Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a mining robot path planning method based on artificial intelligence, which solves the technical defects of insufficient environment perception, weak self-adaptability and limited intelligent decision making capability in the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: A mining robot path planning method based on artificial intelligence comprises the following steps:
S1, acquiring a three-dimensional electronic map of a mining area environment in advance, combining sensor data in a mine, and locking a plurality of potential barriers and dynamic change areas;
S2, monitoring the electric energy state, the position state and the environment perception information of the mining robots in the mine subareas in real time to generate a comprehensive state set, determining and evaluating the environment perception coefficient Rfx of the mining robots at the current position based on the comprehensive state set, and screening out mining robots with insufficient environment perception or planning a first-order obstacle avoidance path for the mining robots according to the evaluation content of the environment perception coefficient Rfx;
S3, according to the situation that the environment of the mining robot obtained in the S2 is insufficient in perception, in combination with the sudden state change of the working environment of the mine subarea, task processing data information of a plurality of groups of mining robots is monitored in real time, a task state set is constructed, a current task emergency degree coefficient Urg of the mining robot with a sequence number of i is generated according to the task state set, a path planning priority is adjusted based on the task emergency degree coefficient Urg, and a dynamic path adjustment scheme is preferentially generated for the task emergency robots;
s4, carrying out dynamic obstacle monitoring on the path of the robot with the sequence number i according to the path planning priority adjusted in the step S3, generating and evaluating an environment change coefficient Envc by combining real-time environment sensing data, dynamic obstacle data and a motion model of the robot, and generating a progressive obstacle avoidance path according to the evaluation content of the environment change coefficient Envc;
S5, monitoring and recording state data of a safety area and a working area in a mine subarea, and predicting and evaluating a path energy consumption evaluation value Nex of a robot finishing a current task by combining current power consumption related data of the robot with a serial number i and obstacle distribution related data in a mining area to finally determine whether the mining robot can finish the current task smoothly and whether a path optimization mode is required to be entered.
Preferably, S1 includes S11 and S12, specifically:
s11, extracting geological data, mine structure data and geographic marking information data of the mining area from the environmental survey related data of the mining area in advance, and then generating a three-dimensional electronic map of the mining area;
s12, after the three-dimensional electronic map is obtained, the system acquires mine environment data in real time through a plurality of sensors arranged in the mine, including laser scanning, infrared sensors and ultrasonic sensors, and integrates the mine environment data with the three-dimensional electronic map, then detects and locks potential barriers, dynamic change areas and special terrains in the mine according to information fed back by the sensors, and marks the potential barriers, the dynamic change areas and the special terrains in the mine, including corresponding position coordinates and dynamic properties.
Preferably, S2 includes S21 and S22, specifically:
S21, each robot acquires current electric quantity, geographical position coordinates and surrounding environment conditions through an embedded sensor, then extracts a residual electric quantity value Eb, a barrier density Obd at the current position, mine environment illumination intensity Lum and mine area air dust concentration Dus in a comprehensive state set, and calculates and acquires an environment perception coefficient Rfx of the current position of the mining robot through the following formula:
。
Preferably, the method comprises the steps of,
S22, comparing and evaluating a preset environment perception threshold Q and an environment perception coefficient Rfx, and screening robots with insufficient environment perception, wherein the specific contents are as follows:
When the environment perception threshold Q is smaller than the environment perception coefficient Rfx, the environment perception threshold Q indicates that the environment perception capability of the robot to the current position is abnormal and the condition of insufficient perception exists;
When the environment perception threshold Q is more than or equal to the environment perception coefficient Rfx, the environment perception capability of the robot on the current position is normal, and planning a primary obstacle avoidance path of the current mining robot at the moment, wherein the planning comprises the steps of dynamically avoiding the obstacle according to the obstacle density Obd of the current position and the task target;
preferably, S3 includes S31 and S32, specifically:
s31, extracting a task state set, and calculating and obtaining a current task emergency degree coefficient Urg of the mining robot with the sequence number i by the following formula, wherein the task state set comprises a task remaining time Rsc, a task priority weight value Ryx and a current task completion progress value Rjd:
。
Preferably, the method comprises the steps of,
S32, comparing and evaluating the preset emergency threshold W with the task emergency degree coefficient Urg to generate the following evaluation contents:
when the task emergency degree coefficient Urg is more than or equal to the emergency threshold W, the current task is indicated to have emergency, and the robot preferably executes path adjustment at the moment. The system marks the robot as 'task emergency', and immediately starts a dynamic path adjustment mode to generate a priority path for the robot, so that the task is completed in time.
