An underground autonomous driving route planning system based on artificial intelligence

Abstract

The present invention relates to the technical field of route planning, and in particular to an underground automatic driving route planning system based on artificial intelligence, comprising an underground route planning platform, an information retrieval unit, an obstruction driving analysis unit, a driving risk supervision unit, a route planning analysis unit, a route tracking management unit and a display management unit; the present invention analyzes the road condition risk and driving of a feasible route to provide data support for subsequent route selection, so as to reduce the underground automatic driving risk of a target vehicle, and performs information fusion planning evaluation analysis by means of information feedback and information fusion, and then selects an accurate and optimal driving path to ensure the safety of the underground automatic driving of the target vehicle, and at the same time performs driving deviation supervision analysis through the actual driving angle, so as to timely adjust the underground driving route of the target vehicle to ensure the accuracy of the driving route of the target vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of route planning, and in particular to an underground automatic driving route planning system based on artificial intelligence. Background Art

[0002] Coal mining and production is a typical high-risk and arduous industry. Using underground unmanned vehicles to replace existing manually driven vehicles is one of the inevitable ways to achieve digital and intelligent production in coal mines, and is also an emerging development direction in the field of energy mining. The significance of underground autonomous driving route planning is to improve safety redundancy and transportation efficiency, reduce system costs, and meet the functions of underground autonomous driving panoramic interaction, vehicle group scheduling, emergency remote intervention, etc.

[0003] However, in the prior art, there are many paths obtained by the driving path planning of the underground autonomous driving vehicle, and it is impossible to reasonably screen the planned paths, which affects the operating safety and stability of the underground autonomous driving vehicle, and is not conducive to the stable control and obstacle avoidance efficiency of the underground autonomous driving vehicle. It is also impossible to safely supervise the selected planned paths, and thus it is impossible to timely optimize the selected planned paths. At the same time, it is impossible to reasonably repair or change the route according to the changing trend of the road damage, which is not conducive to the stable driving of the underground autonomous driving vehicle;

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an underground autonomous driving route planning system based on artificial intelligence to solve the above-mentioned technical defects. The present invention analyzes the road condition risk and driving of the feasible route to provide data support for subsequent route selection, so as to reduce the underground autonomous driving risk of the target vehicle. The information fusion planning evaluation analysis is performed through information feedback and information fusion, and then an accurate and optimal driving path is selected to ensure the underground autonomous driving safety of the target vehicle. At the same time, the driving deviation supervision analysis is performed through the actual driving angle to timely adjust the underground driving route of the target vehicle to ensure the accuracy of the driving route of the target vehicle. At the same time, the road damage trend of the selected route is deeply analyzed, so that the selected route of the target vehicle can be repaired or changed in time to ensure the driving stability of the target vehicle.

[0006] The object of the present invention can be achieved by the following technical solutions: an underground automatic driving route planning system based on artificial intelligence, comprising an underground route planning platform, an information retrieval unit, an obstruction driving analysis unit, a driving risk supervision unit, a route planning analysis unit, a route tracking management unit and a display management unit;

[0007] After receiving the planning instruction, the information retrieval unit immediately retrieves the road condition data and driving data of the feasible route, and sends them to the obstruction driving analysis unit and the driving risk supervision unit respectively;

[0008] After receiving the road condition data, the obstruction driving analysis unit immediately performs driving risk supervision feedback analysis on the road condition data to obtain a driving risk assessment coefficient F;

[0009] After receiving the driving data, the driving risk supervision unit immediately performs a driving defect assessment feedback operation on the driving data to obtain a driving defect assessment coefficient G;

[0010] The route planning and analysis unit is used to perform information fusion planning and evaluation analysis on the driving risk evaluation coefficient F and the driving defect evaluation coefficient G to obtain a selection signal and a screening signal. When the screening signal is generated, the obtained intersection risk value is analyzed to obtain an optimal route;

[0011] The route tracking management unit is used to perform driving deviation supervision analysis on the selected route, compare and analyze the obtained allowable offset value, obtain a stable signal and an adjustment signal, and when a stable signal is generated, compare and analyze the obtained road damage risk index, and send the obtained management signal to the display management unit.

