Dynamic obstacle avoidance control system based on machine vision

Abstract

The invention discloses a dynamic obstacle avoidance control system based on machine vision, which relates to the technical field of machine vision and automatic control. The main scheme is: an information acquisition module acquires image information, basic machine operation and task target data in real time; an image processing module calculates obstacle influencing factor parameters and ranges, a task complexity index and an operation obstruction index according to images and operation data; a data adjustment module determines whether machine transportation will be obstructed according to a comparison result between the operation obstruction index and a threshold value, and sets an obstacle avoidance route; a predicted delay time is calculated according to the operation obstruction index, etc., and then an adaptive task speed value and a steering are obtained; a control decision module determines whether normal operation is affected by comparing the predicted delay time with a threshold set, and adjusts to an adaptive value when affected. The system improves the autonomous obstacle avoidance capability and task execution efficiency of the machine in a complex environment.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision and automatic control, and in particular to a dynamic obstacle avoidance control system based on machine vision. Background Art

[0002] In the development of modern automation and intelligence, machines face many challenges in operating in various complex environments, especially in dynamic environments, where machines need to perceive surrounding obstacles in real time, accurately assess the complexity of tasks and their own operating status, in order to achieve efficient and safe obstacle avoidance and task execution. However, current technologies often have certain limitations when dealing with these problems.

[0003] In the existing technology, some dynamic obstacle avoidance systems mainly obtain environmental information through sensors, and then perform obstacle detection and distance measurement based on this information. Some systems will also combine the machine's operating data to calculate the obstacle avoidance path and adjust the operating speed through preset algorithms. In terms of task complexity assessment, a simple graded assessment may be performed based on factors such as the number of task targets and time requirements.

[0004] Existing sensor technology may have problems such as insufficient accuracy and susceptibility to interference in certain complex environments. When calculating obstacle avoidance paths and adjusting operating speeds, existing systems often lack comprehensive consideration of task complexity and operating obstacles, resulting in low system adaptability and efficiency when tasks are complex or there are many obstacles. Existing technology is not accurate enough in calculating the impact range of obstacles, and it is difficult to fully consider the impact of various factors, which can easily lead to misjudgments or missed judgments. In terms of processing predicted delay time and adaptive adjustments, existing technology is not flexible and intelligent enough to meet the needs of different tasks and environments. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the shortcomings of the existing technology, the present invention provides a dynamic obstacle avoidance control system based on machine vision. By adopting an information acquisition module combined with machine vision technology, comprehensive data can be obtained in real time to improve the accuracy and reliability of environmental perception. By calculating the running influence coefficient data and the obstacle influence range, the system can and task complexity index , and further get the operation obstacle index On this basis, combined with machine environment parameter thresholds, image information data, and predicted delay time , Adaptive task speed value Calculate the adaptive steering angle , which can adapt to more complex tasks, and thus solve the problem in the existing technology that due to fewer considerations, the machine is prone to misjudgment or missed judgment during operation, and obstacles interfere with the operation of the machine.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a dynamic obstacle avoidance control system based on machine vision, comprising:

[0009] Information acquisition module, used to obtain image information data of the surrounding environment, basic machine operation data, task target data and real-time operation data;

[0010] Image processing module, used to calculate the impact range of obstacles based on image information data and machine basic operation data ; According to the mission target data and the impact range of obstacles , calculate the task complexity index ; Calculate the operation influence coefficient data based on the basic operation data of the machine, and calculate the operation influence coefficient data and the obstacle influence range and task complexity index , calculate the operation obstacle index ;

[0011] Data adjustment module, used to adjust the operation according to the obstacle index and Operational Obstacle Index Threshold The comparison results are used to determine whether there will be any obstruction to the machine transportation; if it is determined that there will be an obstruction, the operation obstruction index is used to determine whether there will be any obstruction to the machine transportation. , real-time operation data and mission target data, calculate the predicted delay time ; Calculate the adaptive task speed value based on the task target data and real-time operation data ; Set machine environment parameter thresholds, and predict delay time based on machine environment parameter thresholds, image information data, , Adaptive task speed value and real-time operational obstruction index , calculate the adaptive steering angle ;

[0012] The control decision module is used to predict the delay time and delay time threshold set The comparison result is used to determine whether it affects normal work. If it affects normal work, it is adjusted to the adaptive task speed value. and adaptive steering angle , the machine operates according to the adjusted operating status and path.

[0013] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: Calculate the impact range of obstacles The specific steps are:

[0014] Image information data includes the coordinates of the boundary points of obstacles and the obstacle velocity vector ;

[0015] Basic machine operating data including machine speed vector and the predicted time to reach the obstacle ;

[0016] According to the boundary point coordinates of the obstacle , calculate the center of mass coordinates of the obstacle , the specific formula is as follows:

[0017]

[0018]

[0019] in, Indicates obstacle The horizontal coordinate value of the boundary point, Indicates obstacle The vertical coordinate value of the boundary point, The value of , represents the total number of boundary points;

[0020] According to the coordinates of the center of mass of the obstacle , calculate the equivalent radius , the specific formula is as follows:

[0021]

[0022] According to the obstacle velocity vector and the machine velocity vector , calculate the relative velocity vector , the specific formula is as follows:

[0023]

[0024] According to the relative velocity vector , calculate the relative speed , the specific formula is as follows:

[0025]

[0026] The basic operation data of the machine also includes the predicted time to reach the obstacle ;

[0027] According to the equivalent radius , relative speed and the predicted time to reach the obstacle , calculate the obstacle influence range , the specific formula is as follows:

[0028] .

[0029] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: the calculation task complexity index The specific steps are:

[0030] Mission objective data including complexity , Task execution area size , obstacle density , Task deadline and the estimated time to complete the task ;

[0031] Set the maximum impact range of obstacles ;

[0032] According to the mission target data, the maximum impact range of obstacles And the impact range of obstacles , calculate the task complexity index , the specific formula is as follows:

[0033]

[0034] in, It is The complexity of each functional module, The value range is , Represents the total number of functional modules, is the comprehensive adjustment coefficient, and its value is , The obstacle influence range The adjustment parameter is .

