An Artificial Intelligence-Based Path Planning Method for Mine Robots

Abstract

The present invention discloses a path planning method for mining robots based on artificial intelligence, which relates to the field of artificial intelligence technology. By introducing an environmental perception coefficient Rfx, an environmental change coefficient Envc and a dynamic obstacle monitoring mechanism, and combining the real-time data processing of the total number of dynamic obstacles Zzs, the obstacle distance Zjj, the relative speed of the obstacle Zsd and the turning radius of the robot Zbj, the problem that traditional path planning cannot adapt to sudden changes in the mine environment is effectively solved; by dynamically evaluating the environmental change coefficient Envc, an obstacle avoidance path is generated to improve the safety and adaptability of path planning; at the same time, the urgency coefficient Urg of the task is calculated and evaluated, and a path adjustment plan is preferentially generated to improve the emergency task response efficiency; in addition, by calculating and evaluating the path energy consumption evaluation value Nex, it is judged whether to start the path optimization mode to ensure the smooth completion of the task and reduce the energy consumption risk; overall, the dynamic adaptability, task allocation efficiency and energy consumption management ability of the path planning of mining robots are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and particularly to a path planning method for mining robots based on artificial intelligence. Background Technique

[0002] The background technique of the path planning method for mining robots can be traced back to the end of the last century. With the continuous advancement of mining automation, the complexity of the mining operation environment has promoted the gradual application of path planning technology in the field of mining robots. Early path planning mainly relied on preset routes and was difficult to cope with the dynamically changing mining environment. With the improvement of sensor technology, artificial intelligence, and computing power, the path planning method for mining robots has gradually developed characteristics based on environmental perception, autonomous decision-making, and dynamic adjustment. In recent years, the introduction of deep learning and reinforcement learning algorithms has enabled mining robots to achieve efficient path optimization in complex mining environments, effectively avoiding obstacles and improving operation efficiency.

[0003] However, the path planning method for mining robots has the following three technical drawbacks in the prior art:

[0004] 1. Insufficient dynamic adaptability of path planning: In traditional path planning methods for mining robots, a common problem is that the path planning cannot adapt to sudden changes in the mine environment in real time, such as sudden changes in dynamic obstacles and special terrains in the mine. This can lead to situations where the robot is prone to collisions or the path cannot be executed, thus reducing the task completion efficiency and safety.

[0005] 2. Task priorities are insufficient to achieve optimal resource allocation: Existing path planning technologies usually lack dynamic analysis of the urgency of different robot tasks and cannot adjust robot scheduling and path planning in a timely manner according to the urgency of the tasks. This can lead to resource waste and delays in urgent tasks, and the overall resources of the mining area cannot be fully utilized.

[0006] 3. Insufficient energy consumption assessment and power management: In traditional path planning methods for mining robots, the path energy consumption is usually not finely evaluated. Especially in complex mine environments, the robot may attempt to complete tasks when the power is insufficient, which increases the risk of task failure and may also cause the robot to stay in a dangerous area and be unable to return. Summary of the Invention

[0007] In view of the deficiencies of the prior art, the present invention provides a path planning method for mining robots based on artificial intelligence, which solves the technical drawbacks of insufficient environmental perception, weak self-adaptability, and limited intelligent decision-making ability in the background technique.

[0008] To achieve the above objectives, the present invention is realized through the following technical solutions: A path planning method for mining robots based on artificial intelligence, including the following steps:

[0009] S1. Pre-acquire the 3D electronic map of the mining area environment, combine the sensor data in the mine, and lock a number of potential obstacles and dynamically changing areas; then divide the mine area based on the 3D electronic map to obtain several groups of mine sub-areas; secondly, preset several groups of mining robots and label them with serial numbers, and finally pair the mining robots with the mine sub-areas;

[0010] S2. Real-time monitor the power state, position state and environmental perception information of the mining robots in the mine sub-areas to generate a comprehensive state set, determine and evaluate the environmental perception coefficient Rfx of the mining robots at the current position based on the comprehensive state set, and screen out the mining robots with insufficient environmental perception or plan a preliminary obstacle avoidance path for the mining robots according to the evaluation content of the environmental perception coefficient Rfx;

[0011] S3. According to the insufficient environmental perception situation of the mining robots obtained in step S2, combined with the sudden state changes in the operation environment of the mine sub-areas, real-time monitor the task processing data information of several groups of mining robots, construct a task state set, and generate the current task urgency coefficient Urg of the mining robot numbered i based on the task state set, and adjust the path planning priority based on the task urgency coefficient Urg, and preferentially generate a dynamic path adjustment plan for the robots with urgent tasks;

[0012] S4. According to the adjusted path planning priority in step S3, perform dynamic obstacle monitoring on the path where the robot numbered i is located, combine the real-time environmental perception data, dynamic obstacle data and the motion model of the robot to generate and evaluate the environmental change coefficient Envc, and generate an advanced obstacle avoidance path according to the evaluation content of the environmental change coefficient Envc;

[0013] S5. At the same time, monitor and record the state data of the safe area and the operation area in the mine sub-areas, combine the current power consumption related data of the robot numbered i and the obstacle distribution related data in the mining area, predict and evaluate the path energy consumption evaluation value Nex for the robot to complete the current task, and finally determine whether the mining robot can successfully complete the current task and whether it needs to enter the path optimization mode.

