively choose waypoints that can collect data quickly and are easier to reach.

[0004] The existing robot path planning method only performs obstacle avoidance navigation based on geometric grid maps. In terms of distribution data, it only considers the distribution data of obstacles and the distribution data of the robot itself. At the same time, the starting point and end point need to be given manually during navigation. It is impossible to autonomously plan the optimal route map required for this data collection task, which will lead to inefficient task completion.

[0005] Based on the above shortcomings, the prior art still has deficiencies and needs to be further improved. Summary of the invention

[0006] The embodiments of the present invention provide a path planning method and system based on a geometric grid map and an electromagnetic map, so as to at least solve the problem that the existing robot path planning method only performs obstacle avoidance navigation based on a geometric grid map, resulting in low efficiency in completing tasks.

[0007] According to an embodiment of the present invention, a path planning method based on a geometric grid map and an electromagnetic map is provided, comprising the following steps:

[0008] Collect data from the geometric grid map and the electromagnetic map in real time to obtain observation environment data based on the data; avoid obstacles and plan paths in the geometric grid map, and measure the signal strength of the signal source in the electromagnetic map;

[0009] Based on the acquired observation environment data, the observation environment data is constrained to generate the optimal trajectory predicted in the current time period;

[0010] Based on the acquired predicted optimal trajectory, the robot is controlled to move according to the predicted optimal trajectory.

[0011] Furthermore, before executing the predicted optimal trajectory according to the optimal control command, the method further includes:

[0012] The transmission process of the observation environment data is optimized so that the observation environment data can be sent and received in the required order to ensure the integrity and reliability of the observation environment data.

[0013] Furthermore, data of the geometric grid map and the electromagnetic map are collected in real time to obtain observation environment data based on the data; wherein, by avoiding obstacles and planning paths in the geometric grid map, and by measuring the signal strength of the signal source in the electromagnetic map, the specific steps include:

[0014] Obtain map models of application scenarios in real time;

[0015] Acquire the distance data between objects in the application scenario in real time, wherein the distance data is combined with the map model to generate a geometric grid map; avoid obstacles and plan paths in the geometric grid map; acquire the electromagnetic signals and strengths of objects at different positions in the application scenario to generate a visualized electromagnetic map, and determine the distance of the signal source in the electromagnetic map based on the strength of the signal.

[0016] Furthermore, based on the acquired observation environment data, constraining the observation environment data to generate the predicted optimal trajectory in the current time period specifically includes:

[0017] Set the cost function, and use the cost function to determine the solution direction of the optimization equation to find the minimum value of the cost function;

[0018] Set the minimum distance between the robot and obstacles;

[0019] Limit the robot's speed during movement to a preset speed threshold;

[0020] Limit the acceleration of the robot during movement to a preset acceleration threshold;

[0021] By solving the cost function, constraining the minimum distance between the robot and the obstacle, constraining the speed and transporting the acceleration, the predicted optimal trajectory is obtained.

[0022] Further, based on the acquired predicted optimal trajectory, controlling the robot to move according to the predicted optimal trajectory includes:

[0023] According to the predicted optimal trajectory, the robot's throttle action, the robot's brake action and the robot's movement direction are controlled according to the predicted optimal trajectory.

[0024] A path planning system based on a geometric grid map and an electromagnetic map, comprising:

[0025] The perception module is used to collect data from the geometric grid map and the electromagnetic map in real time to obtain observation environment data based on the data; wherein, obstacles are avoided and paths are planned in the geometric grid map, and the signal strength of the signal source is measured in the electromagnetic map;

[0026] The path planning module is used to constrain the observed environment data based on the acquired observed environment data to generate the predicted optimal trajectory within the current time period;

[0027] The execution module is used to control the robot to move according to the predicted optimal trajectory based on the acquired predicted optimal trajectory.

[0028] Furthermore, the path planning system also includes:

[0029] The communication optimization module is used to send and receive the observation environment data transmitted between the perception module and the execution module in the required order to ensure the integrity and reliability of the observation environment data.

