An indication machine dynamic walking control method based on traffic lane control

Abstract

The present invention relates to the technical field of program control, and specifically to a method for dynamically controlling the movement of an indicating machine based on traffic lane management and control, which realizes efficient, stable and dynamic adjustment of the movement control of the indicating machine for traffic lane management and control in complex environmental changes; it includes: collecting environmental data, event signals, traffic flow parameters and device status using multi-modal sensors; analyzing the environmental data through a real-time environmental analysis model to generate road topology data and calculate the environmental resistance coefficient; generating a global navigation path based on a dynamic path planning algorithm, and performing real-time local optimization through a feedback compensation mechanism to generate an optimized path, and constructing a regulation strategy based on the influence domain; establishing a motion control model, adjusting the parameters of the moving speed and direction control quantity, and generating a control instruction set in combination with the regulation strategy; inputting the control instruction set into a closed-loop controller, and dynamically adjusting the device through a feedforward-feedback composite control architecture so that it reaches the event coordinates along the optimized path and executes the deployment.

Description

Technical Field

[0001] The present invention relates to the technical field of program control, and specifically provides a method for dynamically controlling the movement of an indicating machine based on traffic lane management and control. Background Art

[0002] In the field of program control, through the precise monitoring and adjustment of the operating speed, steering angle, and position information of the machine body, the stability and continuity of the equipment's movement trajectory are achieved, thereby ensuring high safety and efficiency when performing complex tasks. Especially in the face of dynamic environmental changes and emergencies, this control system can respond quickly and achieve instant optimization and fine control of the operation path through real-time data collection and intelligent feedback.

[0003] Continuous trajectory control technology is one of the key technologies in the field of program control to ensure the safe and efficient operation of equipment. Through the precise monitoring and adjustment of speed, position information, and steering angle, smooth transition, dynamic stability, and fine control of the movement trajectory can be achieved. With the progress of technology, the application of real-time data collection and feedback systems in continuous control is becoming more and more extensive, promoting the improvement of the movement trajectory control system in terms of accuracy, response speed, and multi-parameter collaborative control. However, despite a large amount of research, there are still certain technical challenges in the aspects of real-time feedback, adjustment response speed, and movement accuracy of existing control systems when dealing with complex dynamic environments, and there is an urgent need for more efficient, stable, and dynamically adaptable control methods to overcome these problems.

[0004] At present, the indicating machine still faces many challenges in continuous trajectory control technology. When the system responds to complex environmental changes, its real-time feedback, adjustment response speed, and movement accuracy are still insufficient; there are also certain difficulties in achieving the smoothness, dynamic stability, and multi-parameter collaborative control of the movement path during the continuous control of dynamic walking. In addition, the efficiency and accuracy of data fusion and parameter dynamic adjustment technologies still restrict the improvement of the overall system performance, and these problems all need to be effectively solved in the future technological development. Therefore, there is an urgent need for an efficient, stable, and dynamically adjustable continuous trajectory control technology to address the problems of insufficient real-time feedback, adjustment response speed, and movement accuracy when dealing with complex environmental changes.

[0005] Therefore, a method for dynamically controlling the movement of an indicating machine based on traffic lane management and control is proposed. Summary of the Invention

[0006] The purpose of the present invention is to provide a method for dynamically controlling the movement of an indicating machine based on traffic lane management and control, which can achieve efficient, stable, and dynamic adjustment of the movement control of the indicating machine for traffic lane management and control in the face of complex environmental changes.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for dynamically controlling the movement of an indicator machine based on traffic lane control, comprising:

[0009] Collecting environmental data, event signals, traffic parameters, and device status using multi-modal sensors; the event signals include: event coordinates and influence domains; the device status includes: moving speed, direction control quantity, and spatial coordinates;

[0010] Performing multi-dimensional analysis on the environmental data through a real-time environmental analysis model, identifying road topology data, and calculating the environmental resistance coefficient;

[0011] Generating a global navigation path from the spatial coordinates to the event coordinates based on a dynamic path planning model, performing real-time local trajectory optimization on the global navigation path through a feedback compensation mechanism in combination with the traffic parameters, generating an optimized path including spatio-temporal constraints, and constructing a regulation strategy based on the influence domain;

[0012] Establishing a motion control model, performing collaborative parameter adjustment on the moving speed and the direction control quantity according to the road topology data, the environmental resistance coefficient, and the optimized path, and generating a control instruction set in combination with the regulation strategy;

[0013] Inputting the control instruction set into an embedded closed-loop controller, dynamically controlling the motion state of the device through a feedforward-feedback composite control architecture, so that the device reaches the event coordinates along the optimized path and executes the regulation strategy.