[0014] Preferably, S1 includes S11 and S12, specifically:

[0015] S11. Based on the environmental survey related data of the mining area, extract the geological data, mine structure data and geographical annotation information data of the mining area in advance, and then generate a 3D electronic map of the mining area; the generation of the map is based on formatting the map;

[0016] S12. After obtaining the 3D electronic map, the system collects real-time mine environmental data through various types of sensors arranged in the mine, including laser scanners, infrared sensors, and ultrasonic sensors, and integrates the data with the 3D electronic map. Then, based on the information feedback from the sensors, potential obstacles, dynamically changing areas, and special terrains in the mining area are detected and locked. Secondly, the potential obstacles, dynamically changing areas, and special terrains in the mining area are marked, including the corresponding position coordinates and dynamic attributes.

[0017] Preferably, S2 includes S21 and S22, specifically as follows:

[0018] S21. Each robot obtains the current battery level, geographical position coordinates, and surrounding environmental conditions through embedded sensors. Then, the remaining battery level Eb, the obstacle density Obd at the current position, the mine environmental light intensity Lum, and the air dust concentration Dus in the mining area are extracted from the comprehensive status set, and the environmental perception coefficient Rfx of the current position of the mine robot is calculated through the following formula:

[0019] .

[0020] Preferably,

[0021] S22. The preset environmental perception threshold Q is compared and evaluated with the environmental perception coefficient Rfx to screen out robots with insufficient environmental perception. The specific content is as follows:

[0022] When the environmental perception threshold Q < the environmental perception coefficient Rfx, it indicates that the robot's environmental perception ability for the current environment is abnormal and there is a situation of insufficient perception. Then, the mine robots in the current mine sub-region are marked as abnormal and replaced or adjusted abnormally;

[0023] When the environmental perception threshold Q ≥ the environmental perception coefficient Rfx, it indicates that the robot's environmental perception ability for the current environment is normal. At this time, the initial obstacle avoidance path of the current mine robot is planned, including dynamic obstacle avoidance based on the obstacle density Obd at the current position and the task target;

[0024] Preferably, S3 includes S31 and S32, specifically as follows:

[0025] S31. The task status set includes the remaining task duration Rsc, the task priority weight value Ryx, and the current task completion progress value Rjd. The task status set is extracted, and the current task urgency coefficient Urg of the mine robot with serial number i is calculated through the following formula:

[0026] .

[0027] Preferably,

[0028] S32. Compare and evaluate the preset emergency threshold W with the task urgency coefficient Urg to generate the following evaluation content:

[0029] When the task urgency coefficient Urg ≥ the urgency threshold W, the current task is urgent and the robot prioritizes path adjustment. The system marks the robot as "task urgent" and immediately activates dynamic path adjustment mode, generating a priority path for the robot to ensure timely task completion.

[0030] When the task urgency coefficient Urg is less than the emergency threshold W, it indicates that the current task is not urgent, and the robot continues to execute according to the current path planning without additional path adjustment.

[0031] Preferably, S4 includes S41 and S42, specifically:

[0032] S41. Real-time environment perception data, dynamic obstacle data, and robot motion model data are aggregated and, after preprocessing and dimensionless processing, a dynamic obstacle data set is constructed. The total number of dynamic obstacles Zzs, obstacle distance Zjj, obstacle relative speed Zsd, and robot turning radius Zbj in the dynamic obstacle data set are extracted, and the environment variation coefficient Envc is generated using the following formula:

[0033]

[0034] Where, represents the distance between the mining robot and the jth dynamic obstacle, represents the relative speed between the robot and the jth dynamic obstacle, represents the turning radius of the mining robot when interacting with the j-th obstacle.

[0035] Preferably,

[0036] S42. Compare and evaluate the preset safety threshold Es with the environmental variation coefficient Envc. The specific evaluation contents are as follows:

[0037] If the environmental variation coefficient Envc exceeds the preset safety threshold Es, the system determines that the robot's current path is risky and cannot pass safely. At this time, the system automatically generates an advanced obstacle avoidance path for the robot, including prioritizing avoiding high-risk areas and selecting a safe path with a lower obstacle density.

[0038] If the environmental change coefficient Envc ≤ the preset safety threshold Es, the system determines that there is no risk in the robot's current path, and there is no need to generate a new path.

[0039] Preferably, S5 includes S51 and S52, specifically:

[0040] S51. Among them, the status data of the safe area and the working area within the mine sub-region include the passable rate Pav and the regional height difference Alt. The current power consumption-related data and the obstacle distribution-related data within the mining area include the power consumption per meter distance Edi and the obstacle height Obh. After extracting the passable rate Pav, the regional height difference Alt, the power consumption per meter distance Edi, and the obstacle height Obh and performing dimensionless processing, the path energy consumption evaluation value Nex is calculated through the following formula:

[0041] .