[0030] Furthermore, the perception module includes:

[0031] An image acquisition unit, used for acquiring a map model of an application scenario in real time;

[0032] Radar is used to obtain the distance data between objects in the application scene in real time. The distance data is combined with the map model to generate a geometric grid map. The radar module avoids obstacles and plans paths through the geometric grid map. The radar module determines the distance of the signal source based on the strength of the signal in the electromagnetic map.

[0033] The wireless network unit is used for wireless communication between the image acquisition unit and the radar module.

[0034] Furthermore, the path planning module includes:

[0035] The function optimization unit is used to set the cost function, and the solution direction of the optimization equation is determined by the cost function to obtain the optimal trajectory;

[0036] The obstacle avoidance constraint unit is used to set the minimum distance between the robot and obstacles;

[0037] A speed constraint unit is used to limit the speed of the robot during movement to a preset speed threshold;

[0038] An acceleration constraint unit is used to limit the acceleration of the robot during movement to a preset acceleration threshold;

[0039] By solving the cost function, constraining the minimum distance between the robot and the obstacle, constraining the speed and transporting the acceleration, the predicted optimal trajectory is obtained.

[0040] Furthermore, the execution module includes:

[0041] A throttle control unit, used to control the throttle action of the robot according to the predicted optimal trajectory;

[0042] A braking unit, used to control the braking action of the robot according to the predicted optimal trajectory;

[0043] The steering unit controls the robot's movement direction according to the predicted optimal trajectory.

[0044] The path planning method and system based on the geometric grid map and the electromagnetic map in the embodiment of the present invention simultaneously collects the corresponding information of the electromagnetic map and the geometric grid map, and can avoid obstacles and plan paths in the geometric grid map, and measure the signal strength of the signal source in the electromagnetic map. The electromagnetic map is placed in the parameters of route planning, so that when the robot performs automatic navigation data collection, it can integrate electromagnetic signals and obstacles to achieve the optimal solution of the data collection task. Therefore, the present application can achieve route obstacle avoidance planning while ensuring signal strength, and does not need to give a starting point and an end point, and can actively select the waypoints that collect data blocks and are easy to reach in combination with signals and obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0046] Figure 1 It is a flow chart of the path planning method based on geometric grid map and electromagnetic map of the present invention;

[0047] Figure 2 It is a schematic diagram of a path planning system based on a geometric grid map and an electromagnetic map of the present invention;

[0048] Figure 3 It is a schematic diagram of the framework of the path planning system based on the geometric grid map and the electromagnetic map of the present invention;

[0049] Figure 4 This is an embodiment diagram of the global task diagram of the present invention;

[0050] Figure 5 A comparison diagram of the method of the present invention and the existing path planning method. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0052] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0053] Example 1

[0054] According to an embodiment of the present invention, a path planning method based on a geometric grid map and an electromagnetic map is provided. Figure 1 and Figure 2 , including the following steps:

[0055] S100: collecting data of the geometric grid map and the electromagnetic map in real time to obtain observation environment data based on the data; wherein, obstacles are avoided and paths are planned in the geometric grid map, and signal strength of the signal source is measured in the electromagnetic map;

[0056] S200: constraining the observed environment data based on the acquired observed environment data to generate a predicted optimal trajectory within the current time period;

[0057] S300: Based on the acquired predicted optimal trajectory, control the robot to move according to the predicted optimal trajectory.

[0058] The path planning method and device based on the geometric grid map and the electromagnetic map in the embodiment of the present invention simultaneously collects the corresponding information of the electromagnetic map and the geometric grid map, and can avoid obstacles and plan paths in the geometric grid map, and measure the signal strength of the signal source in the electromagnetic map. The electromagnetic map is placed in the parameters of route planning, so that when the robot performs automatic navigation data collection, it can integrate electromagnetic signals and obstacles to achieve the optimal solution of the data collection task. Therefore, the present application can achieve route obstacle avoidance planning while ensuring signal strength, and does not need to give a starting point and an end point, and can actively select the waypoints that collect data blocks and are easy to reach in combination with signals and obstacles.