[0012] Preferably, the driving risk supervision feedback analysis process of the hindering driving analysis unit is as follows:

[0013] The starting point and target destination of the target vehicle are collected, and then multiple driving routes between the starting point and the target destination of the target vehicle are obtained, and the driving routes are set as feasible routes. The road condition data of each feasible route is obtained. The road condition data includes the collision risk value PZ and the obstacle avoidance assessment value BZ, and the driving risk assessment coefficient F is obtained according to the formula.

[0014] Preferably, the collision risk value indicates the duration of time during which the minimum vertical distance between the target vehicle and the collision object while driving on the feasible route is less than a preset threshold; the obstacle avoidance evaluation value indicates that the road area occupied by potholes in the feasible route is greater than a preset threshold, and the depth of the potholes is greater than the number of potholes corresponding to the preset depth threshold.

[0015] Preferably, the driving defect assessment feedback operation process of the driving risk supervision unit is as follows:

[0016] S1: Acquire the driving data of each feasible route, the driving data including the energy consumption evaluation value and the driving time, the energy consumption evaluation value represents the ratio between the total driving energy consumption and the driving distance, and then obtain the product value obtained by multiplying the energy consumption evaluation value and the driving time after data normalization, and set it as the driving evaluation value SP;

[0017] S2: Obtain the corridor interference value CG of each feasible route. The corridor interference value CG indicates the ratio between the length of the corresponding section when the value corresponding to the environmental parameter exceeds the preset threshold and the total length. The environmental parameters include electromagnetic interference value and dust concentration. The driving defect assessment coefficient G is obtained according to the formula.

[0018] Preferably, the information fusion planning evaluation and analysis process of the route planning analysis unit is as follows:

[0019] The feasible route is marked as i, where i is a natural number greater than zero, and the driving risk assessment coefficient Fi and driving defect assessment coefficient Gi of each feasible route are obtained. The driving risk assessment coefficient Fi and driving defect assessment coefficient Gi are substituted into the formula The priority behavior evaluation coefficient of each feasible route is obtained, where v1 is the preset error compensation coefficient, v1 is greater than zero, and Ri is the priority behavior evaluation coefficient of each feasible route. Then, the minimum value of the priority behavior evaluation coefficient Ri is obtained and marked as the optional path value Rmin, and the optional path value Rmin is discriminated and analyzed:

[0020] If the optional path value Rmin is unique, a selection signal is generated;

[0021] If the uniqueness of the optional path value Rmin is not satisfied, a screening signal is generated.

[0022] Preferably, when the route planning and analysis unit generates a screening signal:

[0023] The feasible route corresponding to the screening signal is obtained and set as the alternative route, the number of intersections of each alternative route is obtained, and the number of intersections of each alternative route is set as the intersection risk value, and then the minimum value of the intersection risk value is obtained, and the alternative route corresponding to the minimum value of the intersection risk value is set as the preferred route.

[0024] Preferably, the driving deviation supervision and analysis process of the route tracking management unit is as follows:

[0025] The selected route of the target vehicle is obtained, and the selected route represents a feasible route or a preferred route corresponding to the selection signal, and then the driving route trajectory of the selected route is generated, and the driving route trajectory of the generated selected route is set as the planned trajectory line. At the same time, the actual trajectory line of the target vehicle traveling on the selected route is obtained, and then the overlapping sections and deviated sections between the actual trajectory line and the planned trajectory line are obtained, and the area of ​​the area enclosed by the actual trajectory line and the planned trajectory line corresponding to the deviated section is obtained, and it is set as the allowable offset value, and the allowable offset value is compared and analyzed with the preset allowable offset value threshold value stored in the internal input:

[0026] If the ratio between the allowed offset value and the preset allowed offset value threshold is less than 1, a stable signal is generated;

[0027] If the ratio between the allowable offset value and the preset allowable offset value threshold is greater than or equal to 1, an adjustment signal is generated.

[0028] Preferably, when the route tracking management unit generates a stable signal:

[0029] The duration of the next period of time is obtained and set as the time threshold. The time threshold is divided into g sub-time nodes, where g is a natural number greater than zero. The obstacle avoidance evaluation value of the selected route in each sub-time node is obtained. A rectangular coordinate system is established with the number of sub-time nodes as the X-axis and the obstacle avoidance evaluation value as the Y-axis. The obstacle avoidance evaluation value curve is drawn by plotting points, and the growth trend value of the obstacle avoidance evaluation value curve is obtained. The growth trend value of the obstacle avoidance evaluation value curve is set as the road damage risk index, and the road damage risk index is compared and analyzed with the preset road damage risk index threshold value stored in the internal input:

[0030] If the ratio between the road damage risk index and the preset road damage risk index threshold is less than 1, no signal is generated;

[0031] If the ratio between the road loss risk index and the preset road loss risk index threshold is greater than or equal to 1, a management signal is generated.