[0042] Preferably,

[0043] S52. The evaluation is carried out by comparing the preset path energy consumption threshold R with the path energy consumption evaluation value Nex. The specific content is as follows:

[0044] When the path energy consumption evaluation value Nex ≤ the path energy consumption threshold R, it indicates that the energy consumption of the robot under the current path planning meets the threshold requirements. At this time, the system determines that the robot completes the task within the power range, continues to execute the task along the current path, and no path adjustment is required;

[0045] When the path energy consumption evaluation value Nex > the path energy consumption threshold R, it indicates that the energy consumption of the robot under the current path planning cannot meet the threshold requirements. At this time, the system determines that the power of the robot is insufficient to support the task completion; the system marks the robot as "path optimization required" and starts the path optimization mode.

[0046] The present invention provides a path planning method for a mine robot based on artificial intelligence, having the following beneficial effects:

[0047] (1) For the path planning method for a mine robot based on artificial intelligence, by introducing the environmental perception coefficient Rfx, the environmental change coefficient Envc, and the dynamic obstacle monitoring mechanism, the problem of insufficient dynamic adaptability of path planning is effectively solved. The system generates the environmental change coefficient Envc by dimensionless processing of the total number of dynamic obstacles Zzs, the obstacle distance Zjj, the relative speed of the obstacle Zsd, and the turning radius of the robot Zbj after real-time monitoring of the dynamically changing area of potential obstacles and special terrains within the mine sub-region and combining the sensor feedback data. According to the comparison and evaluation results of Envc and the safety threshold Es, an obstacle avoidance path is dynamically generated to prevent the robot from colliding or the task from being interrupted due to the inability to recognize environmental changes. This improvement enhances the path planning accuracy and safety of the mine robot in a complex mine environment.

[0048] (2) For the problem that the task priority is insufficient to achieve optimal resource allocation in a path planning method for mining robots based on artificial intelligence, this technical solution proposes a dynamic adjustment mechanism for the task urgency coefficient Urg. By extracting the remaining task duration Rsc, task priority weight value Ryx, and current task completion progress value Rjd in the task status set and performing formula calculations, and combining the task emergency threshold W to dynamically evaluate the task urgency coefficient Urg. When the task urgency coefficient Urg is greater than or equal to the task emergency threshold W, the robot is marked as "task urgent", and a dynamic path adjustment plan is preferentially generated. This method realizes the refined management of task allocation for mining robots, significantly improves the response speed of emergency tasks, and optimizes the overall utilization efficiency of mining area resources.

[0049] (3) For the problem of insufficient energy consumption assessment and power management in a path planning method for mining robots based on artificial intelligence, this solution proposes a dynamic prediction method for the path energy consumption assessment value Nex. By performing dimensionless processing on the power consumption per meter Edi, obstacle height Obh, passability Pav, and regional height difference Alt, the path energy consumption assessment value Nex is calculated. Combining with the path energy consumption threshold R for evaluation, when the path energy consumption assessment value Nex is greater than the path energy consumption threshold R, the system marks the robot as "path optimization required" and starts the path optimization mode to avoid task failure or the robot staying in a dangerous area due to insufficient power. This method ensures the task completion rate of mining robots and the high efficiency of energy consumption management, while reducing the safety hazards of mine operations. Brief Description of the Drawings

[0050] Figure 1 It is a schematic diagram of the step flow of a path planning method for a mining robot based on artificial intelligence according to the present invention;

[0051] Figure 2 It is a schematic diagram of the program code of a path planning method for a mining robot based on artificial intelligence according to the present invention. Detailed Embodiments

[0052] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0053] Embodiment 1

[0054] Please refer to Figure 1 , the present invention provides a path planning method for a mining robot based on artificial intelligence, including the following steps:

[0055] S1. Pre-acquire the 3D electronic map of the mining area environment, combine the sensor data in the mine, and lock a number of potential obstacles and dynamically changing areas; then divide the mine area based on the 3D electronic map to obtain several groups of mine sub-areas; secondly, preset several groups of mining robots and label them with serial numbers, and finally pair the mining robots with the mine sub-areas;

[0056] S2. Real-time monitor the power state, position state and environmental perception information of the mining robots in the mine sub-areas to generate a comprehensive state set, determine and evaluate the environmental perception coefficient Rfx of the mining robots at the current position based on the comprehensive state set, and screen out the mining robots with insufficient environmental perception or plan a preliminary obstacle avoidance path for the mining robots according to the evaluation content of the environmental perception coefficient Rfx;

[0057] S3. According to the situation of insufficient environmental perception of the mining robots obtained in step S2, combined with the sudden state changes in the operation environment of the mine sub-areas, real-time monitor the task processing data information of several groups of mining robots, construct a task state set, and generate the current task urgency coefficient Urg of the mining robot with serial number i based on the task state set, and adjust the path planning priority based on the task urgency coefficient Urg, and preferentially generate a dynamic path adjustment plan for the robots with urgent tasks;