[0014] Preferably, the multi-modal sensors include: a high-definition camera, a millimeter-wave radar, and GPS positioning;

[0015] The environmental data includes: highway maps, road surface temperature, humidity, water accumulation thickness, and road surface damage information.

[0016] Preferably, the real-time environmental analysis model includes: a data processing unit, a road topology data identification unit, and an environmental resistance coefficient calculation unit;

[0017] The data processing unit preprocesses the collected environmental data; the preprocessing includes filtering and edge detection;

[0018] The road topology data identification unit identifies road topology data from the preprocessed environmental data; the road topology data includes: lane line information, lane center, and lane speed limit;

[0019] The environmental resistance coefficient calculation unit calculates the environmental resistance coefficient according to the environmental data; the calculation formula for the environmental resistance coefficient is:

[0020] ;

[0021] Among them, is the environmental resistance coefficient; is the influence parameter of accumulated water; is the weight of accumulated water thickness; is the accumulated water thickness; is the influence parameter of road surface temperature; is the weight of road surface temperature; is the road surface temperature; is the optimal temperature for adhesion; is the weight of humidity; is the humidity; is the weight of road surface damage information; is the road surface damage information.

[0022] Preferably, the dynamic path planning model includes: a global navigation path planning unit, a local trajectory optimization unit, and a regulation strategy construction unit;

[0023] The global navigation path planning unit calculates the global navigation path of the device from the spatial coordinates to the event position based on the environmental data, the event coordinates, and the influence domain by using the Dijkstra algorithm;

[0024] The local trajectory optimization unit performs real-time local optimization on the global navigation path based on the traffic parameters, the road topology data, and the environmental resistance coefficient by combining the model predictive control method to obtain an optimized path;

[0025] The regulation strategy construction unit formulates a regulation strategy according to the influence domain and the optimized path based on expert experience and issues regulation information to surrounding vehicles; the regulation strategy includes: dynamic speed limit, lane closure, variable lane adjustment, and detour.

[0026] Preferably, the parameter adjustment formula for the moving speed is:

[0027] ;

[0028] Among them, is the real-time moving speed after parameter adjustment; is the minimum value function; is the maximum speed limit of the lane; is the ideal moving speed based on the optimized path; is the environmental resistance coefficient; is the influence factor of the direction control quantity; is the real-time direction control quantity after parameter adjustment; is the ideal direction control quantity based on the optimized path; is the influence factor of the lateral deviation; To indicate the lateral deviation of the machine from the center of the lane;

[0029] Preferably, the parameter adjustment formula for the direction control quantity is:

[0030] ;

[0031] Wherein, is the real-time direction control quantity after parameter adjustment; is the ideal direction control quantity based on the optimized path; is the lateral deviation influence coefficient; is the lateral deviation of the device from the center of the lane; is the moving speed change influence coefficient; is the moving speed change rate; is the real-time moving speed after parameter adjustment; is the time; is the derivative function.

[0032] Preferably, the control instruction set includes: a moving speed control instruction and a direction control quantity control instruction;

[0033] The specific generation process of the control instruction set includes: a moving speed control instruction generation unit and a direction control quantity control instruction generation unit;

[0034] The moving speed control instruction generation unit calculates the turning radius of the device according to the dynamically adjusted moving speed and the direction control quantity; calculates the moving speed difference of each wheel based on the turning radius and the geometric structure parameters of the device, and generates the moving speed control instruction for each wheel;

[0035] The direction control quantity control instruction generation unit calculates the actual steering angle difference of each wheel according to the Ackerman steering model, and generates the direction control quantity control instruction for each wheel.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] 1. By integrating multi-modal sensor data such as high-definition cameras, millimeter-wave radars, and GPS positioning, the present invention can comprehensively sense the road conditions of highways, including key indicators such as road surface temperature, humidity, water accumulation thickness, and road surface damage. The integration of this multi-source information helps to accurately identify road topology data and calculate the environmental resistance coefficient, providing a reliable basis for dynamically adjusting the moving speed and direction control quantity of the device, thereby effectively improving the safety and stability of the device under complex road conditions.