[0059] Before step S300, the following steps are also included:

[0060] The transmission process of the observation environment data is optimized so that the observation environment data can be sent and received in the required order to ensure the integrity and reliability of the observation environment data.

[0061] Specifically, the communication optimization module is used to optimize the transmission process of the observed environment data. First, channel estimation technology is used to allocate resources. Channel estimation is used to estimate the characteristics of the communication channel in the wireless system. In wireless communication systems, due to factors such as mobility and interference, the channel characteristics will change over time, so it is necessary to regularly estimate the channel to ensure optimal resource allocation.

[0062] After channel estimation is completed, the estimated channel information is used for tasks such as resource allocation, including allocating bandwidth and power to different users or data streams based on the estimated channel quality.

[0063] After completing resource allocation and receiving data information in the observation environment, we establish TCP communication through queue control, because TCP is a queue-based protocol. In TCP communication, data is transmitted through queues between the sender and receiver controlled by queues.

[0064] Queue control includes the sending section and the receiving end. At the sending end, data is placed in a sending queue and then sent to the receiving end through the TCP protocol. The sending queue requires queue control to ensure that data is sent in the correct order and to avoid data overrun or other problems in the queue. At the receiving end, data is received through the TCP protocol and stored in a receiving queue. The receiving queue requires queue control to ensure that data is received in the correct order and to avoid data loss or other problems in the queue.

[0065] Therefore, queue control plays a very important role in TCP communication. It ensures that data is sent and received in the correct order and guarantees the integrity and reliability of the data.

[0066] Step S100 specifically includes:

[0067] S101: Acquire a map model of an application scenario in real time;

[0068] S102: Real-time acquisition of distance data between objects in the application scenario, combining the distance data with the map model to generate a geometric grid map; avoiding obstacles and planning paths in the geometric grid map; acquiring the electromagnetic signals and strengths of objects at different positions in the application scenario to generate a visual electromagnetic map, and determining the distance of the signal source in the electromagnetic map based on the strength of the signal. Electromagnetic signals and strength data can be measured and obtained by electromagnetic sensors.

[0069] Specifically, the perception module collects data from the geometric grid map and the electromagnetic map in real time to obtain observation environment data based on the data; the perception device avoids obstacles and plans paths in the geometric grid map, and the perception device measures the signal strength of the signal source in the electromagnetic map. The perception module includes cameras, radars, and WiFi (WIreless Fidelity, wireless network transmission technology).

[0070] First, the camera is used to model the application scenario map, and the corresponding geometric grid map can be established in combination with the radar. During the robot's mission, the camera combined with the radar can also update the robot's position in the virtual geometric map in real time to ensure the smooth execution of the obstacle avoidance algorithm. At the same time, radar and WiFi can also be used for the detection and calculation of electromagnetic maps. In the electromagnetic map, the strength of the signal depends on the distance from the signal source. The radar can further deduce the location of the signal source through the strength of the signal at different positions, and then find a road that can complete the data collection task while avoiding obstacles. The data information measured by the three devices of camera, radar and WiFi together constitute the observation environment data of this application, and the perception module finally transmits the observation environment data to other modules.

[0071] Step S200 specifically includes:

[0072] S201: setting a cost function, and determining a solution direction of the optimization equation by the cost function to solve for a minimum value of the cost function;

[0073] S202: Setting the minimum distance between the robot and obstacles;

[0074] S202: limiting the speed of the robot during movement to a preset speed threshold;

[0075] S204: limiting the acceleration of the robot during the movement process to a preset acceleration threshold;

[0076] By solving the cost function of the minimum distance constraint between the robot and the obstacle, the speed constraint and the acceleration transportation, the predicted optimal trajectory is obtained.