[0035] In the preferred solution of the dynamic obstacle avoidance control system based on machine vision, the specific steps of calculating the operation influence coefficient data are:

[0036] Operational impact factor data includes performance impact factor , Stability influence coefficient , Task adaptability influence coefficient And the environmental adaptability coefficient ;

[0037] The basic operation data of the machine also includes performance data, stability data, task adaptability data and environmental adaptability data;

[0038] Performance data including average machine speed , Maximum operating speed of the machine , Machine load capacity And the maximum load capacity of the machine ;

[0039] Calculate the performance impact coefficient based on the performance data , the specific formula is as follows:

[0040]

[0041] in, The average running speed The adjustment coefficient is >0; Machine load capacity The adjustment coefficient is >0;

[0042] Stability data including machine vibration amplitude and machine noise levels ;

[0043] Calculate the stability influence coefficient based on the stability data , the specific formula is as follows:

[0044]

[0045] in, is the machine vibration amplitude The adjustment coefficient is >0; is the machine noise level The adjustment coefficient is >0;

[0046] Mission suitability data including historical mission success rates , the highest mission success rate in history And the completion time of historical tasks ;

[0047] Calculate the task adaptability impact coefficient based on the task adaptability data , the specific formula is as follows:

[0048]

[0049] in, The success rate of historical missions The adjustment coefficient is >0; Completion time of historical tasks The adjustment coefficient is >0;

[0050] Environmental adaptability data includes current ambient temperature , Current ambient humidity , the highest adaptation temperature in history , the lowest adaptation temperature in history , the highest humidity in history And the lowest humidity in history ;

[0051] Calculate the environmental adaptability impact coefficient based on the environmental adaptability data , the specific formula is as follows:

[0052]

[0053] in, Current ambient temperature The adjustment coefficient is >0; Current ambient humidity The adjustment coefficient is >0.

[0054] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: calculating the operation obstacle index The specific steps are:

[0055] Operational influence coefficient data, obstacle influence range and task complexity index , calculate the operation obstacle index , the specific formula is as follows:

[0056] .

[0057] In the preferred solution of the dynamic obstacle avoidance control system based on machine vision, the specific steps of determining whether there will be an obstacle to the machine transportation are:

[0058] Set the threshold of the operation obstacle index ;

[0059] When running the Obstacle Index ≤ When transporting the machine, it will not cause any obstruction and will be carried out along the original route;

[0060] When running the Obstacle Index > When the machine is transported, it will be blocked and the next step will be carried out.

[0061] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: calculating the predicted delay time The specific steps are:

[0062] Real-time operation data includes the real time of the machine operation process ;

[0063] Based on real-time operation data, mission target data and operation obstacle index , calculate the predicted delay time , the specific formula is as follows:

[0064]

[0065] in, To predict delay time The adjustment coefficient is a real number.

[0066] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: calculating the adaptive task speed value The specific steps are:

[0067] Real-time operation data also includes real-time remaining distance ;

[0068] According to the task deadline , real time And real-time remaining distance , calculate the adaptive task speed value , the specific formula is as follows:

[0069]

[0070] in, The value is >0.

[0071] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: calculating the adaptive steering The specific steps are:

[0072] Machine environment parameter thresholds including maximum acceptable delay time , Maximum Operation Hindering Index , Maximum machine speed And the maximum obstacle impact radius ;

[0073] According to the machine environment parameter threshold, equivalent radius , predict delay time , Adaptive task speed value and real-time operational obstruction index , adaptive steering angle , the specific formula is as follows:

[0074]

[0075] in, Represents the predicted delay time The weight coefficient is 0.1< ≤0.3, To run the obstacle index in real time The weight coefficient ranges from 0.3 ≤ ≤0.6, is the adaptive task speed value The weight coefficient is 0.2≤ ≤0.5, and + + =1.

[0076] In the preferred solution of the dynamic obstacle avoidance control system based on machine vision, the specific steps of determining whether normal operation is affected are:

[0077] Setting delay time threshold ;

[0078] When the delay time is predicted ≤ When the timeout alarm notification is not triggered;

[0079] when <Estimated delay time When the timeout alarm is triggered, the adaptive task speed value is changed. and adaptive steering angle .

[0080] (III) Beneficial effects

[0081] The present invention provides a dynamic obstacle avoidance control system based on machine vision, which has the following beneficial effects:

[0082] (1) It can obtain comprehensive and real-time image information data of the surrounding environment, basic machine operation data, and task target data, providing an accurate and timely information basis for the entire system, so that the system can fully understand the environmental conditions and task requirements of the machine, and provide a reliable basis for subsequent processing and decision-making.

[0083] (2) Calculating the impact range of obstacles helps the machine perceive possible collision risk areas in advance so that it can take avoidance measures in time and improve the safety of the machine in complex environments; calculating the task complexity index enables the system to understand the difficulty of the task, reasonably allocate resources and adjust strategies, and improve the efficiency and quality of task completion; calculating the operation hindrance index comprehensively considers multiple factors such as the operation impact coefficient data, obstacle impact range and task complexity index, providing a quantitative indicator for the system to evaluate the degree of operation hindrance, which facilitates the system to make more reasonable decisions.

[0084] (3) By comparing the operation obstacle index with the threshold, it is determined whether there is an obstacle to the machine transportation, and an obstacle avoidance route is set. The machine's action path can be planned in time to ensure the safe operation of the machine in a complex environment and improve the reliability of the system. The predicted delay time is calculated. By integrating the operation obstacle index, real-time operation data and task target data, the possible delay of the task can be accurately predicted, so that the system can be prepared in advance. The adaptive task speed value and adaptive steering angle are calculated to dynamically adjust the machine's operating speed and steering according to the actual situation, thereby improving the adaptability and flexibility of the machine in different environments and task conditions and ensuring the efficient completion of the task.

[0085] (4) By comparing the predicted delay time with the delay time threshold set, it is determined whether the normal operation is affected. Problems in task execution can be discovered in a timely manner, and corresponding measures can be taken to make adjustments to ensure the stable operation of the system. When the normal operation is affected, the task speed value and steering angle can be adjusted to the adaptive one. This allows for quick response to problems, optimization of task execution strategies, and improvement of the overall performance and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 It is a flow chart of the dynamic obstacle avoidance control system based on machine vision of the present invention. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0088] See also Figure 1 The present invention provides a dynamic obstacle avoidance control system based on machine vision, comprising:

[0089] The information acquisition module is used to obtain image information data of the surrounding environment, basic machine operation data, task target data and real-time operation data.