[0038] 2. The present invention proposes a dynamic path planning model that conducts global navigation path planning by integrating event signals and device states, and combines traffic parameters to perform real-time local trajectory optimization on the global navigation path, quickly generating an optimized path. Based on the optimized path and real-time traffic parameters, this model formulates control strategies including dynamic speed limits, lane closures, variable lane adjustments, and diversions, and simultaneously broadcasts control information to surrounding vehicles. This method can not only quickly guide the device to the event location, but also effectively coordinate on-site traffic, reduce the risk of secondary congestion or accidents caused by accidents, thus significantly improving the overall traffic emergency response efficiency and road control ability, ensuring smooth traffic flow and driving safety. The optimized path and control strategies obtained by this model provide a route and solution basis for subsequent generation of a control instruction set to dynamically control the movement state of the device.

[0039] 3. The present invention proposes a method for dynamically adjusting the dynamic parameters of the moving speed and direction control amount of a device by combining road topology data, environmental resistance coefficients, and optimized paths. This dynamic parameter adjustment method not only considers key factors such as road surface adhesion and electronic power steering, but also generates a precise control instruction set based on the formulated control strategies, and dynamically controls the movement state of the device through a feedforward-feedback composite control architecture, ensuring that the device can drive stably to the accident scene in complex and emergency situations. This method can respond to environmental changes in real time, automatically adjust the driving path, and make flexible deployments, ensuring timely and efficient completion of accident emergency handling in the event of an emergency, improving the driving accuracy and efficiency of the device on the highway, ensuring driving safety and avoiding the occurrence of secondary accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flowchart of a method for dynamically controlling the walking of an indicating machine based on traffic lane control provided by an embodiment of the present invention;

[0041] Figure 2 It is a flowchart of the optimized path generation and construction of control strategies by the path planning model provided by an embodiment of the present invention;

[0042] Figure 3 It is a flowchart of the generation of the control instruction set provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] With the development of intelligent transportation systems, the applications of autonomous driving and driverless technologies in highway and urban traffic are gradually increasing. Especially in the highway environment, guiding machines (such as autonomous vehicles, unmanned transport vehicles, etc.) need to achieve precise path planning and dynamic control in complex traffic environments to ensure driving safety and efficiency. In this process, how to respond promptly to road emergencies, handle complex traffic flows and environmental conditions, and adjust the driving state of vehicles in real time according to road surface conditions and lane information has become an important technical challenge.

[0045] The present invention proposes a dynamic walking control method for guiding machines based on traffic lane control, which realizes efficient, stable and dynamic adjustment of the walking control of guiding machines for traffic lane control in the face of complex environmental changes. In order to illustrate that the method of the present invention can play a role in efficiently, stably and dynamically adjusting the walking control of guiding machines for traffic lane control in the face of complex environmental changes, the effectiveness of the present invention will be described from two embodiments below.

[0046] Embodiment 1

[0047] In the embodiment of the present application, the process of efficiently, stably and dynamically adjusting the walking control of guiding machines for traffic lane control by using the method proposed by the present invention is described in detail. The embodiment of the present application is directed to the walking control of guiding machines for traffic lane control in a certain highway section A. The following will be based on Figure 1 the content to describe in detail the walking control process of the guiding machines in the highway section A; among them, Figure 1 is the specific flowchart of the method proposed by the present invention, including: collecting environmental data, event signals, traffic flow parameters and device status by using multi-modal sensors; performing multi-dimensional analysis on the environmental data through a real-time environmental analysis model to generate road topology data and calculate the environmental resistance coefficient; generating a global navigation path from spatial coordinates to event coordinates based on a dynamic path planning algorithm; performing real-time local trajectory optimization on the global navigation path through a feedback compensation mechanism in combination with traffic flow parameters to generate an optimized path including spatio-temporal constraints, and constructing a regulation strategy based on the influence domain; establishing a motion control model, and making coordinated parameter adjustments to the moving speed and direction control quantities according to the road topology data, the environmental resistance coefficient and the optimized path, and generating a control instruction set in combination with the regulation strategy; inputting the control instruction set into an embedded closed-loop controller, and dynamically controlling the motion state of the device through a feedforward-feedback composite control architecture, so that the device reaches the event coordinates along the optimized path and executes the regulation strategy. Combining Figure 1 the content in it for the following description:

[0048] A dynamic walking control method for guiding machines based on traffic lane control, including:

[0049] Collect environmental data, event signals, traffic parameters, and device status using multimodal sensors; the event signals include: event coordinates and influence domains; the device status includes: moving speed, direction control amount, and spatial coordinates.

[0050] The multimodal sensors include: high-definition cameras, millimeter-wave radars, and GPS positioning; the environmental data includes: highway maps, road surface temperature, humidity, water accumulation thickness, and road surface damage information.