[0077] Specifically, the path planning module constrains the observed environment data based on the acquired observed environment data to generate a predicted optimal trajectory within the current time period.

[0078] After receiving the observed environment data, the path planning module constrains the relevant data and puts it into the preset solver for solving. The solver adopts the model predictive control method, which is commonly used in the control algorithm of autonomous driving. Its advantage is that it can make the control program meet certain constraints, such as taking various dynamics and kinematics into account as constraints. The main idea of ​​model predictive control is to predict the motion state and trajectory of the robot in a future time window based on the current dynamic model. Then, under the condition of considering the constraints, optimize the control trajectory at each specific moment to ensure the optimal solution at that moment. The optimization problem is divided into five parts: cost function, acceleration limit constraint, speed limit constraint, obstacle avoidance constraint, and dynamic constraint.

[0079] The cost function is the core part of the optimization problem. The setting of the cost function determines the solution direction of the optimization equation. The ultimate goal of optimization is to solve the value that minimizes the cost function.

[0080] The obstacle avoidance constraint is the core constraint of the planning optimization problem. This constraint ensures that the vehicle's trajectory will not collide with obstacles. The basis for determining whether there is a collision is the minimum distance between the robot and the surrounding obstacles. The minimum distance needs to be controlled within a safe range.

[0081] The speed constraint is to limit the speed of the target robot during the movement process within the preset speed and acceleration thresholds. The acceleration constraint is to limit the acceleration of the target robot during the movement process within the preset acceleration threshold, which is obtained according to the robot model of the target robot.

[0082] The final solution is the optimal control command and the predicted optimal trajectory within the period of time, and the predicted control command is passed to the robot for execution.

[0083] It should be noted that after constraining the observed environment data, when the predicted optimal trajectory is generated, the optimal control command will be generated, and the robot executes the optimal control command to run according to the predicted optimal trajectory. Specifically, after the robot receives the optimal control command and the predicted optimal trajectory, the robot will execute the received optimal control command, and the movement of the robot according to the optimal control command is the predicted optimal trajectory.

[0084] Step S300 specifically includes:

[0085] According to the predicted optimal trajectory, the robot's throttle action, the robot's brake action and the robot's movement direction are controlled according to the predicted optimal trajectory.

[0086] Specifically, the robot moves according to the predicted optimal trajectory based on the received optimal control command. The robot includes an accelerator, brake and steering control wheel. The accelerator of the robot is used to add fuel according to the optimal control command. The brake of the robot is used to control whether to brake and the speed according to the optimal control command. The steering control wheel of the robot controls whether to turn and how to turn according to the optimal control command.

[0087] The robot controls the robot to complete the data collection task according to the optimal control command. At the same time, the surrounding environment will change during the movement of the robot. After receiving information through the perception module, the robot's behavior is optimized again. Finally, the execution module will enable the robot to avoid obstacles while optimizing the communication environment.

[0088] In the field of robot autonomous data collection technology, this application places electromagnetic maps in the parameters of route planning, compared with the traditional method of using only geometric grid maps, so that when the robot performs automatic navigation data collection, it can integrate electromagnetic signals and obstacles to achieve the best solution for data collection tasks. Figure 4 In the global task map shown, the existing technology cannot take into account the signal reception problem of the electromagnetic map. When planning the path, it will ignore the two signal sources and only take the shorter path, resulting in poor communication effect. However, the method of this application can refer to the distribution of obstacles and electromagnetic signal sources at the same time, so as to ensure the completion of the basic obstacle avoidance task while obtaining better communication collection data. The final comparison results are as follows: Figure 5 shown.

[0089] This application collects the corresponding information of the electromagnetic map and the geometric grid map at the same time. It can avoid obstacles and plan paths in the geometric grid map, and measure the signal strength of the signal source in the electromagnetic map. Therefore, this application can do route avoidance planning while ensuring signal strength, and does not need to give a starting point and an end point. It can actively select the waypoints that are easy to reach and collect data blocks in combination with signals and obstacles.