[0058] S4. According to the path planning priority adjusted in step S3, conduct dynamic obstacle monitoring on the path where the robot with serial number i is located, combine the real-time environmental perception data, dynamic obstacle data and the motion model of the robot to generate and evaluate the environmental change coefficient Envc, and generate an advanced obstacle avoidance path according to the evaluation content of the environmental change coefficient Envc;

[0059] S5. At the same time, monitor and record the state data of the safe areas and operation areas in the mine sub-areas, combine the current power consumption related data of the robot with serial number i and the obstacle distribution related data in the mining area, predict and evaluate the path energy consumption evaluation value Nex for the robot to complete the current task, and finally determine whether the mining robot can successfully complete the current task and whether it needs to enter the path optimization mode.

[0060] In this embodiment, step S1 locks potential obstacles and dynamically changing areas by obtaining a three-dimensional electronic map of the mining area environment and combining the sensor data in the mine. At the same time, the mine is divided into sub-areas and paired with mining robots, providing a basic area division and preliminary environmental recognition ability for path planning; step S2 generates a comprehensive status set by real-time monitoring of the power status, position status and environmental perception information of the mining robot, calculates the environmental perception coefficient Rfx of the current position, screens out the robots with insufficient environmental perception and generates a preliminary obstacle avoidance path for them, improving the perception accuracy and safety of the robots in the complex mining area environment; step S3 constructs a task status set and generates a task urgency coefficient Urg, adjusts the path planning priority based on the task urgency, and generates a dynamic path adjustment scheme for the robots with urgent tasks, enabling them to respond promptly to sudden changes in the mining area and improving the task completion efficiency and adaptability; step S4 generates an environmental change coefficient Envc according to the dynamic obstacle data, real-time environmental perception data and the robot motion model, and generates an advanced obstacle avoidance path through evaluation, effectively reducing the collision risk of the robot in the dynamic environment and ensuring path safety; step S5 monitors and records the status data of the safe area and the working area in the mine sub-area, combines the current power consumption data and the obstacle distribution data, calculates the path energy consumption evaluation value Nex, so as to evaluate whether the robot can successfully complete the task or needs to enter the path optimization mode, ensuring the efficient completion of the task and the optimal selection of the path under the power limit.

[0061] Embodiment 2

[0062] S1 includes S11 and S12, specifically:

[0063] S11. Based on the environmental survey related data of the mining area, the geological data, mine structure data and geographical annotation information data of the mining area are extracted in advance, and then a three-dimensional electronic map of the mining area is generated; the generation of the map is based on formatting the map.

[0064] S12. After obtaining the three-dimensional electronic map, the system collects the mine environment data in real time through various types of sensors arranged in the mine, including laser scanning, infrared sensors and ultrasonic sensors, and integrates the data with the three-dimensional electronic map; then, according to the information feedback by the sensors, the potential obstacles, dynamically changing areas and special terrains in the mining area are detected and locked, and then the potential obstacles, dynamically changing areas and special terrains in the mining area are marked, including the corresponding position coordinates and dynamic attributes.

[0065] In this embodiment, step S1 provides comprehensive environmental data support and dynamic monitoring basis for the path planning of the mine robot through operations including S11 and S12; in S11, by extracting geological data, mine structure data, and geographical annotation information of the mining area, a formatted three-dimensional electronic map is generated, enabling the system to have the basic geographical structure information of the mining area;

[0066] In S12, the system uses laser scanning, infrared sensors, and ultrasonic sensors to collect mine environmental data in real time, integrates it with the three-dimensional electronic map, combines sensor feedback information to detect and lock potential obstacles, dynamic change areas, and special terrains in the mining area, and at the same time marks the position coordinates and dynamic attributes of these key areas, enabling the system to continuously obtain accurate and dynamic spatial information in a complex mining area environment; this step plays a key role in the path planning method, enabling the robot to anticipate and avoid obstacles, adapt to environmental changes in real time, and improve the accuracy of path planning and the safety of task execution;

[0067] Among them, the specific process of detecting and locking potential obstacles, dynamic change areas, and special terrains in the mining area is as follows: the laser scanning sensor scans the three-dimensional space of the mining area to generate preliminary contour data of obstacles and measure their position coordinates; then, the infrared sensor captures changes in thermal signals to identify the movement trajectory of heat sources in dynamic areas; subsequently, the ultrasonic sensor detects the surface unevenness characteristics in the mine through sound wave reflection to identify special terrains; all sensor data is transmitted to the central processing unit in real time, and multi-source information is integrated using data fusion technology, and the movement trend of obstacles, the change of heat source intensity, and the terrain complexity are analyzed through a specific dynamic change model; the system classifies and marks the analysis results, including the boundary attributes of static obstacles, dynamic change areas, and the risk levels of special terrains, and stores their positions and dynamic attributes in the three-dimensional electronic map to ensure that the analysis results can be called in real time during the robot path planning process, improving the perception accuracy and safety of the mine environment.