[0090] Specifically, the module is configured to obtain real-time image information data of the surrounding environment, including the boundary point coordinates of obstacles. and the obstacle velocity vector ; Obtain basic machine operation data in real time, including machine speed vector , predicted time to reach the obstacle , performance data, stability data, mission adaptability data, and environmental adaptability data; real-time acquisition of mission target data, including complexity , Task execution area size , obstacle density , Task deadline and the estimated time to complete the task .

[0091] Image processing module, used to calculate the impact range of obstacles based on image information data and machine basic operation data ; According to the mission target data and the impact range of obstacles , calculate the task complexity index ; Calculate the operation influence coefficient data based on the basic operation data of the machine, and calculate the operation influence coefficient data and the obstacle influence range and task complexity index , calculate the operation obstacle index .

[0092] Specifically, based on the image information data and the basic machine operation data, the influence range of the obstacle is calculated; the complexity of the task is evaluated by combining the task target data and the influence range of the obstacle, and a task complexity index is generated, which reflects the difficulty of completing the task; based on the basic machine operation data, the operation influence coefficient data is calculated, and the coefficient reflects the limitation of the machine's current state on the ability to perform the task; combined with the obstacle influence range and the task complexity index, a multi-factor comprehensive analysis is used to calculate the operation hindrance index, which quantifies the degree of hindrance encountered by the machine in a given task.

[0093] Data adjustment module, used to adjust the operation according to the obstacle index and Operational Obstacle Index Threshold The comparison results are used to determine whether there will be any obstruction to the machine transportation; if it is determined that there will be an obstruction, the operation obstruction index is used to determine whether there will be any obstruction to the machine transportation. , real-time operation data and mission target data, calculate the predicted delay time ; Calculate the adaptive task speed value based on the task target data and real-time operation data ; Set machine environment parameter thresholds, and predict delay time based on machine environment parameter thresholds, image information data, , Adaptive task speed value and real-time operational obstruction index , calculate the adaptive steering angle .

[0094] Specifically, the operation obstruction index is compared with a preset operation obstruction index threshold. If the threshold is exceeded, it is determined that an obstruction will be caused to the machine transportation, and an obstacle avoidance route is automatically generated. The operation obstruction index, real-time operation data and task target data are comprehensively considered to calculate the predicted delay time, which reflects the expected delay in task completion time without taking additional measures. Based on the predicted delay time, the adaptive task speed value and the adaptive steering angle are calculated to ensure that the task is completed in the shortest possible time and in the best way.

[0095] The control decision module is used to predict the delay time and delay time threshold set The comparison result is used to determine whether it affects normal work. If it affects normal work, it is adjusted to the adaptive task speed value. and adaptive steering angle , the machine operates according to the adjusted operating status and path.

[0096] Specifically, the predicted delay time is compared with a preset delay time threshold set to evaluate the impact of the task delay on the overall work plan; if it is determined that the delay will affect normal work, the operating state of the machine is immediately adjusted, the speed is adjusted to the calculated adaptive task speed value, and the steering is adjusted to adaptive steering to ensure that the task can be completed on time or within an acceptable delay range.

[0097] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: Calculate the impact range of obstacles The specific steps are:

[0098] The image information acquisition device is equipped with a high-resolution camera to capture the image information of the surrounding environment in real time, and use image processing algorithms, such as edge detection algorithms, to identify the outline of obstacles and determine the coordinates of each point on the boundary of the obstacle to obtain the boundary point coordinates of the obstacle. and the obstacle velocity vector .

[0099] The machine basic operation data sensor monitors the machine's operating status in real time and measures the machine's speed components in different directions to determine the machine's speed vector .

[0100] According to the boundary point coordinates of the obstacle , calculate the center of mass coordinates of the obstacle , the specific formula is as follows:

[0101]

[0102]

[0103] in, Indicates obstacle The horizontal coordinate value of the boundary point, Indicates obstacle The vertical coordinate value of the boundary point, The value of , Represents the total number of boundary points.

[0104] It should be noted that the coordinates of the center of mass are determined by summing and averaging the coordinates of the obstacle boundary points. , sum up the horizontal coordinate values ​​of all boundary points and divide by the total number of boundary points , which is based on the physical concept that the position of the center of mass in all directions is the average of the positions of all components. Similarly, for the ordinate , which is to sum up the ordinate values ​​of all boundary points and divide by , thereby determining the center of mass of the obstacle. This step provides a basic reference point for the subsequent calculation of the equivalent radius.

[0105] According to the coordinates of the center of mass of the obstacle , calculate the equivalent radius , the specific formula is as follows:

[0106] .

[0107] It should be noted that the equivalent radius is calculated using the distance relationship between the centroid coordinates and the boundary point coordinates. , calculate its centroid Distance , then sum the distances of all boundary points and divide by the total number of boundary points The equivalent radius obtained in this way can roughly characterize the size of the obstacle and simplify the obstacle of complex shape into a circle with an equivalent radius, which is convenient for subsequent calculation and analysis.

[0108] According to the obstacle velocity vector and the machine velocity vector , calculate the relative velocity vector , the specific formula is as follows:

[0109]

[0110] According to the relative velocity vector , calculate the relative speed , the specific formula is as follows:

[0111] .

[0112] It should be noted that the relative velocity is calculated by dividing the obstacle velocity vector With the machine speed vector Subtract them to get. In a two-dimensional plane, the relative velocity Quantity and Subtract the components separately, that is Then calculate the relative velocity This is based on the principle of vector synthesis, which synthesizes the components of the relative velocity in two directions into a total relative velocity, which is used to measure the relative movement speed between the obstacle and the machine.

[0113] The basic operation data of the machine also includes the predicted time to reach the obstacle .

[0114] According to the equivalent radius , relative speed and the predicted time to reach the obstacle , calculate the obstacle influence range , the specific formula is as follows:

[0115] .

[0116] It should be noted that, first of all, This part is based on the circular area formula, because the obstacle is equivalent to a circle, and its area is equal to the equivalent radius. Plus This one, is the relative velocity, It can be understood as a time factor. This means that in addition to considering the size of the obstacle itself, the range of influence that the relative speed may cause within a certain period of time is also considered. As time goes by, due to relative movement, the obstacle may have an impact on a larger range, so the product of relative speed and time is added to the calculation of the impact range, so as to more comprehensively evaluate the potential impact range of the obstacle on the movement of the machine.