When the task urgency coefficient Urg is smaller than the urgency threshold W, the current task is indicated to have no urgency, and the robot continues to execute according to the current path planning without additional path adjustment.
Preferably, S4 includes S41 and S42, specifically:
s41, summarizing real-time environment perception data, dynamic obstacle data and motion model data of a robot, and constructing a dynamic obstacle data set after preprocessing and dimensionless processing, wherein the environment change coefficient Envc is generated by extracting the total number Zzs of dynamic obstacles, the obstacle distance Zjj, the relative speed Zsd of the obstacles and the turning radius Zbj of the robot in the dynamic obstacle data set through the following formula:
In the formula,Representing the distance between the mining robot and the jth dynamic obstacle,Indicating the relative speed of the robot to the jth dynamic barrier,Indicating the turning radius of the mining robot when interacting with the jth obstacle.
Preferably, the method comprises the steps of,
S42, comparing and evaluating the safety threshold Es with the environmental change coefficient Envc, wherein the specific evaluation content is as follows:
If the environmental change coefficient Envc is greater than a preset safety threshold Es, the system judges that the current path of the robot has risk and cannot pass safely;
If the environmental change coefficient Envc is less than or equal to the preset safety threshold Es, the system judges that the current path of the robot is not at risk, and a brand new path is not required to be generated at the moment.
Preferably, S5 includes S51 and S52, specifically:
S51, state data of a safety area and an operation area in a mine subarea comprise passable rate Pav and area height difference Alt, current power consumption related data and obstacle distribution related data in a mining area comprise electric energy consumption Edi and obstacle height Obh per meter, after the passable rate Pav, the area height difference Alt, the electric energy consumption Edi per meter and the obstacle height Obh are extracted for dimensionless processing, a path energy consumption evaluation value Nex is calculated through the following formula:
。
Preferably, the method comprises the steps of,
S52, evaluating through a preset path energy consumption threshold R and a path energy consumption evaluation value Nex, wherein the specific contents are as follows:
when the path energy consumption evaluation value Nex is less than or equal to the path energy consumption threshold value R, the energy consumption of the robot under the current path planning meets the threshold value requirement;
When the path energy consumption evaluation value Nex > is equal to the path energy consumption threshold value R, the energy consumption of the robot under the current path planning cannot meet the threshold value requirement, at the moment, the system judges that the electric energy of the robot is insufficient to support the task to finish, marks the robot as 'path optimization requirement', and starts a path optimization mode.
The invention provides a mining robot path planning method based on artificial intelligence. The beneficial effects are as follows:
(1) The mining robot path planning method based on artificial intelligence effectively solves the problem of insufficient dynamic adaptability of path planning by introducing an environment perception coefficient Rfx, an environment change coefficient Envc and a dynamic obstacle monitoring mechanism, the system generates an environment change coefficient Envc by monitoring a potential obstacle dynamic change area and special topography in a mine subarea in real time and carrying out dimensionless processing on the total number of dynamic obstacles Zzs, the obstacle distance Zjj, the relative speed Zsd of the obstacles and the steering radius Zbj of the robot by combining sensor feedback data, dynamically generates an obstacle avoidance path according to a comparison evaluation result of Envc and a safety threshold Es, avoids collision or task interruption caused by incapability of recognizing environment change, and improves the path planning accuracy and safety of the mining robot in a complex mine environment.
(2) The mining robot path planning method based on artificial intelligence aims at the problem that task priority is insufficient to achieve resource optimization allocation, a dynamic adjustment mechanism of task emergency degree coefficients Urg is provided according to the technical scheme, task residual duration Rsc in a task state set, task priority weight values Ryx and current task completion progress values Rjd are extracted and formula calculation is conducted, task emergency degree coefficients Urg are dynamically evaluated in combination with task emergency threshold W, when the task emergency degree coefficients Urg are greater than or equal to the task emergency threshold W, mark that a robot is a task emergency, a dynamic path adjustment scheme is preferentially generated, fine management of task allocation of the mining robot is achieved, response speed of emergency tasks is remarkably improved, and overall utilization efficiency of mining area resources is optimized.