[0090] This application has the following advantages: 1. In this application, the perception module not only perceives the geometric grid map, but also the electromagnetic map, and can perceive the electromagnetic signal emitted by the collector. And input it into the observed environment data as a reference. 2. In data collection, this application can combine the corresponding data and autonomously give the optimal route, which can save a lot of time compared to traditional path planning.

[0091] Example 2

[0092] According to another embodiment of the present invention, a path planning system based on a geometric grid map and an electromagnetic map is provided. Figure 2 and Figure 3 ,include:

[0093] The sensing module 100 is used to collect data of the geometric grid map and the electromagnetic map in real time to obtain observation environment data based on the data; wherein, obstacles are avoided and paths are planned in the geometric grid map, and the signal strength of the signal source is measured in the electromagnetic map;

[0094] A path planning module 200 is used to constrain the observed environment data based on the acquired observed environment data to generate a predicted optimal trajectory within the current time period;

[0095] The execution module 300 is used to control the robot to move according to the predicted optimal trajectory based on the acquired predicted optimal trajectory.

[0096] The present application firstly adopts the perception module 100 to geometrically collect the data of the geometric grid map and the electromagnetic map at the same time, transmits the data to the communication optimization module 400 and the path planning module 300, and then imports the data into the execution module 300 after solving the problem. The execution module 300 controls the robot to move according to the predicted optimal trajectory, so as to achieve the purpose of improving the communication environment and avoiding obstacles at the same time.

[0097] Specifically, in the robot path planning based on geometric grid maps and electromagnetic maps, in the data collection task, the perception module is used to collect data. For example, cameras, radar modules, WiFi (wireless network units) and other devices obtain corresponding information from electromagnetic maps and geometric grid maps and transmit them into the observation environment, and perform task-oriented navigation on the relevant data. The graph model is used internally for optimization, which is reflected in the use of meta-search technology to optimize the local optimal obstacle avoidance algorithm, and the branch and bound method to optimize the global optimal electromagnetic path planning.

[0098] After obtaining the corresponding data, the global trajectory is passed to the communication optimization module to establish TCP communication, and the waypoints in the global trajectory are passed to the path planning module 200, which is used to describe the specific motion state of the robot on the global trajectory, such as direction, speed, acceleration, etc. Then, the execution method is obtained using the existing solver and constraint conditions. Finally, the obtained data is imported into the execution module 300, and the task is completed by controlling the throttle, brake and steering to achieve the purpose of improving the route communication environment and avoiding obstacles.

[0099] The path planning method and device based on the geometric grid map and the electromagnetic map in the embodiment of the present invention simultaneously collects the corresponding information of the electromagnetic map and the geometric grid map, and can avoid obstacles and plan paths in the geometric grid map, and measure the signal strength of the signal source in the electromagnetic map. The electromagnetic map is placed in the parameters of route planning, so that when the robot performs automatic navigation data collection, it can integrate electromagnetic signals and obstacles to achieve the optimal solution of the data collection task. Therefore, the present application can achieve route obstacle avoidance planning while ensuring signal strength, and does not need to give a starting point and an end point, and can actively select the waypoints that collect data blocks and are easy to reach in combination with signals and obstacles.

[0100] The path planning system includes:

[0101] The communication optimization module 400 is used to send and receive the observed environment data transmitted between the perception module and the execution module in a required order to ensure the integrity and reliability of the observed environment data.

[0102] Specifically, the communication optimization module 400 includes: a channel estimation unit, a resource allocation unit, a queue control unit and TCP (Transmission Control Protocol) communication. The channel estimation unit uses channel estimation technology to allocate resources, and channel estimation is used to estimate the characteristics of the communication channel in the wireless system. In a wireless communication system, due to factors such as mobility and interference, the channel characteristics will change over time, so it is extremely important to regularly estimate the channel to ensure optimal resource allocation.