[0032] The beneficial effects of the present invention are as follows:

[0033] (1) The present invention analyzes the road condition risk and driving of the feasible route to provide data support for subsequent route selection, so as to reduce the underground autonomous driving risk of the target vehicle, that is, the road condition data is analyzed for driving risk supervision feedback to understand the driving risk of each feasible route, and the driving defect assessment feedback operation is performed on the driving data to analyze the driving energy consumption and driving environment to understand the driving defect of each feasible route;

[0034] (2) The present invention performs information fusion planning evaluation analysis through information feedback and information fusion, and then selects an accurate and optimal driving path to ensure the safety of the target vehicle's underground automatic driving. At the same time, the driving deviation supervision analysis is performed through the actual driving angle, so as to timely adjust the underground driving route of the target vehicle to ensure the accuracy of the target vehicle's driving route. At the same time, the road damage trend of the selected route is deeply analyzed, so that the selected route of the target vehicle can be repaired or changed in time to ensure the driving stability of the target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention will be further described below in conjunction with the accompanying drawings;

[0036] Figure 1 It is a flowchart of the system of the present invention;

[0037] Figure 2 This is a local analysis diagram of Example 1 of the present invention. DETAILED DESCRIPTION

[0038] 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.

[0039] Embodiment 1:

[0040] See also Figure 1 to Figure 2 As shown, the present invention is an underground automatic driving route planning system based on artificial intelligence, including an underground route planning platform, an information retrieval unit, an obstruction driving analysis unit, a driving risk supervision unit, a route planning analysis unit, a route tracking management unit and a display management unit, the underground route planning platform is in a one-way communication connection with the information retrieval unit, the information retrieval unit is in a one-way communication connection with the obstruction driving analysis unit and the driving risk supervision unit, the obstruction driving analysis unit and the driving risk supervision unit are in a one-way communication connection with the route planning analysis unit, the route planning analysis unit is in a one-way communication connection with the route tracking management unit and the display management unit, and the route tracking management unit is in a one-way communication connection with the display management unit;

[0041] When the underground route planning platform generates a planning instruction, the planning instruction is sent to the information retrieval unit. After receiving the planning instruction, the information retrieval unit immediately retrieves the road condition data and driving data of the feasible route, and sends them to the obstruction driving analysis unit and the driving risk supervision unit respectively. After receiving the road condition data, the obstruction driving analysis unit immediately performs driving risk supervision feedback analysis on the road condition data to understand the driving risk situation of each feasible route. The specific driving risk supervision feedback analysis process is as follows:

[0042] The starting point and the target destination of the target vehicle are collected, and then multiple driving routes between the starting point and the target destination of the target vehicle are obtained, and the driving routes are set as feasible routes. The road condition data of each feasible route is obtained. The road condition data includes collision risk value and obstacle avoidance evaluation value. The collision risk value and obstacle avoidance evaluation value are marked as PZ and BZ respectively. According to the formula Obtaining a driving risk assessment coefficient, wherein a1 and a2 are respectively preset proportional factor coefficients of the collision risk value and the obstacle avoidance assessment value, the proportional factor coefficients are used to correct the deviations of various parameters in the formula calculation process, so as to make the calculation result more accurate, a3 is a preset fault tolerance factor coefficient, a1, a2 and a3 are all greater than zero, and F is a driving risk assessment coefficient, and the driving risk assessment coefficient F is sent to the route planning analysis unit;

[0043] In the embodiment of the present invention, the collision risk value indicates the duration of time during which the minimum vertical distance between the target vehicle and the collision object is less than a preset threshold value during the driving process of the feasible route. It should be noted that the analysis is performed from the perspective of the collision risk duration to understand the driving risk of each feasible route;

[0044] In the embodiment of the present invention, the obstacle avoidance evaluation value indicates that the road area occupied by the pits in the feasible route is greater than the preset threshold, and the depth of the pits is greater than the number of pits corresponding to the preset depth threshold. It should be noted that the analysis is performed from the perspective of road conditions to understand the driving risk of each feasible route;