[0051] In the embodiments of this application, by fusing data from multimodal sensors such as high-definition cameras, millimeter-wave radars, and GPS positioning, it is possible to comprehensively perceive the road conditions of highways, including key indicators such as road surface temperature, humidity, water accumulation thickness, and road surface damage. The integration of such multi-source information helps to accurately identify road topology data and calculate the environmental resistance coefficient subsequently, providing a reliable basis for dynamically adjusting the moving speed and direction control amount of the indicating machine, thereby effectively improving the safety and stability of vehicles under complex road conditions.

[0052] Preferably, perform multi-dimensional analysis on the environmental data through a real-time environmental analysis model to identify road topology data and calculate the environmental resistance coefficient;

[0053] The real-time environmental analysis model includes: a data processing unit, a road topology data identification unit, and an environmental resistance coefficient calculation unit;

[0054] The data processing unit preprocesses the collected environmental data; the preprocessing includes filtering and edge detection;

[0055] The road topology data identification unit identifies road topology data from the preprocessed environmental data; the road topology data includes: lane line information, lane center, and lane maximum speed limit;

[0056] The environmental resistance coefficient calculation unit calculates the environmental resistance coefficient according to the environmental data; the calculation formula for the environmental resistance coefficient is:

[0057] ;

[0058] Where, is the environmental resistance coefficient; is the water accumulation influence parameter; is the water accumulation thickness weight; is the water accumulation thickness; is the road surface temperature influence parameter; is the road surface temperature weight; is the road surface temperature; is the optimal temperature for adhesion; is the humidity weight; is the humidity; is the weight of road surface damage information; is the road surface damage information.

[0059] Specifically, the edge detection extracts the lane edge features in the highway map through the Canny edge detection algorithm; the lane line information accurately identifies the position information of the lane lines from the lane edge features through the Hough transform, including: lane width, number of lanes, and lane boundary lines; the lane center is calculated through the lane width; the maximum speed limit of the lane obtains traffic sign information through the OCR recognition algorithm and identifies the maximum speed limit of each lane.

[0060] In the embodiment of the present application, the collected environmental data is analyzed multi-dimensionally through the real-time environment parsing model, realizing the accurate identification of road topology data and the efficient calculation of the environmental resistance coefficient, thereby providing a precise road environment assessment for instructing the machine to perform lane control. The collected environmental data is processed through filtering and edge detection to remove noise and interference, providing high-quality data for subsequent analysis. The lane edge features are extracted through the Canny edge detection algorithm, combined with the Hough transform to identify the lane line information, accurately obtaining the width, quantity, and boundary lines of the lanes, which helps to improve the accuracy of lane recognition. The calculation of the lane center position provides a precise driving trajectory reference for the instructing machine. The environmental resistance coefficient is calculated by combining multiple environmental factors such as water accumulation, road surface temperature, humidity, and road surface damage, effectively quantifying the impact of the environment on driving, enabling the model to dynamically control the walking strategy of the instructing machine, thereby optimizing the driving experience, improving the handling stability of the vehicle, and reducing the accident risk. This model not only enhances the road adaptability of the instructing machine but also improves the response ability of the instructing machine to perform lane control in complex environments.

[0061] Preferably, a global navigation path from the spatial coordinate to the event coordinate is generated based on the dynamic path planning model, and the global navigation path is optimized in real-time locally through a feedback compensation mechanism in combination with the traffic flow parameters to generate an optimized path including spatio-temporal constraints, and a regulation strategy is constructed based on the influence domain; refer to Figure 2 ;

[0062] The dynamic path planning model includes: a global navigation path planning unit, a local trajectory optimization unit, and a regulation strategy construction unit;

[0063] The global navigation path planning unit calculates the global navigation path of the device from the spatial coordinate to the event position based on the environmental data, the event coordinate, and the influence domain by using the Dijkstra algorithm;

[0064] The local trajectory optimization unit performs real-time local optimization on the global navigation path based on the traffic parameters, the road topology data, and the environmental resistance coefficient, and combines the model predictive control method to obtain an optimized path;

[0065] The regulation strategy construction unit formulates a regulation strategy according to the influence domain and the optimized path based on expert experience, and issues regulation information to surrounding vehicles; the regulation strategy includes: dynamic speed limit, lane closure, variable lane adjustment, and detour.

[0066] Specifically, the local trajectory optimization unit uses the LSTM method to estimate the traffic state within a certain period of time in the future, and combines the feedback compensation mechanism to correct the local path deviation in real time, so as to generate an optimized path that simultaneously satisfies the spatio-temporal constraints to cope with sudden traffic conditions or environmental changes.