[0103] After the channel estimation is completed, the estimated channel information is used for tasks such as resource allocation through the resource allocation unit, including allocating bandwidth and power to different users or data streams based on the estimated channel quality.

[0104] After completing resource allocation and receiving data information in the observation environment, TCP communication is established through the queue control unit. Because TCP is a queue-based protocol, in TCP communication, data is transmitted through queues between the sending and receiving ends of the queue control unit.

[0105] The queue control unit includes a sending end and a receiving end. At the sending end, data is put into a sending queue and then sent to the receiving end through the TCP communication protocol. The sending queue needs queue control to ensure that data is sent in the correct order and to avoid data overrun or other problems in the queue. At the receiving end, data is received through the TCP communication protocol and stored in a receiving queue. The receiving queue needs queue control to ensure that data is received in the correct order and to avoid data loss or other problems in the queue.

[0106] Therefore, the queue control unit plays a very important role in TCP communication. It ensures that data is sent and received in the correct order and guarantees the integrity and reliability of the data.

[0107] The perception module includes:

[0108] An image acquisition unit, used for acquiring a map model of an application scenario in real time;

[0109] Radar is used to obtain the distance data between objects in the application scene in real time. The distance data is combined with the map model to generate a geometric grid map. The radar module avoids obstacles and plans paths through the geometric grid map. The radar module determines the distance of the signal source based on the strength of the signal in the electromagnetic map.

[0110] The wireless network unit is used for wireless communication between the image acquisition unit and the radar module.

[0111] When the relevant information of the geometric grid map has not been obtained, the image acquisition unit can be used to model the application scenario map, and the corresponding geometric grid map can be established in combination with the radar. The image acquisition unit can be a camera. During the robot's mission, the camera combined with the radar can also update the robot's position in the virtual geometric grid map in real time to ensure the smooth execution of the obstacle avoidance algorithm. At the same time, the radar module and WiFi can also be used for the detection and calculation of electromagnetic maps. In the electromagnetic map, the strength of the signal depends on the distance from the signal source. The radar can further deduce the position of the signal source through the height of the signal strength at different positions, and then find a road that can complete the data collection task while avoiding obstacles. The data information measured by the three devices of the camera, radar and WiFi together constitute the observation environment data of this application, and the perception module finally transmits the observation environment data to other modules.

[0112] The path planning module 200 includes:

[0113] The function optimization unit is used to set the cost function, and the solution direction of the optimization equation is determined by the cost function to obtain the optimal trajectory; the cost function describes the quality of the robot trajectory; by determining the solution direction of the optimization equation, the cost function is minimized to obtain the optimal trajectory.

[0114] The obstacle avoidance constraint unit is used to set the minimum distance between the robot and obstacles;

[0115] A speed constraint unit is used to limit the speed of the robot during movement to a preset speed threshold;

[0116] An acceleration constraint unit is used to limit the acceleration of the robot during movement to a preset acceleration threshold;

[0117] By solving the cost function of the minimum distance constraint between the robot and the obstacle, the speed constraint and the acceleration transportation, the predicted optimal trajectory is obtained.

[0118] Specifically, the path planning module 200 constrains the observed environment data based on the acquired observed environment data to generate a predicted optimal trajectory within the current time period.

[0119] After the path planning module 200 receives the observed environment data from the perception module 100, the path planning module 200 constrains the relevant data and puts it into the preset solver for solving. The solver adopts the model predictive control method, which is more commonly used in the control algorithm of autonomous driving. Its advantage is that it can make the control program meet certain constraints, such as taking various dynamics and kinematics into consideration as constraints. The main idea of ​​model predictive control is to predict the motion state and trajectory of the robot in a future time window based on the current dynamic model. Then, under the condition of considering the constraints, optimize the control trajectory at each specific moment to ensure the optimal solution at this moment. The optimization problem is divided into five parts: cost function, acceleration limit constraint, speed limit constraint, obstacle avoidance constraint, and dynamic constraint.