[0117] First, the above formula provides an accurate basis for the subsequent determination of the key position of the obstacle by calculating the coordinates of the obstacle's mass center, which helps to analyze the characteristics of the obstacle more accurately. Calculating the equivalent radius simplifies the complex-shaped obstacle into a circle, which facilitates quantitative analysis and calculation and improves calculation efficiency. The calculation of relative speed enables the system to accurately grasp the dynamic relationship between the obstacle and the machine, providing key information for obstacle avoidance decisions. Secondly, the obstacle influence range formula comprehensively considers the impact of the obstacle's own size and relative motion, and can more comprehensively evaluate the potential threat of obstacles to machine movement and plan safe paths in advance. This helps to improve the system's obstacle avoidance accuracy and reliability, reduce collision risks, and ensure the safe operation of the machine in complex environments. It also provides important quantitative indicators for the dynamic adjustment and optimization of the system, and improves the efficiency and quality of task execution.

[0118] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: the calculation task complexity index The specific steps are:

[0119] Mission objective data including complexity , Task execution area size , obstacle density , Task deadline and the estimated time to complete the task .

[0120] By analyzing the tasks, we consider the technical difficulty involved in the tasks, the complexity of the operation steps, the depth of the required professional knowledge and other factors to score them, and then take the sum of the scores to comprehensively determine the value of the complexity. .

[0121] Determine the boundary coordinates of the task execution area through map data, positioning system, etc., and then calculate its area to obtain the size of the task execution area .

[0122] Scan and monitor the area through sensors to determine the density of obstacles .

[0123] Set the maximum impact range of obstacles according to the maximum possible size of the obstacle .

[0124] According to the mission target data, the maximum impact range of obstacles And the impact range of obstacles , calculate the task complexity index , the specific formula is as follows:

[0125]

[0126] in, It is The complexity of each functional module, The value range is , Represents the total number of functional modules, is the comprehensive adjustment coefficient, and its value is , The obstacle influence range The adjustment parameter is .

[0127] It should be noted that Represents the sum of the complexity of all functional modules. It is The complexity of each functional module can be reflected by accumulating the complexity of each functional module, which can reflect the comprehensive complexity of different functional modules of the whole system when performing tasks. and is the size of the task execution area and the obstacle density, the inverse of the task deadline It reflects the time urgency of the task. The closer the deadline is, the larger the value is, indicating that the time pressure of the task is greater, thus increasing the complexity of the task. It is the estimated time to complete the task. A longer estimated time to complete the task means more time is spent on machine operation, and a shorter estimated time to complete the task means less time is spent on machine operation. It interacts with the time factor in the numerator to jointly measure the complexity of the task in the time dimension. If the estimated time to complete the task is longer, it will increase the task complexity index. The value of is reduced, and the estimated time to complete the task is shorter, which will make the task complexity index The value of increases. in Is the obstacle influence range The adjustment parameters of It is the maximum impact range of obstacles. This part takes into account the impact of obstacles on the task. When the actual impact range of obstacles is close to the maximum impact range, the value becomes smaller and the task complexity increases relatively. Otherwise, the task complexity decreases relatively. Comprehensive adjustment coefficient , used to adjust the entire calculation result according to the actual situation to adapt to different application scenarios and task characteristics. It can be determined based on experience or experiments to ensure that the calculated task complexity index reflects the actual situation more accurately.

[0128] This formula takes into account the complexity of different parts of the system when performing tasks by summing up the complexity of each functional module, which helps to accurately assess the difficulty of the overall task and the size of the task execution area. and obstacle density It can adapt to the special requirements of different types of tasks. The use of the countdown of the task deadline and the estimated time to complete the task fully considers the impact of time factors on the complexity of the task, allowing the system to better arrange resources and plan progress. Combining the maximum impact range and actual impact range of obstacles, it can accurately measure the degree of interference of obstacles on the task and provide a basis for the formulation of obstacle avoidance strategies. The comprehensive adjustment coefficient can flexibly adjust the calculation results according to actual conditions, which improves the applicability of the formula. In short, this formula helps the system to more accurately evaluate the task complexity index, improve the efficiency and safety of task execution, and adapt to various complex application scenarios.

[0129] In the preferred solution of the dynamic obstacle avoidance control system based on machine vision, the specific steps of calculating the operation influence coefficient data are:

[0130] Operational impact factor data includes performance impact factor , Stability influence coefficient , Task adaptability influence coefficient And the environmental adaptability coefficient .

[0131] The basic machine operation data also includes performance data, stability data, task adaptability data and environmental adaptability data.

[0132] Performance data including average machine speed , Maximum operating speed of the machine , Machine load capacity And the maximum load capacity of the machine .

[0133] Calculate the performance impact coefficient based on the performance data , the specific formula is as follows:

[0134]

[0135] in, The average running speed The adjustment coefficient is >0; Machine load capacity The adjustment coefficient is >0.

[0136] It should be noted that Through experiments, the system performance is observed under different operating speed conditions, such as the efficiency and accuracy of task completion. Adjust the system performance according to the performance changes at different speeds. The value of makes the performance impact coefficient accurately reflect the actual impact of speed on system performance; Obtained through experiments. Gradually increase the load of the machine and observe the changes in system performance. Adjust the load according to the degree of impact on performance. For example, you can perform task tests under different load conditions, record the system's performance, and determine the value by analyzing the relationship between load and performance. .

[0137] The performance impact coefficient mainly considers the impact of the average operating speed and load capacity of the machine on system performance. In the formula, Indicates the ratio of the machine's current operating speed to its maximum operating speed, reflecting its speed performance. Used to adjust the weight of speed factor in performance impact. Indicates the ratio of the machine's current load capacity to its maximum load capacity, reflecting the load performance. Used to adjust the weight of load factors in performance impact. By considering these two factors comprehensively, the impact of the machine on system operation can be more comprehensively measured.

[0138] Stability data including machine vibration amplitude and machine noise levels .

[0139] Calculate the stability influence coefficient based on the stability data , the specific formula is as follows:

[0140]

[0141] in, is the machine vibration amplitude The adjustment coefficient is >0; is the machine noise level The adjustment coefficient is >0.

[0142] It should be noted that the stability of the system is determined by testing the stability of the system under different vibration amplitudes. Use vibration test equipment to simulate different degrees of vibration and observe the stability indicators of the system, such as error range, response time, etc. According to the relationship between vibration amplitude and stability, adjust The value of stability influence coefficient can accurately reflect the influence of vibration on system stability. , test the stability performance of the system under different noise levels. For example, you can run the system in different noise environments and record the changes in stability indicators to determine The value of .