[0068] Embodiment 3

[0069] S2 includes S21 and S22, specifically:

[0070] S21. Each robot obtains the current battery power, geographical position coordinates, and surrounding environmental conditions through embedded sensors; then extracts the remaining battery power value Eb, the obstacle density Obd at the current position, the mine environmental light intensity Lum, and the mine air dust concentration Dus from the comprehensive status set, and calculates the environmental perception coefficient Rfx of the current position of the mine robot through the following formula:

[0071]

[0072] S22. Compare and evaluate the preset environmental perception threshold Q with the environmental perception coefficient Rfx to screen out robots with insufficient environmental perception. The specific contents are as follows:

[0073] When the environmental perception threshold Q is less than the environmental perception coefficient Rfx, it indicates that the robot's ability to perceive the current environment is abnormal and insufficient; the mining robot in the current mine sub-area will be marked as abnormal and replaced or adjusted abnormally;

[0074] When the environmental perception threshold Q ≥ environmental perception coefficient Rfx, it indicates that the robot's ability to perceive the current environment is normal; at this time, the current mining robot performs preliminary obstacle avoidance path planning, including dynamic obstacle avoidance based on the obstacle density Obd at the current location and the task target;

[0075] S3 includes S31 and S32, specifically:

[0076] S31, the task status set includes the remaining task time Rsc, the task priority weight value Ryx, and the current task completion progress value Rjd; extract the task status set, and calculate the current task urgency coefficient Urg of the mining robot with sequence number i using the following formula:

[0077]

[0078] S32. Compare and evaluate the preset emergency threshold W with the task urgency coefficient Urg to generate the following evaluation content:

[0079] When the task urgency coefficient Urg ≥ the emergency threshold W, it indicates that the current task is urgent and the robot will prioritize path adjustment. The system marks the robot as "task urgent" and immediately activates dynamic path adjustment mode to generate a priority path for it to ensure timely completion of the task.

[0080] When the task urgency coefficient Urg is less than the emergency threshold W, it indicates that the current task is not urgent, and the robot continues to execute according to the current path planning without additional path adjustment.

[0081] S4 includes S41 and S42, specifically:

[0082] S41. Real-time environment perception data, dynamic obstacle data, and robot motion model data are aggregated and, after preprocessing and dimensionless processing, a dynamic obstacle data set is constructed. The total number of dynamic obstacles Zzs, obstacle distance Zjj, obstacle relative speed Zsd, and robot turning radius Zbj in the dynamic obstacle data set are extracted, and the environment variation coefficient Envc is generated using the following formula:

[0083]

[0084] In the formula, represents the distance between the mine robot and the j-th dynamic obstacle, represents the relative velocity between the robot and the j-th dynamic obstacle, represents the turning radius of the mine robot when interacting with the j-th obstacle.

[0085] S42. Compare and evaluate through the preset safety threshold Es and the environmental change coefficient Envc, and the specific evaluation content is as follows:

[0086] If the environmental change coefficient Envc > the preset safety threshold Es, the system determines that there is a risk in the current path of the robot and it cannot pass safely; at this time, the system automatically generates an advanced obstacle avoidance path for the robot, including preferentially avoiding high-risk areas and selecting a safe path with a lower obstacle density;

[0087] If the environmental change coefficient Envc ≤ the preset safety threshold Es, the system determines that there is no risk in the current path of the robot, and there is no need to generate a new path at this time.

[0088] In this embodiment, precise perception, adaptive adjustment, and intelligent path optimization of the robot in the mining area are achieved through each step; in S2, each robot obtains the current power, geographical position coordinates, and surrounding environmental conditions through an embedded sensor, and extracts the remaining power value Eb, the obstacle density Obd at the current position, the mine environmental light intensity Lum, and the mine air dust concentration Dus in the comprehensive state set, and generates an environmental perception coefficient Rfx through calculation. This coefficient is used to evaluate the current perception ability of the robot to ensure timely replacement or adjustment of the path when the perception is insufficient; among them, the obstacle density Obd represents the distribution density of the number of obstacles in a unit area and is used to reflect the complexity of the mine environment. The mine environmental data is obtained in real time through various types of sensors arranged in the mine, including laser scanners, ultrasonic sensors, and infrared sensors; the number of obstacles in the sensor coverage area is counted, and combined with the geographical position coordinates, the number of obstacles per unit area is calculated; and the environmental perception threshold Q is obtained through experimental calibration and is usually set according to the complexity of the mine environment, and the value range is generally between 0.1 and 1; the specific value of the environmental perception coefficient Rfx is calculated according to the parameters and generally ranges from 0.0 to 1.0.