[0045] After receiving the driving data, the driving risk supervision unit immediately performs driving defect assessment feedback operation on the driving data, so as to analyze the driving energy consumption and driving environment from two points of view, so as to understand the driving defect situation of each feasible route. The specific driving defect assessment feedback operation process is as follows:

[0046] The driving data of each feasible route is obtained, the driving data includes an energy consumption evaluation value and a driving time, the energy consumption evaluation value represents the ratio between the total driving energy consumption and the driving distance, and then the product value obtained by multiplying the energy consumption evaluation value and the driving time after data normalization processing is obtained, and the product value obtained by multiplying the energy consumption evaluation value and the driving time after data normalization processing is set as the driving evaluation value SP. It should be noted that the driving evaluation value SP is an influencing parameter reflecting the advantage of the feasible route. The smaller the value of the driving evaluation value SP is, the greater the advantage of the feasible route is;

[0047] The corridor interference value CG of each feasible route is obtained. The corridor interference value CG indicates the ratio between the length of the corresponding road section when the value corresponding to the environmental parameter exceeds the preset threshold and the total length. The environmental parameters include electromagnetic interference value, dust concentration, etc. It should be noted that the underground driving environment factors affect the perception and control system of the unmanned vehicle. The corridor interference value CG is an influencing parameter reflecting the driving risk of the feasible route;

[0048] According to the formula A driving defect assessment coefficient is obtained, wherein f1 and f2 are preset weight factor coefficients of the driving assessment value and the corridor interference value respectively, f3 is a preset correction factor coefficient, f1, f2 and f3 are all greater than zero, G is the driving defect assessment coefficient, and the driving defect assessment coefficient G is sent to the route planning analysis unit.

[0049] Embodiment 2:

[0050] The route planning and analysis unit is used to perform information fusion planning, evaluation and analysis on the driving risk assessment coefficient F and the driving defect assessment coefficient G, and then select an accurate and optimal driving path, while reducing the underground automatic driving risk of the target vehicle. The specific information fusion planning, evaluation and analysis process is as follows:

[0051] The feasible route is marked as i, where i is a natural number greater than zero, and the driving risk assessment coefficient Fi and driving defect assessment coefficient Gi of each feasible route are obtained. The driving risk assessment coefficient Fi and driving defect assessment coefficient Gi are substituted into the formula The priority behavior evaluation coefficient of each feasible route is obtained, where v1 is the preset error compensation coefficient, v1 is greater than zero, and Ri is the priority behavior evaluation coefficient of each feasible route. Then, the minimum value of the priority behavior evaluation coefficient Ri is obtained and marked as the optional path value Rmin, and the optional path value Rmin is discriminated and analyzed:

[0052] If the optional path value Rmin is unique, a selection signal is generated and sent to the display management unit. After receiving the selection signal, the display management unit immediately displays the feasible route number corresponding to the selection signal, thereby selecting an accurate and optimal selection path, while reducing the risk of underground automatic driving of the target vehicle;

[0053] If the uniqueness of the optional path value Rmin is not satisfied, a screening signal is generated. When the screening signal is generated, the feasible route corresponding to the screening signal is obtained and set as the alternative route. The number of intersections of each alternative route is obtained, and the number of intersections of each alternative route is set as the intersection risk value, and then the minimum value of the intersection risk value is obtained, and the alternative route corresponding to the minimum value of the intersection risk value is set as the preferred route, and the preferred route is sent to the display management unit. After receiving the preferred route, the display management unit immediately displays the number corresponding to the preferred route, so as to accurately and optimally select the path, while reducing the risk of underground automatic driving of the target vehicle;

[0054] The route tracking management unit is used to perform driving deviation supervision and analysis on the selected route, so as to timely adjust the underground driving route of the target vehicle to ensure the safety of the underground automatic driving of the target vehicle. The specific driving deviation supervision and analysis process is as follows:

[0055] The selected route of the target vehicle is obtained, and the selected route represents a feasible route or a preferred route corresponding to the selection signal, and then the driving route trajectory of the selected route is generated, and the driving route trajectory of the generated selected route is set as the planned trajectory line. At the same time, the actual trajectory line of the target vehicle traveling on the selected route is obtained, and then the overlapping sections and deviated sections between the actual trajectory line and the planned trajectory line are obtained, and the area of ​​the area enclosed by the actual trajectory line and the planned trajectory line corresponding to the deviated section is obtained, and it is set as the allowable offset value, and the allowable offset value is compared and analyzed with the preset allowable offset value threshold value stored in the internal input:

[0056] If the ratio between the allowed offset value and the preset allowed offset value threshold is less than 1, a stable signal is generated;

[0057] If the ratio between the allowed offset value and the preset allowed offset value threshold is greater than or equal to 1, an adjustment signal is generated and sent to the display management unit. After receiving the adjustment signal, the display management unit immediately displays the preset warning text corresponding to the adjustment signal, so as to timely adjust the deviation section of the target vehicle to ensure the driving safety and driving route accuracy of the target vehicle;

[0058] When a stable signal is generated, the duration of the next period of time is obtained and set as the time threshold. The time threshold is divided into g sub-time nodes, where g is a natural number greater than zero. The obstacle avoidance evaluation value of the selected route in each sub-time node is obtained. A rectangular coordinate system is established with the number of sub-time nodes as the X-axis and the obstacle avoidance evaluation value as the Y-axis. An obstacle avoidance evaluation value curve is drawn by plotting points, and the growth trend value of the obstacle avoidance evaluation value curve is obtained. The growth trend value of the obstacle avoidance evaluation value curve is set as the road damage risk index, and the road damage risk index is compared and analyzed with the preset road damage risk index threshold value stored in the internal input:

[0059] If the ratio between the road damage risk index and the preset road damage risk index threshold is less than 1, no signal is generated;

[0060] If the ratio between the road damage risk index and the preset road damage risk index threshold is greater than or equal to 1, a management signal is generated and sent to the display management unit. After receiving the management signal, the display management unit immediately displays the preset warning text corresponding to the management signal, so as to timely repair or change the selected route of the target vehicle to ensure the driving safety and driving stability of the target vehicle;

[0061] In summary, the present invention analyzes the road condition risk and driving of the feasible route to provide data support for subsequent route selection, so as to reduce the risk of underground automatic driving of the target vehicle, that is, the road condition data is subjected to driving risk supervision feedback analysis to understand the driving risk of each feasible route, and the driving data is subjected to driving defect assessment feedback operation to analyze from the two points of driving energy consumption and driving environment to understand the driving defect of each feasible route, and information fusion planning evaluation analysis is performed through information feedback and information fusion, so as to select an accurate and optimal driving path to ensure the safety of underground automatic driving of the target vehicle, and at the same time, driving deviation supervision analysis is performed from the perspective of actual driving, so as to timely adjust the underground driving route of the target vehicle to ensure the accuracy of the driving route of the target vehicle, and at the same time, the road damage trend of the selected route is deeply analyzed, so as to timely repair or change the selected route of the target vehicle to ensure the driving stability of the target vehicle.