[0120] The cost function is the core part of the optimization problem. The setting of the cost function determines the solution direction of the optimization equation. The ultimate goal of optimization is to solve the value that minimizes the cost function.

[0121] The obstacle avoidance constraint is the core constraint of the planning optimization problem. This constraint ensures that the vehicle's trajectory will not collide with obstacles. The basis for determining whether there is a collision is the minimum distance between the robot and the surrounding obstacles. The minimum distance needs to be controlled within a safe range.

[0122] The speed constraint is to limit the speed of the target robot during the movement process within the preset speed and acceleration thresholds. The acceleration constraint is to limit the acceleration of the target robot during the movement process within the preset acceleration threshold, which is obtained according to the robot model of the target robot.

[0123] The final solution is the optimal control command and the predicted optimal trajectory within the period of time, and the predicted control command is passed to the robot for execution.

[0124] It should be noted that after constraining the observed environment data, when the predicted optimal trajectory is generated, the optimal control command will be generated, and the robot executes the optimal control command to run according to the predicted optimal trajectory. Specifically, after the robot receives the optimal control command and the predicted optimal trajectory, the robot will execute the received optimal control command, and the movement of the robot according to the optimal control command is the predicted optimal trajectory.

[0125] The execution module 300 includes:

[0126] A throttle control unit, used to control the throttle action of the robot according to the predicted optimal trajectory;

[0127] A braking unit, used to control the braking action of the robot according to the predicted optimal trajectory;

[0128] The steering unit controls the robot's movement direction according to the predicted optimal trajectory.

[0129] According to the predicted optimal trajectory, the robot's throttle action, the robot's brake action and the robot's movement direction are controlled according to the predicted optimal trajectory.

[0130] Specifically, the robot moves according to the predicted optimal trajectory based on the received optimal control command. The robot includes an accelerator, brake and steering control wheel. The accelerator of the robot is used to add fuel according to the optimal control command. The brake of the robot is used to control whether to brake and the speed according to the optimal control command. The steering control wheel of the robot controls whether to turn and how to turn according to the optimal control command.

[0131] The robot controls the robot to complete the data collection task according to the optimal control command. At the same time, the surrounding environment will change during the movement of the robot. After receiving information through the perception module, the robot's behavior is optimized again. Finally, the execution module will enable the robot to avoid obstacles while optimizing the communication environment.

[0132] Example 3

[0133] A storage medium stores a program file capable of implementing any one of the above-mentioned full life cycle operation and maintenance strategy methods based on a prediction model.

[0134] Example 4

[0135] A processor is used to run a program, wherein when the program is running, any one of the above-mentioned full life cycle operation and maintenance strategy methods based on a prediction model is executed.

[0136] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0137] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0138] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0139] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0140] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0141] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes 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 a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0142] The above is only 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 principle 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 based on geometric grid map and electromagnetic map, It is characterized in that The following steps are involved: Collecting data of the geometric grid map and the electromagnetic map in real time to obtain observation environment data based on the data; wherein, obstacles are avoided and paths are planned in the geometric grid map, and the signal strength of the signal source is measured in the electromagnetic map; Based on the acquired observed environment data, constraining the observed environment data to generate a predicted optimal trajectory within a current time period; Based on the acquired predicted optimal trajectory, the robot is controlled to move according to the predicted optimal trajectory.

2. According to the path planning method based on geometric grid map and electromagnetic map according to claim 1, It is characterized in that Before executing the predicted optimal trajectory according to the optimal control command, the method further includes: The transmission process of the observed environment data is optimized so that the observed environment data is sent and received in a required order, thereby ensuring the integrity and reliability of the observed environment data.