[0089] In S3, the remaining task duration Rsc, the task priority weight value Ryx, and the current task completion progress value Rjd are used to generate the task urgency coefficient Urg. By comparing it with the preset emergency threshold W, it is determined whether priority path adjustment is required to ensure that urgent tasks can be completed in a timely manner. Among them, the task urgency coefficient Urg is calculated from the remaining task duration Rsc (in seconds) and the task priority weight value Ryx (0 - 1), and usually ranges from 0 to 10. The emergency threshold W is set according to the time sensitivity of the mining area tasks and usually ranges from 5 to 8. At the same time, the dynamic path adjustment mode includes combining the motion model data of the robot and using the dynamic path planning algorithm to generate a new path set in real time. Subsequently, by evaluating the safety, passability, and energy consumption of each path in the path set, a path with a lower obstacle density, the lowest risk in the dynamically changing area, and an energy consumption evaluation value Nex less than or equal to the path energy consumption threshold R is preferentially selected as the priority path. At the same time, the system marks high-risk areas in real time and notifies the robot to bypass these areas. During the path execution, the system continuously monitors the changes in dynamic obstacles and the robot state. If new environmental changes occur, the path parameters are dynamically adjusted to ensure that the robot is always in the optimal path state. The following is a specific example after the dynamic path adjustment mode is started:

[0090] Case 1: The original path plan of the robot passes through a mine tunnel with a large slope, a high obstacle density, and there is a landslide risk in this area. After the system detects that this path is not feasible, it selects a safer passage to bypass. Even though the energy consumption of this path is higher, this path is still preferentially selected to ensure safety and timely task completion;

[0091] Case 2: The system detects a new obstacle (such as a fallen rock) on another path in the mine. After the path is re-planned, the robot is guided to bypass the obstacle. The updated path can not only avoid the obstacle but also ensure the timeliness of the task and complete the shortest path planning;

[0092] In S4, the real-time environmental perception data, dynamic obstacle data, and the motion model data of the robot are aggregated. After preprocessing and dimensionless processing, a dynamic obstacle data set is constructed. The specific construction process of the dynamic obstacle data set is as follows:

[0093] Using multi-modal data fusion technology, the data collected by laser scanning, ultrasonic sensors, and infrared sensors are preprocessed, including data cleaning, noise reduction, and format unification. The dimensionless method is used to perform dimensionless processing on parameters such as the distance, speed, and quantity of dynamic obstacles in order to uniformly construct the dynamic obstacle data set. The specific dimensionless processing is: , where X represents the original parameter value, Xmin represents the minimum value of the original parameter, and Xmax represents the maximum value of the original parameter.

[0094] Generate an environmental change coefficient Envc based on the total number of dynamic obstacles Zzs, the obstacle distance Zjj, the relative speed of the obstacle Zsd, and the turning radius of the robot Zbj, so as to evaluate the safety of the path and generate an advanced obstacle avoidance path when necessary, ensuring the safety and path continuity of the robot in a dynamic and complex environment; through the acquisition and evaluation of each lower-level parameter, a comprehensive monitoring of the mining operation environment is realized, providing accurate data support for path planning, enabling the system to have self-adaptability and intelligent decision-making capabilities, and ensuring the efficient completion of the robot task and safe operation; among them, based on the total number of obstacles Zzs (unit: number) in the dynamic obstacle data set, the obstacle distance Zjj (unit: meter, range 0 - 5 meters), and the turning radius of the robot Zbj (unit: meter, range 0.1 - 10 meters); the safety threshold Es is preset according to the safety level and risk tolerance of the mine environment, and usually ranges from 5 to 7.

[0095] Example 4

[0096] S5 includes S51 and S52. Specifically:

[0097] S51. Among them, the state data of the safe area and the operation area in the mine sub-region includes the passability Pav and the regional height difference Alt, and the current power consumption-related data and the obstacle distribution-related data in the mining area include the power consumption per meter Edi and the obstacle height Obh; after extracting the passability Pav, the regional height difference Alt, the power consumption per meter Edi, and the obstacle height Obh and performing dimensionless processing, the path energy consumption evaluation value Nex is calculated through the following formula:

[0098]

[0099] Evaluate by presetting the path energy consumption threshold R and the path energy consumption evaluation value Nex. The specific content is as follows:

[0100] When the path energy consumption evaluation value Nex ≤ the path energy consumption threshold R, it indicates that the energy consumption of the robot under the current path planning meets the threshold requirements; at this time, the system judges that the robot can complete the task within the power range, continues to execute the task along the current path, and no path adjustment is required;

[0101] When the path energy consumption evaluation value Nex > the path energy consumption threshold R, it indicates that the energy consumption of the robot under the current path planning cannot meet the threshold requirements; at this time, the system judges that the power of the robot is insufficient to support the completion of the task; the system marks this robot as "path optimization required" and starts the path optimization mode.

[0102] In this embodiment, the energy consumption optimization and path decision-making of the robot in the mining area are realized through S5, ensuring the efficient completion of tasks. In S51, the system collects the state data of the safe area and the working area in the mine sub-region. Among them, the passability rate Pav and the regional height difference Alt provide the passing difficulty and slope information of the robot under different path conditions. The power consumption per meter Edi represents the unit energy consumption of the robot under standard path conditions, while the obstacle height Obh reflects the potential energy consumption impact of obstacles in the path on the robot. By dimensionless processing of these parameters, the system calculates the path energy consumption evaluation value Nex, thereby quantifying the total energy consumption required for the path during actual execution.