[0067] Table 1 is a data comparison table before and after local optimization of the global navigation path.

[0068] Table 1 Data Comparison Table Before and After Local Optimization

[0069]

[0070] The embodiment of the present application proposes a dynamic path planning model, which can realize the generation of a global navigation path from spatial coordinates to event coordinates, and combine traffic parameters for real-time local trajectory optimization to effectively cope with the dynamically changing traffic environment. By using the Dijkstra algorithm to calculate the global navigation path, the rationality and optimality of the path planning can be ensured; at the same time, combining the model predictive control method for local trajectory optimization can adjust the driving route in real time to avoid the influence of traffic congestion, emergencies or environmental factors, thereby improving the efficiency and safety of guiding the machine to walk. Through the construction and release of regulation strategies, including measures such as dynamic speed limit, lane closure, variable lane adjustment, and detour, precise guidance and regulation of surrounding vehicles can be carried out, thereby optimizing the traffic flow, relieving the road pressure, and reducing the probability of traffic accidents. This model not only improves the efficiency of guiding the machine to walk, but also provides strong support for subsequent lane control through the guiding machine.

[0071] Preferably, a motion control model is established, and the mobile speed and the direction control amount are coordinately adjusted according to the road topology data, the environmental resistance coefficient, and the optimized path; the parameter adjustment formula for the mobile speed is:

[0072] ;

[0073] wherein, is the real-time mobile speed after parameter adjustment; is the minimum value function; is the maximum speed limit of the lane; is the ideal moving speed based on the optimized path; is the environmental resistance coefficient; is the influence factor of the direction control amount; is the real-time direction control amount after parameter adjustment; is the ideal direction control amount based on the optimized path; is the influence factor of the lateral deviation; is the lateral deviation indicating the machine from the center of the lane.

[0074] In the embodiment of the present application, by adjusting the parameters of the moving speed, the motion state of the indicating machine can be dynamically optimized according to the road topology data, the environmental resistance coefficient, and the actual situation of the optimized path. This adjustment method combines the maximum speed limit of the lane to ensure that the moving speed does not exceed the safe range and improves the driving safety. By introducing the environmental resistance coefficient, the influence of factors such as road surface temperature, humidity, water accumulation thickness, and road surface damage on driving stability can be fully considered, enabling the indicating machine to adaptively adjust the moving speed under complex road conditions and reducing risks such as skidding and out-of-control. Combining the influence factor of the direction control amount and the influence factor of the lateral deviation can optimize the steering control while maintaining a reasonable moving speed, reduce the driving trajectory deviation caused by speed changes, and further improve the path tracking accuracy and vehicle stability. This parameter adjustment method of the moving speed can effectively improve the driving smoothness and safety, ensure that the indicating machine can accurately move along the optimized path while reducing unnecessary energy consumption and improving the driving efficiency.

[0075] Preferably, the parameter adjustment formula of the direction control amount is:

[0076] ;

[0077] where is the real-time direction control amount after parameter adjustment; is the lateral deviation influence coefficient; is the influence coefficient of the moving speed change; is the moving speed change rate; is the time; is the derivative function.

[0078] Table 2 is a comparison table of the path tracking accuracy of the indicating machine after parameter adjustment.

[0079] Table 2 Comparison Table of Path Tracking Accuracy

[0080]

[0081] In the embodiments of the present application, by adjusting the parameters of the direction control quantity, the driving stability and path tracking accuracy of the indicating machine in a complex road environment can be effectively improved. The adjustment of the direction control quantity comprehensively considers the ideal direction control quantity of the optimized path, the lateral deviation, and the influencing factors of the moving speed, so that the indicating machine can accurately align with the center of the lane and reduce the influence of the lateral deviation on the driving trajectory. By introducing a lateral deviation influence factor, the deviation caused by road curvature changes or external disturbances such as wind force and road surface unevenness can be dynamically compensated, thereby enhancing the adaptive ability to the trajectory. By adjusting the direction control quantity in combination with the change of the moving speed, it is possible to ensure a reasonable steering response in different speed ranges, avoid oversteering at high speeds or understeering at low speeds, and thus improve the smoothness and safety of the overall control. The parameter adjustment method of the direction control quantity can optimize the path tracking effect of the indicating machine in a complex traffic environment, improve the accuracy of intelligent driving, and at the same time reduce the adjustment time caused by path deviation and improve the operation efficiency.