(3) The mining robot path planning method based on artificial intelligence aims to solve the problems of insufficient energy consumption assessment and electric quantity management, and provides a dynamic prediction method of a path energy consumption assessment value Nex; the method comprises the steps of carrying out dimensionless processing on electric energy consumption Edi, barrier height Obh, passable rate Pav and area height difference Alt of each meter, calculating a path energy consumption evaluation value Nex, carrying out evaluation by combining a path energy consumption threshold value R, marking the robot as a path optimization requirement by a system when the path energy consumption evaluation value Nex is larger than the path energy consumption threshold value R, starting a path optimization mode to avoid task failure or the situation that the robot stays in a dangerous area due to insufficient electric quantity, guaranteeing the task completion rate and the high efficiency of energy consumption management of the mining robot, and reducing the potential safety hazard of mine operation.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the invention provides a mining robot path planning method based on artificial intelligence, which comprises the following steps:
S1, acquiring a three-dimensional electronic map of a mining area environment in advance, combining sensor data in a mine, and locking a plurality of potential barriers and dynamic change areas;
S2, monitoring the electric energy state, the position state and the environment perception information of the mining robots in the mine subareas in real time to generate a comprehensive state set, determining and evaluating the environment perception coefficient Rfx of the mining robots at the current position based on the comprehensive state set, and screening out mining robots with insufficient environment perception or planning a first-order obstacle avoidance path for the mining robots according to the evaluation content of the environment perception coefficient Rfx;
S3, according to the situation that the environment of the mining robot obtained in the S2 is insufficient in perception, in combination with the sudden state change of the working environment of the mine subarea, task processing data information of a plurality of groups of mining robots is monitored in real time, a task state set is constructed, a current task emergency degree coefficient Urg of the mining robot with a sequence number of i is generated according to the task state set, a path planning priority is adjusted based on the task emergency degree coefficient Urg, and a dynamic path adjustment scheme is preferentially generated for the task emergency robots;
s4, carrying out dynamic obstacle monitoring on the path of the robot with the sequence number i according to the path planning priority adjusted in the step S3, generating and evaluating an environment change coefficient Envc by combining real-time environment sensing data, dynamic obstacle data and a motion model of the robot, and generating a progressive obstacle avoidance path according to the evaluation content of the environment change coefficient Envc;
S5, monitoring and recording state data of a safety area and a working area in a mine subarea, and predicting and evaluating a path energy consumption evaluation value Nex of a robot finishing a current task by combining current power consumption related data of the robot with a serial number i and obstacle distribution related data in a mining area to finally determine whether the mining robot can finish the current task smoothly and whether a path optimization mode is required to be entered.
In the embodiment, step S1 locks potential barriers and dynamic change areas by acquiring a three-dimensional electronic map of the mining area environment and combining sensor data in a mine, and simultaneously divides the mine into subareas and pairs the subareas with mining robots, so that basic area division and primary environment recognition capability are provided for path planning; step S2, generating a comprehensive state set by monitoring the electric energy state, the position state and the environment sensing information of the mining robot in real time, calculating the environment sensing coefficient Rfx of the current position, screening out robots with insufficient environment sensing, generating a first-order obstacle avoidance path for the robots, and improving the sensing precision and safety of the robots in complex mining area environments; step S3, a dynamic path adjustment scheme is generated for the task emergency robot by constructing a task state set and generating a task emergency degree coefficient Urg and adjusting the path planning priority based on the task emergency degree, so that the task emergency robot can respond to sudden changes in a mining area in time, the task completion efficiency and adaptability are improved, step S4 generates an environment change coefficient Envc according to dynamic obstacle data, real-time environment perception data and a robot motion model, a progressive obstacle avoidance path is generated through evaluation, the collision risk of the robot in the dynamic environment is effectively reduced, the path safety is guaranteed, step S5 monitors and records the state data of a safety area and an operation area in a mine subarea, current electric energy consumption data and obstacle distribution data are combined, a path energy consumption evaluation value Nex is calculated, and therefore whether the robot can complete the task smoothly or needs to enter a path optimization mode is evaluated, and efficient completion of the task and optimal selection of the path are guaranteed under electric energy limitation.
Example 2
S1 comprises S11 and S12, and specifically comprises the following steps:
s11, extracting geological data, mine structure data and geographic marking information data of the mining area from the environmental survey related data of the mining area in advance, and then generating a three-dimensional electronic map of the mining area;
s12, after the three-dimensional electronic map is obtained, the system acquires mine environment data in real time through a plurality of sensors arranged in the mine, including laser scanning, infrared sensors and ultrasonic sensors, and integrates the mine environment data with the three-dimensional electronic map, then detects and locks potential barriers, dynamic change areas and special terrains in the mine according to information fed back by the sensors, and marks the potential barriers, the dynamic change areas and the special terrains in the mine, including corresponding position coordinates and dynamic properties.