[0062] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0063] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. An underground automatic driving route planning system based on artificial intelligence, characterized in that: It includes an underground route planning platform, an information retrieval unit, an obstacle driving analysis unit, a driving risk supervision unit, a route planning analysis unit, a route tracking management unit and a display management unit; After receiving the planning instruction, the information retrieval unit immediately retrieves the road condition data and driving data of the feasible route, and sends them to the obstruction driving analysis unit and the driving risk supervision unit respectively; After receiving the road condition data, the obstruction driving analysis unit immediately performs driving risk supervision feedback analysis on the road condition data to obtain a driving risk assessment coefficient F; After receiving the driving data, the driving risk supervision unit immediately performs a driving defect assessment feedback operation on the driving data to obtain a driving defect assessment coefficient G; The route planning and analysis unit is used to perform information fusion planning and evaluation analysis on the driving risk evaluation coefficient F and the driving defect evaluation coefficient G to obtain a selection signal and a screening signal. When the screening signal is generated, the obtained intersection risk value is analyzed to obtain an optimal route; The route tracking management unit is used to perform driving deviation supervision analysis on the selected route, compare and analyze the obtained allowable deviation value, obtain a stable signal or an adjustment signal, and when a stable signal is generated, compare and analyze the obtained road damage risk index, and send the obtained management signal to the display management unit; The driving risk supervision feedback analysis process of the hindering driving analysis unit is as follows: The starting point and the target destination of the target vehicle are collected, and then multiple driving routes between the starting point and the target destination of the target vehicle are obtained, and the driving routes are set as feasible routes, and the road condition data of each feasible route is obtained. The road condition data includes a collision risk value PZ and an obstacle avoidance evaluation value BZ. The collision risk value PZ and the obstacle avoidance evaluation value BZ are substituted into the formula to obtain a driving risk evaluation coefficient F; The collision risk value indicates the time duration corresponding to the minimum vertical distance between the target vehicle and the collision object during the driving process of the feasible route is less than a preset threshold; The obstacle avoidance evaluation value indicates that the road area occupied by the pits in the feasible route is greater than a preset threshold, and the depth of the pits is greater than the number of pits corresponding to the preset depth threshold; The driving defect assessment feedback operation process of the driving risk supervision unit is as follows: S1: Acquire the driving data of each feasible route, the driving data including the energy consumption evaluation value and the driving time, the energy consumption evaluation value represents the ratio between the total driving energy consumption and the driving distance, and then obtain the product value obtained by multiplying the energy consumption evaluation value and the driving time after data normalization, and set it as the driving evaluation value SP; S2: Obtain the corridor interference value CG of each feasible route. The corridor interference value CG indicates the ratio between the length of the road section corresponding to the value of the environmental parameter exceeding the preset threshold and the total length. The environmental parameters include the electromagnetic interference value and the dust concentration. Substitute the driving evaluation value SP and the corridor interference value CG into the formula to obtain the driving defect evaluation coefficient G; The information fusion planning evaluation and analysis process of the route planning analysis unit is as follows: The feasible route is marked as i, where i is a natural number greater than zero, and the driving risk assessment coefficient Fi and driving defect assessment coefficient Gi of each feasible route are obtained. The driving risk assessment coefficient Fi and driving defect assessment coefficient Gi are substituted into the formula The priority behavior evaluation coefficient of each feasible route is obtained, where v1 is the preset error compensation coefficient, v1 is greater than zero, and Ri is the priority behavior evaluation coefficient of each feasible route. Then, the minimum value of the priority behavior evaluation coefficient Ri is obtained and marked as the optional path value Rmin, and the optional path value Rmin is discriminated and analyzed: If the optional path value Rmin is unique, a selection signal is generated; If the uniqueness of the optional path value Rmin is not satisfied, a screening signal is generated; When the route planning and analysis unit generates a screening signal: Obtaining a feasible route corresponding to the screening signal and setting it as an alternative route, obtaining the number of intersections of each alternative route, and setting the number of intersections of each alternative route as an intersection risk value, and then obtaining a minimum value among the intersection risk values, and setting the alternative route corresponding to the minimum value among the intersection risk values ​​as a preferred route; The driving deviation supervision and analysis process of the route tracking management unit is as follows: The selected route of the target vehicle is obtained, and the selected route represents a feasible route or a preferred route corresponding to the selection signal, and then the driving route trajectory of the selected route is generated, and the driving route trajectory of the generated selected route is set as the planned trajectory line. At the same time, the actual trajectory line of the target vehicle traveling on the selected route is obtained, and then the overlapping sections and deviated sections between the actual trajectory line and the planned trajectory line are obtained, and the area of ​​the area enclosed by the actual trajectory line and the planned trajectory line corresponding to the deviated section is obtained, and it is set as the allowable offset value, and the allowable offset value is compared and analyzed with the preset allowable offset value threshold value stored in the internal input: If the ratio between the allowed offset value and the preset allowed offset value threshold is less than 1, a stable signal is generated; If the ratio between the allowed offset value and the preset allowed offset value threshold is greater than or equal to 1, an adjustment signal is generated; When the route tracking management unit generates a stable signal: The duration of the next period of time is obtained and set as the time threshold. The time threshold is divided into g sub-time nodes, where g is a natural number greater than zero. The obstacle avoidance evaluation value of the selected route in each sub-time node is obtained. A rectangular coordinate system is established with the number of sub-time nodes as the X-axis and the obstacle avoidance evaluation value as the Y-axis. The obstacle avoidance evaluation value curve is drawn by plotting points, and the growth trend value of the obstacle avoidance evaluation value curve is obtained. The growth trend value of the obstacle avoidance evaluation value curve is set as the road damage risk index, and the road damage risk index is compared and analyzed with the preset road damage risk index threshold value stored in the internal input: If the ratio between the road damage risk index and the preset road damage risk index threshold is less than 1, no signal is generated; If the ratio between the road loss risk index and the preset road loss risk index threshold is greater than or equal to 1, a management signal is generated.

Images