[0082] Preferably, after the collaborative parameter adjustment of the moving speed and the direction control quantity, a control instruction set is generated in combination with the regulation strategy; refer to Figure 3 ;

[0083] The control instruction set includes: a moving speed control instruction and a direction control quantity control instruction;

[0084] The specific generation process of the control instruction set includes: a moving speed control instruction generation unit and a direction control quantity control instruction generation unit;

[0085] The moving speed control instruction generation unit calculates the turning radius of the device according to the dynamically adjusted moving speed and the direction control quantity; calculates the moving speed difference of each wheel based on the turning radius and the geometric structure parameters of the device, and generates the moving speed control instruction of each wheel;

[0086] The direction control quantity control instruction generation unit calculates the actual steering angle difference of each wheel according to the Ackerman steering model, and generates the direction control quantity control instruction of each wheel.

[0087] Specifically, the calculation formula of the turning radius is:

[0088] ;

[0089] Among them, is the turning radius;

[0090] The geometric structure parameters are the lateral spacing and wheelbase between the wheels of the indicating machine;

[0091] The calculation formula of the moving speed difference is:

[0092] ;

[0093] Wherein, is the moving speed difference between the inner and outer wheels; is the lateral spacing indicating the machine wheels;

[0094] According to the moving speed difference, decelerate the inner wheel and accelerate the outer wheel, and generate the speed control commands for each wheel, so that the speeds of each wheel meet the requirements of circular motion when the vehicle is actually running;

[0095] The calculation formula of the actual steering angle difference is:

[0096] ;

[0097] Wherein, is the actual steering angle difference; is the steering angle of the inner wheel; is the steering angle of the outer wheel; is the wheelbase indicating the machine wheels;

[0098] By calculating the actual steering angle difference, generate the direction control commands for each wheel, ensure that the inner wheel obtains a larger steering angle and the outer wheel obtains a smaller steering angle, so as to achieve correct steering motion.

[0099] Table 3 is the stability evaluation table of the indicating machine after adjusting the moving speed difference and steering angle difference of each wheel.

[0100] Table 3 Indicating Machine Stability Evaluation Table

[0101]

[0102] In the embodiment of the present application, by accurately calculating and adjusting the moving speed difference and steering angle difference of each wheel, more accurate and stable steering control can be achieved, especially when turning. By dynamically adjusting the speed and steering angle of the wheels, the inner and outer wheels can obtain appropriate motion states according to the geometric structure of the vehicle and the difference in turning radius, thereby effectively reducing tire wear, improving maneuverability, and ensuring the smooth driving of the vehicle under complex road conditions. In addition, this process fully considers the dynamic characteristics of the indicating machine walking, optimizes the generation method of control commands, can adapt to different speed and turning radius requirements, improves the steering accuracy and response speed of the indicating machine, and helps to improve the safety and stability of the indicating machine in complex highway environments.

[0103] Preferably, the control instruction set is input into an embedded closed-loop controller, and through a feedforward-feedback composite control architecture, the motion state of the device is dynamically controlled to enable the device to reach the event coordinates along the optimized path and execute the regulation strategy;

[0104] Specifically, the embedded closed-loop controller includes: a feedforward control unit and a feedback control unit;

[0105] Based on the target moving speed and target direction control quantity in the optimized path, the feedforward control unit generates an initial motion control instruction and predicts the motion state through a machine learning model to achieve preliminary path tracking control;

[0106] The feedback control unit real-time obtains the current position, moving speed, and direction control quantity of the device, and calculates the current position deviation, speed error, and direction error by combining the inertial measurement unit and multi-modal sensor data, and performs error compensation based on the PID control algorithm or model predictive control method;

[0107] Combined with the feedback compensation result, the motion control instruction is dynamically adjusted to make the actual driving trajectory of the indicating machine consistent with the optimized path, and the deviation is gradually corrected to ensure that the indicating machine can move forward stably along the optimized path;

[0108] When the indicating machine approaches the event coordinates, the control parameters are further optimized, the moving speed and direction control quantity are adjusted, so that the device can accurately reach the event coordinates within a predetermined time, and the regulation strategy is executed in combination with the influence domain, including dynamic speed limit, lane closure, variable lane adjustment or detour, to optimize the traffic flow and improve the road traffic safety.