In the embodiment, the step S1 provides comprehensive environmental data support and dynamic monitoring basis for mining robot path planning through operations comprising the steps S11 and S12, and in the step S11, a formatted three-dimensional electronic map is generated by extracting geological data, mine structure data and geographic marking information of a mining area, so that the system has basic geographic structure information of the mining area;
in S12, the system acquires mine environment data in real time by utilizing laser scanning, an infrared sensor and an ultrasonic sensor, integrates the mine environment data with a three-dimensional electronic map, detects and locks potential obstacles, dynamic change areas and special terrains in a mining area by combining sensor feedback information, and marks position coordinates and dynamic properties of the key areas at the same time, so that the system can continuously acquire accurate and dynamic space information in a complex mining area environment;
the method comprises the specific processes of detecting and locking potential barriers, dynamic change areas and special terrains in a mining area, wherein a laser scanning sensor scans a three-dimensional space of the mining area to generate preliminary contour data of the barriers and measure position coordinates of the preliminary contour data, an infrared sensor captures thermal signal changes to identify heat source moving tracks of the dynamic areas, an ultrasonic sensor detects surface concave-convex characteristics in a mine through sound wave reflection to identify the special terrains, all sensor data are transmitted to a central processing unit in real time, multi-source information is integrated through a data fusion technology, the moving trend, the heat source strength changes and the terrain complexity of the barriers are analyzed through a specific dynamic change model, the system classifies and marks analysis results, including boundary attributes of the static barriers and the dynamic change areas and risk grades of the special terrains, and stores the positions and the dynamic attributes of the static barriers and the boundary attributes in a three-dimensional electronic map, so that real-time calling of the analysis results in a robot path planning process is ensured, and the perception precision and safety of the mine environment are improved.
Example 3
S2 comprises S21 and S22, and specifically comprises the following steps:
S21, each robot acquires current electric quantity, geographical position coordinates and surrounding environment conditions through an embedded sensor, then extracts a residual electric quantity value Eb, a barrier density Obd at the current position, mine environment illumination intensity Lum and mine area air dust concentration Dus in a comprehensive state set, and calculates and acquires an environment perception coefficient Rfx of the current position of the mining robot through the following formula:
s22, comparing and evaluating a preset environment perception threshold Q and an environment perception coefficient Rfx, and screening robots with insufficient environment perception, wherein the specific contents are as follows:
When the environment perception threshold Q is smaller than the environment perception coefficient Rfx, the environment perception threshold Q indicates that the environment perception capability of the robot to the current position is abnormal and the condition of insufficient perception exists;
When the environment perception threshold Q is more than or equal to the environment perception coefficient Rfx, the environment perception capability of the robot on the current position is normal, and planning a primary obstacle avoidance path of the current mining robot at the moment, wherein the planning comprises the steps of dynamically avoiding the obstacle according to the obstacle density Obd of the current position and the task target;
s3 comprises S31 and S32, and specifically comprises the following steps:
s31, extracting a task state set, and calculating and obtaining a current task emergency degree coefficient Urg of the mining robot with the sequence number i by the following formula, wherein the task state set comprises a task remaining time Rsc, a task priority weight value Ryx and a current task completion progress value Rjd:
s32, comparing and evaluating the preset emergency threshold W with the task emergency degree coefficient Urg to generate the following evaluation contents:
when the task emergency degree coefficient Urg is more than or equal to the emergency threshold W, the current task is indicated to have emergency, and the robot preferably executes path adjustment at the moment. The system marks the robot as 'task emergency', and immediately starts a dynamic path adjustment mode to generate a priority path for the robot, so that the task is ensured to be completed in time;
When the task urgency coefficient Urg is smaller than the urgency threshold W, the current task is indicated to have no urgency, and the robot continues to execute according to the current path planning without additional path adjustment.
S4 includes S41 and S42, specifically:
s41, summarizing real-time environment perception data, dynamic obstacle data and motion model data of a robot, and constructing a dynamic obstacle data set after preprocessing and dimensionless processing, wherein the environment change coefficient Envc is generated by extracting the total number Zzs of dynamic obstacles, the obstacle distance Zjj, the relative speed Zsd of the obstacles and the turning radius Zbj of the robot in the dynamic obstacle data set through the following formula:
In the formula,Representing the distance between the mining robot and the jth dynamic obstacle,Indicating the relative speed of the robot to the jth dynamic barrier,Indicating the turning radius of the mining robot when interacting with the jth obstacle.