3. According to the path planning method based on geometric grid map and electromagnetic map as claimed in claim 2, It is characterized in that The real-time collection of data from the grid map and the electromagnetic map to obtain observation environment data based on the data; wherein, avoiding obstacles and planning paths in the geometric grid map, and measuring the signal strength of the signal source in the electromagnetic map specifically include: Obtain map models of application scenarios in real time; Acquire the distance data between objects in the application scenario in real time, wherein the distance data is combined with the map model to generate the geometric grid map; avoid obstacles and plan paths in the geometric grid map; acquire the electromagnetic signals and strengths of objects at different positions in the application scenario to generate a visualized electromagnetic map, and determine the distance of the signal source in the electromagnetic map based on the strength of the signal.

4. According to the path planning method based on geometric grid map and electromagnetic map as claimed in claim 2, It is characterized in that The step of constraining the observed environment data based on the acquired observed environment data to generate a predicted optimal trajectory in the current time period specifically includes: Setting a cost function, and determining a solution direction of the optimization equation by the cost function to solve for a minimum value of the cost function; Setting the minimum distance between the robot and obstacles; Limiting the speed of the robot during movement to a preset speed threshold; Limiting the acceleration of the robot during movement to a preset acceleration threshold; The predicted optimal trajectory is obtained by solving the cost function, constraining the minimum distance between the robot and the obstacle, constraining the speed and transporting the acceleration.

5. According to the path planning method based on geometric grid map and electromagnetic map as claimed in claim 2, It is characterized in that The method of controlling the robot to move according to the predicted optimal trajectory based on the acquired predicted optimal trajectory comprises: According to the predicted optimal trajectory, the throttle action of the robot, the brake action of the robot and the movement direction of the robot are controlled according to the predicted optimal trajectory.

6. A path planning system based on geometric grid map and electromagnetic map, It is characterized in that include: A perception module is used to collect data from a geometric grid map and an electromagnetic map in real time to obtain observation environment data based on the data; wherein, obstacles are avoided and paths are planned in the geometric grid map, and signal strength of a signal source is measured in the electromagnetic map; A path planning module, configured to constrain the observed environment data based on the acquired observed environment data to generate a predicted optimal trajectory within a current time period; An execution module is used to control the robot to move according to the predicted optimal trajectory based on the acquired predicted optimal trajectory.

7. The path planning system based on geometric grid map and electromagnetic map according to claim 6, It is characterized in that The path planning system also includes: The communication optimization module is used to send and receive the observed environment data transmitted between the perception module and the execution module in a required order to ensure the integrity and reliability of the observed environment data.

8. The path planning system based on geometric grid map and electromagnetic map according to claim 7, It is characterized in that The perception module comprises: An image acquisition unit, used for acquiring a map model of an application scenario in real time; A radar is used to obtain distance data between objects in the application scene in real time, and the distance data is combined with the map model to generate the geometric grid map; the radar module avoids obstacles and plans paths through the geometric grid map; the radar module determines the distance of the signal source according to the strength of the signal in the electromagnetic map; A wireless network unit is used for wireless communication between the image acquisition unit and the radar module.

9. The path planning system based on geometric grid map and electromagnetic map according to claim 7, It is characterized in that The path planning module includes: A function optimization unit, used to set a cost function, and determine the solution direction of the optimization equation by the cost function to obtain an optimal trajectory; An obstacle avoidance constraint unit, used to set a minimum distance between the robot and obstacles; A speed constraint unit, used to limit the speed of the robot during movement to a preset speed threshold; An acceleration constraint unit, used to limit the acceleration of the robot during movement to a preset acceleration threshold; The predicted optimal trajectory is obtained by solving the cost function, constraining the minimum distance between the robot and the obstacle, constraining the speed and transporting the acceleration.

10. The path planning system based on geometric grid map and electromagnetic map according to claim 7, It is characterized in that The execution module includes: A throttle control unit, used to control the throttle action of the robot according to the predicted optimal trajectory; A braking unit, used to control the braking action of the robot according to the predicted optimal trajectory; A steering unit controls the movement direction of the robot according to the predicted optimal trajectory.

Images