[0109] The embodiment of the present application provides a method for dynamically controlling the walking of an indicating machine based on traffic lane control. By integrating multi-modal sensor data, it realizes the precise perception of the traffic environment, and combines with a real-time environment analysis model to identify road topology data and calculate the environmental resistance coefficient, so as to provide high-quality environmental information support for subsequent path planning and driving control. Through the dynamic path planning model, it can combine global navigation and local trajectory optimization to effectively respond to sudden traffic events, dynamic traffic flow changes and complex road conditions, realize the intelligent optimization of the driving path, and improve the driving efficiency and path rationality. In addition, by establishing a motion control model, the collaborative parameter adjustment of the moving speed and direction control amount is carried out according to different road environments and driving states to ensure that the indicating machine can stably drive on the best trajectory, and improve the control accuracy and path tracking ability. Combining the feedforward-feedback composite control architecture, the control instruction is input into the embedded closed-loop controller to realize the dynamic adjustment of the motion state of the device, ensure that the device can accurately execute the regulation strategy, and finally realize efficient, safe and stable intelligent driving in a complex traffic environment. This method not only improves the road adaptability and control stability of the indicating machine, but also enhances its execution efficiency in traffic lane control, providing strong technical support for intelligent traffic lane control and automated vehicle scheduling.

[0110] Embodiment 2

[0111] In Embodiment 1, the method proposed by the present invention successfully realizes the efficient, stable and dynamic adjustment of the walking control of the indicating machine for traffic lane control in the face of complex environmental changes. To further verify the effectiveness of the present invention, in the embodiment of the present application, the dynamic walking control of the indicating machine used for traffic lane control in Section B of the highway is also carried out.

[0112] A method for dynamically controlling the walking of an indicating machine based on traffic lane control includes:

[0113] Collecting environmental data, event signals, traffic flow parameters and device status by using multi-modal sensors; the event signals include: event coordinates and influence domains; the device status includes: moving speed, direction control amount and spatial coordinates;

[0114] The multi-modal sensors include: high-definition cameras, millimeter-wave radars and GPS positioning; the environmental data includes: highway maps, road surface temperature, humidity, water accumulation thickness and road surface damage information.

[0115] Preferably, the environmental data is analyzed in multiple dimensions through a real-time environment analysis model to identify road topology data and calculate the environmental resistance coefficient;

[0116] The real-time environment analysis model includes: a data processing unit, a road topology data identification unit and an environmental resistance coefficient calculation unit;

[0117] The data processing unit preprocesses the collected environmental data; the preprocessing includes filtering and edge detection;

[0118] The road topology data recognition unit recognizes road topology data from the preprocessed environmental data; the road topology data includes: lane line information, lane center, and lane speed limit;

[0119] The environmental resistance coefficient calculation unit calculates the environmental resistance coefficient according to the environmental data; the calculation formula of the environmental resistance coefficient is:

[0120] ;

[0121] where, is the environmental resistance coefficient; is the water accumulation influence parameter; is the water accumulation thickness weight; is the water accumulation thickness; is the road surface temperature influence parameter; is the road surface temperature weight; is the road surface temperature; is the optimal temperature for adhesion; is the humidity weight; is the humidity; is the road surface damage information weight; is the road surface damage information.

[0122] Preferably, a global navigation path from the spatial coordinates to the event coordinates is generated based on the dynamic path planning model, and the global navigation path is optimized in real-time locally through a feedback compensation mechanism in combination with the traffic parameters to generate an optimized path including spatio-temporal constraints, and a regulation strategy is constructed based on the influence domain;

[0123] The dynamic path planning model includes: a global navigation path planning unit, a local trajectory optimization unit, and a regulation strategy construction unit;

[0124] The global navigation path planning unit calculates the global navigation path of the device from the spatial coordinates to the event position based on the environmental data, the event coordinates, and the influence domain by using the Dijkstra algorithm;

[0125] The local trajectory optimization unit performs real-time local optimization on the global navigation path based on the traffic parameters, the road topology data, and the environmental resistance coefficient, and combines the model predictive control method to obtain an optimized path;

[0126] The control strategy construction unit formulates a control strategy according to the influence domain and the optimization path, and issues control information to surrounding vehicles; the control strategy includes: dynamic speed limit, lane closure, variable lane adjustment, and detour.

[0127] Preferably, a motion control model is established, and the moving speed and the direction control quantity are coordinately adjusted according to the road topology data, the environmental resistance coefficient, and the optimization path; the parameter adjustment formula for the moving speed is:

[0128] ;

[0129] where is the real-time moving speed after parameter adjustment; is the minimum value function; is the maximum speed limit of the lane; is the ideal moving speed based on the optimization path; is the environmental resistance coefficient; is the influence factor of the direction control quantity; is the real-time direction control quantity after parameter adjustment; is the ideal direction control quantity based on the optimization path; is the influence factor of the lateral deviation; is the lateral deviation indicating the machine from the center of the lane.