S42, comparing and evaluating the safety threshold Es with the environmental change coefficient Envc, wherein the specific evaluation content is as follows:
If the environmental change coefficient Envc is greater than a preset safety threshold Es, the system judges that the current path of the robot has risk and cannot pass safely;
If the environmental change coefficient Envc is less than or equal to the preset safety threshold Es, the system judges that the current path of the robot is not at risk, and a brand new path is not required to be generated at the moment.
In the embodiment, accurate sensing, self-adaptive adjustment and intelligent path optimization of robots in a mining area are realized through the steps, in S2, each robot acquires current electric quantity, geographical position coordinates and surrounding environment conditions through an embedded sensor, extracts residual electric quantity Eb in a comprehensive state set, obstacle density Obd at the current position, mine environment illumination intensity Lum and mine area air dust concentration Dus, generates an environment sensing coefficient Rfx through calculation, is used for evaluating the current sensing capability of the robot to ensure timely replacement or adjustment of the path when the sensing is insufficient, wherein the obstacle density Obd is used for reflecting the complexity degree of the mine environment, acquires mine environment data in real time through a plurality of types of sensors distributed in the mine, including a laser scanner, an ultrasonic sensor and an infrared sensor, counts the obstacle quantity in a sensor coverage area, calculates the obstacle quantity in the unit area through combining with the geographical position coordinates, and acquires the environment sensing threshold Q through experimental calibration, generally sets according to the environment complexity degree, and takes a value range of generally 0.1-1, and takes a specific environment sensing coefficient Rfx of generally 0.0-0.0.
S3, generating a task emergency degree coefficient Urg by using a task residual duration Rsc, a task priority weight value Ryx and a current task completion progress value Rjd, judging whether a priority path adjustment is required to be performed or not by comparing the task emergency degree coefficient Urg with a preset emergency threshold W, ensuring that an emergency task can be completed in time, wherein the task emergency degree coefficient Urg is calculated by using a task residual duration Rsc (unit is seconds) and a task priority weight value Ryx (0-1), and is generally in a value range of 0-10, the emergency threshold W is set according to the time sensitivity of a mining area task, and is generally in a value range of 5-8, meanwhile, a dynamic path adjustment mode comprises combining motion model data of a robot, generating a new path set in real time by using a dynamic path planning algorithm, then preferentially selecting a path with lower barrier density and a minimum dynamic change area risk and a path with an energy consumption evaluation value Nex being smaller than or equal to a path energy consumption threshold R as a priority path, simultaneously, marking a high risk area in real time and notifying a robot, and notifying the robot of the high risk area, and continuously monitoring the path in a dynamic change state of the path adjustment mode after the path is continuously performed by a system, and the robot is in a dynamic state, and the dynamic state is in a dynamic state is continuously adjusted when the dynamic state is in a state, and the dynamic state is in the optimal state is continuously monitored by the path adjustment mode:
in case 1, the original path of the robot is planned to pass through a mine road with a larger gradient, the density of obstacles is higher, and the area has landslide risk. After the system detects that the path is not feasible, a channel which bypasses more safely is selected, and even if the energy consumption of the path is higher, the path is still selected preferentially for ensuring the safety and completing the task in time;
The system monitors that a new obstacle (such as falling rock) appears on the other path of the mine, after the path is re-planned, the robot is guided to bypass the obstacle, the updated path can avoid the obstacle, timeliness of the task can be ensured, and the shortest path planning is completed;
In S4, summarizing real-time environment sensing data, dynamic obstacle data and motion model data of the robot, and constructing a dynamic obstacle data set after preprocessing and dimensionless processing, wherein the specific construction process of the dynamic obstacle data set is as follows:
Preprocessing data collected by a laser scanning, ultrasonic sensors and infrared sensors by using a multi-mode data fusion technology, including data cleaning, noise reduction and format unification, adopting a dimensionless method to carry out dimensionless processing on parameters such as distance, speed and number of dynamic obstacles so as to uniformly construct a dynamic obstacle data set, wherein the specific dimensionless processing is as follows: X represents the value of the original parameter, xmin represents the minimum value of the original parameter, and Xmax represents the maximum value of the original parameter.