[0143] The stability influence coefficient mainly considers the influence of the vibration amplitude and noise level of the machine on the system stability. In the formula, It represents the reciprocal of the machine vibration amplitude plus the reciprocal of 1. As the value increases, this value will decrease, which means that the greater the vibration amplitude, the greater the negative impact on stability. Used to adjust the weight of the vibration amplitude factor in the stability impact. The reciprocal of the machine noise level plus 1, the noise level The larger the value, the smaller it will be, which means that the higher the noise level, the greater the adverse effect on stability. Used to adjust the weight of the noise level factor in the stability impact.

[0144] Mission suitability data including historical mission success rates , the highest mission success rate in history And the completion time of historical tasks .

[0145] Calculate the task adaptability impact coefficient based on the task adaptability data , the specific formula is as follows:

[0146]

[0147] in, The success rate of historical missions The adjustment coefficient is >0; Completion time of historical tasks The adjustment coefficient is >0.

[0148] It should be noted that based on the statistical analysis of historical task data and the relationship between success rate and system performance, the The value of to accurately reflect the impact of success rate on task adaptability; by evaluating the system adaptability under different task completion times to determine , analyze the relationship between task completion time and system resource utilization efficiency, user satisfaction and other factors, and adjust The value of makes the task adaptability influence coefficient can reasonably reflect the impact of completion time on system adaptability.

[0149] The task adaptability impact coefficient mainly considers the impact of historical task success rate and task completion time on the system's ability to adapt to tasks. In the formula, It indicates the ratio of the historical task success rate to the theoretical maximum success rate. The higher the success rate, the stronger the system's ability to adapt to tasks. Used to adjust the weight of the success rate factor in the impact of task adaptability. It represents the reciprocal of the task completion time plus the reciprocal of the task completion time. The shorter the task completion time, the larger this value is, which means the system has better adaptability to the task. Used to adjust the weight of the task completion time factor in the impact of task adaptability.

[0150] Environmental adaptability data includes current ambient temperature , Current ambient humidity , the highest adaptation temperature in history , the lowest adaptation temperature in history , the highest humidity in history And the lowest humidity in history .

[0151] Calculate the environmental adaptability impact coefficient based on the environmental adaptability data , the specific formula is as follows:

[0152]

[0153] in, Current ambient temperature The adjustment coefficient is >0; Current ambient humidity The adjustment coefficient is >0.

[0154] It should be noted that the performance and stability of the system are tested under different temperature conditions, the operation of the system under various temperatures is recorded, and the relationship between temperature and system adaptability is analyzed to determine value; conduct humidity test experiments, run the system in different humidity environments, observe the changes in system performance and stability, and adjust the system according to the relationship between humidity and system adaptability. The value of .

[0155] The environmental adaptability coefficient mainly considers the impact of the current ambient temperature and humidity on the system's adaptability to running in different environments. In the formula, Indicates the relationship between the current ambient temperature and the temperature adaptation range. When the current temperature is in the middle of the temperature adaptation range, this value is close to 0.5, indicating that the system has good environmental adaptability at this temperature. Used to adjust the weight of temperature factors in the impact of environmental adaptability. Indicates the relationship between the current ambient humidity and the humidity adaptation range. Similarly, this value reflects the environmental adaptability of the system under the current humidity. Used to adjust the weight of humidity factor in the impact of environmental adaptability.

[0156] These formulas can comprehensively and accurately evaluate the comprehensive impact of the machine's operating status on the system by considering the influencing factors of performance, stability, task adaptability, and environmental adaptability, and calculating the operating impact coefficient data in a quantitative manner. For the performance impact coefficient, combined with the average operating speed and load capacity, resource allocation can be optimized and task execution efficiency can be improved. The stability impact coefficient considers the vibration amplitude and noise level, which helps to improve the reliability and stability of the system. The task adaptability impact coefficient can better adapt to different task requirements based on the historical task success rate and completion time. The environmental adaptability impact coefficient focuses on temperature and humidity, so that the system can operate stably in different environments. These formulas provide a scientific basis for the dynamic adjustment and optimization of the system, improve the overall performance and adaptability of the dynamic obstacle avoidance control system based on machine vision, and ensure the safe and efficient operation of the system in complex environments.

[0157] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: calculating the operation obstacle index The specific steps are:

[0158] Operational influence coefficient data, obstacle influence range and task complexity index , calculate the operation obstacle index , the specific formula is as follows:

[0159] .

[0160] It should be noted that the purpose of this formula is to calculate the operation obstacle index , to quantify the degree of obstacles faced by the machine in the process of performing tasks. It comprehensively considers multiple factors such as operation impact coefficient data, obstacle impact range and task complexity index; This part combines the influence coefficients of four different aspects, representing the influence of machine performance, stability, task adaptability and environmental adaptability on system operation. By multiplying these four coefficients and taking the square root, a comprehensive influence factor can be obtained, which reflects the contribution of the overall operation status of the machine to the degree of obstruction. If any of the coefficients is low, it may increase the degree of obstruction of the system; is the square of the obstacle’s impact range, indicating that the degree of obstruction to the system operation is closely related to the obstacle’s impact range. The larger the range, the greater the possible obstruction. The square operation further emphasizes the importance of the obstacle’s impact range to the obstruction index. Here, the task complexity index is introduced. , and process it through logarithmic operation. The higher the task complexity index, the more difficult the task itself is, which may increase the obstacles to the operation of the system. Logarithmic operation can alleviate the impact of the growth of the task complexity index on the obstacle index to a certain extent, making its change smoother. At the same time, adding 1 is to avoid =0 is the case where the logarithm is undefined.

[0161] This formula comprehensively considers the operating influence coefficients of various aspects such as performance, stability, task adaptability and environmental adaptability, and can comprehensively evaluate the impact of the machine's operating status on the degree of obstruction, providing a more accurate basis for system optimization. The square term of the obstacle's impact range highlights the importance of the obstacle size in the obstruction index, allowing the system to more keenly perceive the challenges brought by obstacles. The introduction of the task complexity index and the use of logarithmic operations not only consider the impact of the difficulty of the task itself on the obstruction, but also avoid the excessive growth of the obstruction index due to the high task complexity index. The operation obstruction index calculated by this formula helps the system to adjust its strategy in a timely manner, such as setting obstacle avoidance routes, adjusting speed and steering, etc., to improve the adaptability and safety of the system in complex environments, ensure the efficient execution of tasks, and reduce the risk of collision. At the same time, it also provides scientific quantitative indicators for the dynamic optimization and resource allocation of the system.