[0103] Among them, the value range of the path energy consumption threshold R is mainly determined by the complexity of the mine environment, the battery capacity of the robot, and the task completion requirements. Usually, it is set according to the maximum energy consumption limit of the task. The specific value is generally: the energy consumption unit is usually J / m (joules per meter). In the mine environment, the typical range of the path energy consumption threshold R is 10-100 J / m, and a higher value is taken in a complex environment. The setting method is to evaluate the average energy consumption per unit path of the mine robot in different environments through experiments or simulations, and then add a certain safety margin. The value range of the path energy consumption evaluation value Nex is 15-120 J / m, and the specific value varies depending on the path length and environmental complexity.

[0104] In S52, the system compares and evaluates the path energy consumption evaluation value Nex with the preset path energy consumption threshold R to determine whether the current path is feasible within the robot's power range. After the system determines that the robot's power is insufficient, it is marked as "path optimization required" and the path optimization mode is started to generate a low-energy consumption path for the robot. This method enables the mine robot to complete tasks in an environment with limited power through accurate energy consumption evaluation, improving the energy consumption efficiency of path planning and the reliability of task completion.

[0105] Among them, the passability rate Pav represents the probability that the robot can safely pass through a certain area within a unit time. The specific quantification method is as follows: within a specific time window, count the number of obstacles in the area, including static and dynamic obstacles, and the movement speed Zsd of the dynamic obstacles. Then, combined with the environmental perception data, calculate the proportion of the area covered by obstacles in the total area. Using the obstacle density Obd and the movement frequency of dynamic obstacles as the core parameters, apply the following formula to calculate: , where Aobs represents the total area covered by obstacles, and Atotal represents the total area of the region. The value ranges from [0, 1], and the closer the value is to 1, the higher the passability rate.

[0106] The height difference Alt represents the vertical height change between the starting point and the ending point in the robot's path planning. The specific acquisition method is as follows:

[0107] Obtain three-dimensional terrain data using laser scanning equipment or high-precision topographic mapping equipment deployed in the mine; extract the height values z1 and z2 from the starting point coordinates (x1, y1, z1) and the ending point coordinates (x2, y2, z2) of the current path of the robot; calculate the height difference in combination with the following formula: , Range: The value range of the height difference Alt is usually taken between 0 and 10 meters according to the terrain characteristics of the mining area, and the specific range is determined by the complexity of the mine environment.

[0108] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A path planning method for mining robots based on artificial intelligence, characterized in that: It includes the following steps: S1. Pre-acquire the three-dimensional electronic map of the mining area environment, combine the sensor data in the mine, and lock a number of potential obstacles and dynamic change areas; then divide the mine area based on the three-dimensional electronic map to obtain several groups of mine sub-areas; secondly, preset several groups of mining robots and mark their serial numbers, and finally pair the mining robots with the mine sub-areas; S2. Real-time monitor the power state, position state and environmental perception information of the mining robots in the mine sub-areas to generate a comprehensive state set, determine and evaluate the environmental perception coefficient Rfx of the mining robots at the current position based on the comprehensive state set, and screen out the mining robots with insufficient environmental perception or plan a preliminary obstacle avoidance path for the mining robots according to the evaluation content of the environmental perception coefficient Rfx; S3. According to the situation of insufficient environmental perception of the mining robots obtained in step S2, combined with the sudden state changes in the operation environment of the mine sub-areas, real-time monitor the task processing data information of several groups of mining robots, construct a task state set, and generate the current task urgency coefficient Urg of the mining robot with serial number i based on the task state set, and adjust the path planning priority based on the task urgency coefficient Urg, and preferentially generate a dynamic path adjustment plan for the robots with urgent tasks; S4. According to the adjusted path planning priority in step S3, perform dynamic obstacle monitoring on the path where the robot with serial number i is located, combine the real-time environmental perception data, dynamic obstacle data and the motion model of the robot to generate and evaluate the environmental change coefficient Envc, and generate an advanced obstacle avoidance path according to the evaluation content of the environmental change coefficient Envc; S5. At the same time, monitor and record the state data of the safe area and the operation area in the mine sub-areas, combine the current power consumption related data of the robot with serial number i and the obstacle distribution related data in the mining area, predict and evaluate the path energy consumption evaluation value Nex for the robot to complete the current task, and finally determine whether the mining robot can successfully complete the current task and whether it needs to enter the path optimization mode; The above S1 includes S11 and S12, specifically: S11. Based on the environmental survey related data of the mining area, extract the geological data, mine structure data and geographical annotation information data of the mining area in advance to generate a three-dimensional electronic map of the mining area; S12. After obtaining the three-dimensional electronic map, the system uses various types of sensors arranged in the mine, including laser scanners, infrared sensors and ultrasonic sensors, to collect mine environment data in real time and integrate the data with the three-dimensional electronic map; according to the information feedback by the sensors, detect and lock the potential obstacles, dynamic change areas and special terrains in the mining area, and secondly mark the potential obstacles, dynamic change areas and special terrains in the mining area, including the corresponding position coordinates and dynamic attributes; The above S2 includes S21 and S22, specifically: S21. Each robot obtains the current power, geographic location coordinates, and surrounding environmental conditions through embedded sensors. Then, the remaining power value Eb, the obstacle density Obd at the current location, the mine ambient light intensity Lum, and the mine air dust concentration Dus are extracted from the comprehensive state set. The environmental perception coefficient Rfx at the current location of the mining robot is calculated using the following formula: S22. Compare and evaluate the preset environmental perception threshold Q with the environmental perception coefficient Rfx to screen out robots with insufficient environmental perception. The specific contents are as follows: When the environmental perception threshold Q is less than the environmental perception coefficient Rfx, it indicates that the robot's ability to perceive the current environment is abnormal and insufficient; the mining robot in the current mine sub-area will be marked as abnormal and replaced or adjusted abnormally; When the environmental perception threshold Q ≥ environmental perception coefficient Rfx, it indicates that the robot's ability to perceive the current environment is normal; at this time, the current mining robot performs preliminary obstacle avoidance path planning, including dynamic obstacle avoidance based on the obstacle density Obd at the current location and the task target; The S3 includes S31 and S32, specifically: S31, the task status set includes the remaining task time Rsc, the task priority weight value Ryx, and the current task completion progress value Rjd; extract the task status set, and calculate the current task urgency coefficient Urg of the mining robot with sequence number i using the following formula:

2. The method for path planning of a mining robot based on artificial intelligence according to claim 1, characterized in that: S32. Compare and evaluate the preset emergency threshold W with the task urgency coefficient Urg to generate the following evaluation content: When the task urgency coefficient Urg ≥ the emergency threshold W, it indicates that the current task is urgent. The robot will prioritize path adjustment at this time. The system will mark the robot as "task urgent" and immediately start the dynamic path adjustment mode to generate a priority path for it. When the task urgency coefficient Urg is less than the emergency threshold W, it indicates that the current task is not urgent, and the robot continues to execute according to the current path planning without additional path adjustment.

3. A path planning method for a mining robot based on artificial intelligence according to claim 1, characterized in that: S4 includes S41 and S42, specifically: S41, aggregating the real-time environment perception data, the dynamic obstacle data, and the robot's motion model data, and constructing a dynamic obstacle data set after preprocessing and dimensionless processing; The total number of dynamic obstacles Zzs, obstacle distance Zjj, obstacle relative speed Zsd, and robot turning radius Zbj in the dynamic obstacle data set are extracted, and the environment change coefficient Envc is generated by the following formula: In the formula, represents the distance between the mining robot and the j-th dynamic obstacle, represents the relative velocity between the robot and the j-th dynamic obstacle, represents the turning radius of the mining robot when interacting with the j-th obstacle.

4. A path planning method for a mining robot based on artificial intelligence according to claim 1, characterized in that: S42. Compare and evaluate the preset safety threshold Es with the environmental variation coefficient Envc. The specific evaluation contents are as follows: If the environmental variation coefficient Envc exceeds the preset safety threshold Es, the system determines that the robot's current path is risky and cannot pass safely. At this time, the system automatically generates an advanced obstacle avoidance path for the robot, including prioritizing avoiding high-risk areas and selecting a safe path with a lower obstacle density. If the environmental change coefficient Envc ≤ the preset safety threshold Es, the system determines that there is no risk in the robot's current path, and there is no need to generate a new path.

5. A path planning method for a mining robot based on artificial intelligence according to claim 1, characterized in that: S5 includes S51 and S52, specifically: S51. Among them, the status data of the safe area and the operation area in the mine sub-region include the passable rate Pav and the regional height difference Alt, and the current power consumption-related data and the obstacle distribution-related data in the mining area include the power consumption per meter distance Edi and the obstacle height Obh; after extracting the passable rate Pav, the regional height difference Alt, the power consumption per meter distance Edi, and the obstacle height Obh and performing dimensionless processing, the path energy consumption evaluation value Nex is calculated through the following formula:

6. The method for path planning of a mine robot based on artificial intelligence according to claim 1, wherein: S52. Evaluate through the preset path energy consumption threshold R and the path energy consumption evaluation value Nex. The specific content is as follows: When the path energy consumption evaluation value Nex ≤ the path energy consumption threshold R, it indicates that the energy consumption of the robot under the current path planning meets the threshold requirements; at this time, the system determines that the robot completes the task within the power range, continues to execute the task along the current path, and no path adjustment is required; When the path energy consumption evaluation value Nex > the path energy consumption threshold R, it indicates that the energy consumption of the robot under the current path planning cannot meet the threshold requirements; at this time, the system determines that the power of the robot is insufficient to support the task completion; the system marks the robot as "path optimization required", and starts the path optimization mode.

Images