The method comprises the steps of generating an environment change coefficient Envc through a dynamic obstacle total number Zzs, an obstacle distance Zjj, an obstacle relative speed Zsd and a robot steering radius Zbj, evaluating the safety of a path and generating a progressive obstacle avoidance path when necessary, guaranteeing the safety and path continuity of the robot in a dynamic complex environment, acquiring and evaluating each lower parameter, realizing the comprehensive monitoring of the mining area working environment, providing accurate data support in path planning, enabling the system to have self-adaption and intelligent decision making capability, and guaranteeing the efficient completion and operation safety of the robot task, wherein the safety threshold Es is preset according to the safety grade and the risk tolerance of the mine environment based on the total number Zzs (in units of numbers) of the obstacles, the obstacle distance Zjj (in units of meters, in the range of 0-5 meters) and the robot steering radius Zbj (in units of meters, in the range of 0.1-10 meters) of the dynamic obstacle data set, and the safety threshold Es is usually 5-7.
Example 4
S5 includes S51 and S52, specifically:
S51, state data of a safety area and an operation area in a mine subarea comprise passable rate Pav and area height difference Alt, current power consumption related data and obstacle distribution related data in a mining area comprise electric energy consumption Edi and obstacle height Obh per meter, after the passable rate Pav, the area height difference Alt, the electric energy consumption Edi per meter and the obstacle height Obh are extracted for dimensionless processing, a path energy consumption evaluation value Nex is calculated through the following formula:
the path energy consumption threshold R and the path energy consumption evaluation value Nex are preset for evaluation, and the specific contents are as follows:
when the path energy consumption evaluation value Nex is less than or equal to the path energy consumption threshold value R, the energy consumption of the robot under the current path planning meets the threshold value requirement;
When the path energy consumption evaluation value Nex > is equal to the path energy consumption threshold value R, the energy consumption of the robot under the current path planning cannot meet the threshold value requirement, at the moment, the system judges that the electric energy of the robot is insufficient to support the task to finish, marks the robot as 'path optimization requirement', and starts a path optimization mode.
In S51, the system collects state data of a safety area and an operation area in a mine subarea, wherein the passable rate Pav and the area height difference Alt provide passing difficulty and gradient information of the robot under different path conditions, the electric energy consumption Edi per meter distance represents unit energy consumption of the robot under standard path conditions, and the barrier height Obh reflects potential energy consumption influence of barriers in the path on the robot;
The method mainly comprises the steps of determining a path energy consumption threshold R according to the complexity of a mine environment, the capacity of a robot battery and the task completion requirement, wherein the value range is generally set according to the maximum energy consumption limit of the task, the specific numerical value is generally that the energy consumption unit is generally J/m, in the mine environment, the typical range of the path energy consumption threshold R is 10-100J/m, the value is higher in the complex environment, the setting mode is to evaluate the average energy consumption of a unit path of the mining robot in different environments through experiments or simulation, and then a certain safety margin is added, wherein the value range of a path energy consumption evaluation value Nex is 15-120J/m, and the specific numerical value is different according to the path length and the environment complexity;
in S52, the system judges whether the current path is feasible within the electric energy range of the robot by comparing and evaluating the path energy evaluation value Nex with a preset path energy threshold R, and marks as a path optimization requirement and starts a path optimization mode after judging that the electric energy of the robot is insufficient to generate a low-energy-consumption path for the robot;
the specific quantification method comprises the steps of counting the number of the obstacles in a certain area, including static and dynamic obstacles and the moving speed Zsd of the dynamic obstacles, in a specific time window, calculating the proportion of the area of the covered area of the obstacle to the total area by combining environment sensing data, and calculating by taking the density Obd of the obstacle and the moving frequency of the dynamic obstacle as core parameters, wherein the passing rate Pav represents the probability that the robot can safely pass in a unit time in the certain area: Wherein Aobs represents the total area covered by the obstacle, atotal represents the total area of the area, and the value is [0,1], wherein the closer the value is to 1, the higher the passing rate is;
the height difference Alt represents the vertical height change between the starting point and the end point in the robot path planning, and the specific acquisition method is as follows:
The method comprises the steps of obtaining three-dimensional topographic data by using laser scanning equipment or high-precision topographic mapping equipment arranged in a mine, extracting height values z1 and z2 in a starting point coordinate (x 1, y1, z 1) and an ending point coordinate (x 2, y2, z 2) of a current path of a robot, and calculating a height difference by combining the following formulas: the range of the height difference Alt is usually 0-10 m according to the topography characteristics of the mining area, and the specific range is determined by the complexity of the mine environment.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.