[0162] In the preferred solution of the dynamic obstacle avoidance control system based on machine vision, the specific steps of determining whether there will be an obstacle to the machine transportation are:

[0163] Set the threshold of the operation obstacle index .

[0164] When running the Obstacle Index ≤ When transporting the machine, there will be no obstruction and the machine will be transported along the original route.

[0165] When running the Obstacle Index > When the machine is transported, it will be blocked and the next step will be carried out.

[0166] It should be noted that the distribution of the operation obstruction index in the historical operation data can be analyzed. Find out the historical data that obviously cause the machine transportation to be affected to different degrees. Based on these values, For example, the historical data of the machine transportation that caused some minor problems but still basically functioned normally Value as The reference value will cause serious obstruction to the transportation of the machine or make it impossible to carry out the normal operation. The value is used as a reference value for obstacles to machine transportation.

[0167] When running the Obstacle Index ≤ When , it means that the machine transportation is not hindered. When the operation obstacle index does not exceed this threshold, it indicates that the machine does not hinder the machine transportation during the execution of the task and executes according to the original route.

[0168] When running the Obstacle Index > When , it means that the machine transportation is blocked. When this threshold is exceeded, it means that the machine faces great difficulties in performing the task in the current environment, and measures need to be taken to ensure safety and continue to complete the task.

[0169] By setting different thresholds for the operation obstacle index, the degree of obstacle faced by the machine transportation can be accurately judged. When the obstacle is light, the machine can perform the task along the original route, avoiding unnecessary route adjustments and waste of resources, and improving the efficiency of task execution. When the obstacle is large, the system can detect it in time and take corresponding measures to ensure the safety of the machine and the continuation of the task. This solution helps to improve the stability and reliability of the system. When faced with obstacles of different degrees, the system can make reasonable decisions based on the actual situation, reducing the risk of task failure due to unexpected situations. At the same time, clear threshold standards also make the operation of the system more standardized and predictable. This solution improves the intelligence level of the system. It can automatically identify the degree of obstacle and take corresponding actions, reducing the need for manual intervention and improving the system's autonomous decision-making ability. This has important practical application value for complex dynamic obstacle avoidance control systems.

[0170] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: calculating the predicted delay time The specific steps are:

[0171] Real-time operation data includes the real time of the machine operation process .

[0172] Based on real-time operation data, mission target data and operation obstacle index , calculate the predicted delay time , the specific formula is as follows:

[0173]

[0174] in, To predict delay time The adjustment coefficient is a real number.

[0175] It should be noted that in different actual scenarios, the machine is asked to perform various tasks and the operation obstacle index, real-time time, task deadline and actual predicted delay time under different circumstances are recorded. For different task scenarios, different adjustment coefficient values ​​are tried to observe the degree of closeness between the calculated predicted delay time and the actual situation. According to the experimental results, the value of the adjustment coefficient is continuously adjusted until the calculated predicted delay time is consistent with the actual situation. The value of .

[0176] The purpose of this formula is to calculate the time , that is, predicting the remaining time from the current moment to the task deadline, and considering the impact of the operation obstacle index on the predicted delay time. , here the role is to adjust the predicted delay time according to the operation obstacle index. When the operation obstacle index is large, it means that the machine transportation faces greater obstacles and may cause more delays. At this time, the predicted delay time is increased by adjusting the coefficient and the inverse of the operation obstacle index. The adjustment coefficient is used to adjust this impact according to the actual situation to obtain a more accurate prediction result. , represents the remaining time from the current moment to the task deadline. This value reflects the theoretical remaining time without considering the operation obstacle index. In summary, the formula calculates a more accurate prediction delay time by considering the impact of the operation obstacle index on the predicted delay time and combining it with the remaining time from the current moment to the task deadline, providing a basis for the system's decision-making.

[0177] By introducing the factor of multiplying the inverse of the operation obstacle index and the adjustment coefficient, the formula can dynamically reflect the impact of the degree of obstacles faced by machine transportation on the predicted delay time. When the obstacle is large, the predicted delay time is increased accordingly, so that the system can prepare for the response in advance and adjust the task strategy. Secondly, combined with the difference between the task deadline and the real-time time, the time urgency of the task is fully considered, providing the system with an intuitive reference for the remaining time. The setting of the adjustment coefficient can be flexibly adjusted according to actual conditions, which improves the applicability and accuracy of the formula. This helps the system to plan the task progress more accurately, select appropriate obstacle avoidance routes and transportation methods, and improve the efficiency and reliability of machine transportation. At the same time, it also provides a scientific basis for the system's decision-making, ensuring that the task can be completed on time in a complex environment, reducing the cost and risk caused by delays, and improving the performance of the entire dynamic obstacle avoidance control system based on machine vision.

[0178] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: calculating the adaptive task speed value The specific steps are:

[0179] Real-time operation data also includes real-time remaining distance .

[0180] According to the task deadline , real time And real-time remaining distance , calculate the adaptive task speed value , the specific formula is as follows:

[0181]

[0182] in, The value is >0.

[0183] It should be noted that the purpose of this formula is to calculate the adaptive task speed value To ensure that the machine can dynamically adjust the task speed when facing different operating conditions and obstacles, thereby improving the efficiency and safety of task execution. Represents the remaining task distance. As the task progresses, The value of will change continuously, reflecting the status of the current task. It represents the remaining time from the current moment to the task deadline, and takes into account the impact of the operation obstacle index on the predicted delay time.

[0184] By combining the task progress-related parameters with the predicted remaining time, the formula can dynamically adjust the adaptive task speed value according to the actual task situation and time urgency. When the remaining distance is small and time is tight, the speed is increased to ensure that the task is completed on time, achieving a balance between the efficiency and accuracy of task execution. When faced with various complex operating conditions and environmental changes, it can better meet the needs of different tasks. This formula helps to improve the intelligence level of the machine, enabling it to autonomously adjust its speed to cope with different obstacles and time pressures, reduce delays or waste of resources caused by unreasonable speed, and improve the performance of the entire dynamic obstacle avoidance control system based on machine vision, ensuring that the task is completed efficiently under the premise of safety.

[0185] In the preferred solution of the above-mentioned dynamic obstacle avoidance control system based on machine vision: calculating the adaptive steering The specific steps are:

[0186] Machine environment parameter thresholds including maximum acceptable delay time , Maximum Operation Hindering Index , Maximum machine speed And the maximum obstacle impact radius .

[0187] According to the machine environment parameter threshold, equivalent radius , predict delay time , Adaptive task speed value and real-time operational obstruction index , calculate the adaptive steering angle , the specific formula is as follows:

[0188]

[0189] in, Represents the predicted delay time The weight coefficient is 0.1< ≤0.3, To run the obstacle index in real time The weight coefficient ranges from 0.3 ≤ ≤0.6, is the adaptive task speed value The weight coefficient is 0.2≤ ≤0.5, and + + =1.

[0190] It should be noted that the maximum acceptable delay time is determined based on specific mission requirements and objectives. ; Test the system in different simulation environments or actual scenarios, gradually increase the number of obstacles, complexity and task difficulty, and record the corresponding operation obstacle index. When the system performance is significantly reduced or the task cannot be performed normally, the operation obstacle index at this time can be used as the maximum operation obstacle index Reference value; check the technical specifications of the machine to find out the maximum speed of the machine ; For different types of obstacles, analyze their possible maximum impact range. For example, for a large spherical obstacle, the maximum impact range radius can be determined based on its radius; for irregularly shaped obstacles, the maximum obstacle impact range radius can be estimated by simulating the maximum impact distance that may be produced in different directions.

[0191] The purpose of this formula is to calculate the adaptive steering angle , so that the machine can adjust the steering angle according to different factors during dynamic obstacle avoidance to ensure safe and efficient completion of the task. Indicates the ratio of the predicted delay time to the maximum acceptable delay time. When the predicted delay time approaches or exceeds the maximum acceptable delay time, this ratio will increase. Weight coefficient Used to adjust the impact of the predicted delay time on adaptive steering. If it is larger, it means that the system pays more attention to the impact of the predicted delay time on steering, and may adopt a more aggressive steering strategy to reduce delays when the predicted delay time is large.

[0192] It is the ratio of the real-time operation obstacle index to the maximum operation obstacle index. When the operation obstacle index is larger, this ratio will increase. Weight coefficient Controls the effect of the running obstacle index on adaptive steering. If it is large, it means that the system will be more inclined to adjust the steering according to the obstacle index when the running obstacle is large, so as to avoid obstacles and reduce obstacles.

[0193] It is the ratio of the adaptive task speed value to the maximum speed of the machine, reflecting the relationship between the current task speed and the maximum speed. It is the ratio of the radius of the current obstacle influence range to the radius of the maximum obstacle influence range, reflecting the relative size of the current obstacle influence range. Adjust the effect of the combination of these two factors on adaptive steering. When the speed is fast and the obstacle has a large impact range, the impact of this part may increase, prompting the system to adjust the steering to adapt to this situation. In general, by comprehensively considering factors such as predicted delay time, operation obstruction index, adaptive task speed value, and obstacle impact range, and adjusting according to the weight coefficients of different factors, this formula enables the machine to flexibly adjust the steering angle according to actual conditions in the dynamic obstacle avoidance control system to achieve the best obstacle avoidance effect and task execution efficiency. At the same time, due to + + =1, which ensures that the influence of each factor is within a reasonable range and that no one factor excessively dominates the steering decision.

[0194] The formula comprehensively considers key factors such as predicted delay time, operation obstruction index, adaptive task speed value, and obstacle influence range, which can comprehensively reflect various situations of the machine in the dynamic obstacle avoidance process, making the steering decision more scientific and reasonable. Through different weight coefficients, the influence degree of each factor can be flexibly adjusted according to the actual task requirements and environmental characteristics, which improves the adaptability of the system. When facing urgent time constraints, the weight of the predicted delay time may increase, prompting the machine to adjust the steering as soon as possible to reduce delays. In the case of dense obstacles or large obstacles, the weight of the operation obstruction index will play a greater role to ensure safe obstacle avoidance. Combined with the adaptive task speed value and obstacle influence range, it can make appropriate steering decisions under different speeds and obstacle conditions, improve the efficiency and safety of task execution, and provide a precise and flexible steering control method for the dynamic obstacle avoidance control system based on machine vision.

[0195] In the preferred solution of the dynamic obstacle avoidance control system based on machine vision, the specific steps of determining whether normal operation is affected are:

[0196] Setting delay time threshold .

[0197] When the delay time is predicted ≤ When the timeout alarm notification is not triggered.

[0198] when <Estimated delay time When the timeout alarm is triggered, the adaptive task speed value is changed. and adaptive steering angle .

[0199] It should be noted that a large number of tests were conducted in different actual scenarios, allowing the machine to run under various task conditions and record the predicted delay time under different conditions; observing the performance of the machine under different delay conditions and the degree of impact on the task, dividing different delay intervals, and thus determining approximate range.

[0200] Threshold Represents a critical value of the predicted delay time. When the predicted delay time is less than this value, it indicates that the current task progress is within an acceptable time range, the system runs relatively normally, and there is no need to trigger a timeout alarm notification.

[0201] When the delay time is predicted ≤ , keep the current adaptive task speed value unchanged and continue to execute the task according to the established speed strategy. This means that if the previous speed is the optimal speed calculated based on factors such as task progress and running obstacle index, then this speed will continue to be maintained if it does not exceed the threshold to ensure efficient execution of the task. Also keep the current adaptive steering angle unchanged. In this case, the system believes that the current steering strategy can effectively avoid obstacles and move towards the task goal, and no adjustment is required. The system will continue to operate according to the original steering angle and path planning to ensure the smooth progress and safety of the task.

[0202] when <Estimated delay time When the The steering angle will be increased to improve the efficiency of task execution; when an obstacle is detected, when an obstacle appears in front of the machine at a close distance, the system may calculate a larger steering angle to quickly avoid the obstacle. As the task goal changes and the environment changes dynamically, the steering angle will also be adjusted continuously. If the location of the task goal changes or a new obstacle appears, the system will recalculate the steering angle to ensure that the machine can move towards the new goal and avoid the new obstacle.

[0203] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware or in combination with computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0204] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0205] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A dynamic obstacle avoidance control system based on machine vision, characterized by: include: Information acquisition module, used to obtain image information data of the surrounding environment, basic machine operation data, task target data and real-time operation data; Image processing module, used to calculate the impact range of obstacles based on image information data and machine basic operation data ; Calculate the impact range of obstacles The specific steps are: Image information data includes the coordinates of the boundary points of obstacles and the obstacle velocity vector ; Basic machine operating data including machine speed vector and the predicted time to reach the obstacle ; According to the boundary point coordinates of the obstacle , calculate the center of mass coordinates of the obstacle , the specific formula is as follows: in, Indicates obstacle The horizontal coordinate value of the boundary point, Indicates obstacle The vertical coordinate value of the boundary point, The value of , represents the total number of boundary points; According to the coordinates of the center of mass of the obstacle , calculate the equivalent radius , the specific formula is as follows: According to the obstacle velocity vector and the machine velocity vector , calculate the relative velocity vector , the specific formula is as follows: According to the relative velocity vector , calculate the relative speed The specific formula is as follows: According to the equivalent radius , relative speed and the predicted time to reach the obstacle , calculate the obstacle influence range , the specific formula is as follows: According to the mission target data and the impact range of obstacles , calculate the task complexity index ; Calculate the task complexity index The specific steps are: Mission objective data including complexity , Task execution area size , obstacle density , Task deadline and the estimated time to complete the task ; Set the maximum impact range of obstacles ; According to the mission target data, the maximum impact range of obstacles And the impact range of obstacles , calculate the task complexity index The specific announcements are as follows: in, It is The complexity of each functional module, The value range is , Represents the total number of functional modules, is the comprehensive adjustment coefficient, and its value is , The obstacle influence range The adjustment parameter is ; Calculate the operation influence coefficient data based on the basic operation data of the machine, and calculate the operation influence coefficient data and the obstacle influence range. and task complexity index , calculate the operation obstacle index ; The specific steps for calculating the operation impact coefficient data are: Operational impact factor data includes performance impact factor , Stability influence coefficient , Task adaptability influence coefficient And the environmental adaptability coefficient ; The basic operation data of the machine also includes performance data, stability data, task adaptability data and environmental adaptability data; Performance data including average machine speed , Maximum operating speed of the machine , Machine load capacity And the maximum load capacity of the machine ; Calculate the performance impact coefficient based on the performance data , the specific formula is as follows: in, The average running speed The adjustment coefficient is >0; Machine load capacity The adjustment coefficient is >0; Stability data including machine vibration amplitude and machine noise levels ; Calculate the stability influence coefficient based on the stability data The specific formula is as follows: in, is the machine vibration amplitude The adjustment coefficient is >0; is the machine noise level The adjustment coefficient is >0; Mission suitability data including historical mission success rates , the highest mission success rate in history And the completion time of historical tasks ; Calculate the task adaptability impact coefficient based on the task adaptability data , the specific formula is as follows: in, The success rate of historical missions The adjustment coefficient is >0; Completion time of historical tasks The adjustment coefficient is >0; Environmental adaptability data includes current ambient temperature 、Current ambient humidity , the highest adaptation temperature in history , the lowest adaptation temperature in history , the highest humidity in history And the lowest humidity in history ; Calculate the environmental adaptability impact coefficient based on the environmental adaptability data , the specific formula is as follows: in, Current ambient temperature The adjustment coefficient is >0; Current ambient humidity The adjustment coefficient is >0; Calculating the Operational Hindering Index The specific steps are: Operational influence coefficient data, obstacle influence range and task complexity index , calculate the operation obstacle index , the specific formula is as follows: Data adjustment module, used to adjust the operation according to the obstacle index and Operational Obstacle Index Threshold The comparison results are used to determine whether there will be any obstruction to the machine transportation; if it is determined that there will be an obstruction, the operation obstruction index is used to determine whether there will be any obstruction to the machine transportation. , real-time operation data and mission target data, calculate the predicted delay time ; Calculate the predicted delay time The specific steps are: Real-time operation data includes the real time of the machine operation process ; Based on real-time operation data, mission target data and operation obstacle index , calculate the predicted delay time , the specific formula is as follows: in, To predict delay time The adjustment coefficient is a real number; Calculate the adaptive mission speed value based on mission target data and real-time operation data ; Calculate the adjusted adaptive task speed value The specific steps are: Real-time operation data also includes real-time remaining distance ; According to the task deadline , real time And real-time remaining distance , calculate the adaptive task speed value The specific formula is as follows: in, The value is >0; Set machine environment parameter thresholds, and predict delay time based on machine environment parameter thresholds, image information data, and , Adaptive task speed value and real-time operational obstruction index Calculating adaptive steering angle ; Calculate adaptive steering The specific steps are: Machine environment parameter thresholds including maximum acceptable delay time , Maximum Operation Hindering Index , Maximum machine speed And the maximum obstacle impact radius ; According to the machine environment parameter threshold, equivalent radius , predict delay time , Adaptive task speed value and real-time operational obstruction index , calculate the adaptive steering angle , the specific formula is as follows: in, Represents the predicted delay time The weight coefficient is 0.1< ≤0.3, To run the obstacle index in real time The weight coefficient ranges from 0.3 ≤ ≤0.6, is the adaptive task speed value The weight coefficient is 0.2≤ ≤0.5, and + + =1; The control decision module is used to predict the delay time and delay time threshold set The comparison result is used to determine whether it affects normal work. If it affects normal work, it is adjusted to the adaptive task speed value. and adaptive steering angle , the machine operates according to the adjusted operating status and path.

2. The dynamic obstacle avoidance control system based on machine vision according to claim 1, characterized in that: The specific steps to determine whether there will be obstacles to the transportation of the machine are: Set the threshold of the operation obstacle index ; When running the Obstacle Index ≤ When transporting the machine, it will not cause any obstruction and will be carried out along the original route; When running the Obstacle Index > When the machine is transported, it will be blocked and the next step will be carried out.

3. The dynamic obstacle avoidance control system based on machine vision according to claim 2, characterized in that: The specific steps to determine whether normal operation is affected are: Setting delay time threshold ; When the delay time is predicted ≤ When the timeout alarm notification is not triggered; when <Estimated delay time When the timeout alarm is triggered, the adaptive task speed value is changed. and adaptive steering angle .

Images