[0130] Preferably, the parameter adjustment formula for the direction control quantity is:

[0131] ;

[0132] where is the real-time direction control quantity after parameter adjustment; is the influence coefficient of the lateral deviation; is the influence coefficient of the change in moving speed; is the rate of change of the moving speed; is the time; is the derivative function.

[0133] Preferably, after coordinately adjusting the moving speed and the direction control quantity, a control instruction set is generated in combination with the control strategy; the control instruction set includes: a moving speed control instruction and a direction control quantity control instruction.

[0134] The specific generation process of the control instruction set includes: a moving speed control instruction generation unit and a direction control quantity control instruction generation unit;

[0135] The moving speed control instruction generation unit calculates the turning radius of the device according to the dynamically adjusted moving speed and the direction control amount; calculates the moving speed differences of the wheels based on the turning radius and the geometric structure parameters of the device, and generates the moving speed control instructions for the wheels;

[0136] The direction control amount control instruction generation unit calculates the actual steering angle differences of the wheels according to the Ackerman steering model, and generates the direction control amount control instructions for the wheels.

[0137] Table 4 is a stability evaluation table of the machine after adjusting the moving speed differences and steering angle differences of the wheels.

[0138] Table 4 Stability Evaluation Table of the Machine

[0139]

[0140] Preferably, the control instruction set is input into an embedded closed-loop controller, and the motion state of the device is dynamically controlled through a feedforward-feedback composite control architecture, so that the device reaches the event coordinates along the optimized path and executes the regulation strategy.

[0141] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic walking control method for an indicating machine based on traffic lane control, characterized in that: include: Use multimodal sensors to collect environmental data, event signals, flow parameters, and equipment status; The event signal includes: event coordinates and impact domain; the device state includes: moving speed, direction control amount and space coordinates; Perform multi-dimensional analysis on the environmental data through a real-time environmental analysis model, identify road topology data and calculate environmental resistance coefficient; Generate a global navigation path from the spatial coordinates to the event coordinates based on a dynamic path planning model, perform real-time local trajectory optimization on the global navigation path through a feedback compensation mechanism in combination with the traffic parameters, generate an optimized path containing spatiotemporal constraints, and construct a control strategy based on the influence domain; A motion control model is established, and the moving speed and the direction control amount are adjusted in coordination according to the road topology data, the environmental resistance coefficient and the optimized path, and a control instruction set is generated in combination with the control strategy; the parameter adjustment formula of the moving speed is: ； in, It is the real-time moving speed after parameter adjustment; is the minimum function; The maximum speed limit for the lane; is the ideal moving speed based on the optimized path; is the environmental resistance coefficient; is the influencing factor of the direction control quantity; It is the real-time direction control amount after parameter adjustment; is the ideal directional control quantity based on the optimized path; is the lateral deviation influencing factor; is the lateral deviation of the equipment from the center of the lane; The parameter adjustment formula of the direction control amount is: ； in, It is the real-time direction control amount after parameter adjustment; is the ideal directional control quantity based on the optimized path; is the lateral deviation influence coefficient; is the lateral deviation of the equipment from the center of the lane; is the influence coefficient of moving speed change; is the rate of change of moving speed; It is the real-time moving speed after parameter adjustment; For time; is the derivative function; The control instruction set is input into an embedded closed-loop controller, and the motion state of the device is dynamically controlled through a feedforward-feedback composite control architecture, so that the device reaches the event coordinate along the optimized path and executes the control strategy.

2. The method for dynamic walking control of an indicating machine based on traffic lane control according to claim 1, characterized in that: The multimodal sensor includes: a high-definition camera, a millimeter-wave radar and a GPS positioning; The environmental data include: highway map, road surface temperature, humidity, water thickness and road surface damage information.

3. The method for dynamic walking control of an indicating machine based on traffic lane control according to claim 1, characterized in that: The real-time environmental analysis model includes: a data processing unit, a road topology data recognition unit and an environmental resistance coefficient calculation unit; The data processing unit pre-processes the collected environmental data; the pre-processing includes filtering and edge detection; The road topology data identification unit identifies road topology data from the pre-processed environment data; the road topology data includes: lane line information, lane center and lane maximum speed limit; The environmental resistance coefficient calculation unit calculates the environmental resistance coefficient according to the environmental data; the calculation formula of the environmental resistance coefficient is: ； in, is the environmental resistance coefficient; Parameters that affect water accumulation; is the water accumulation thickness weight; is the thickness of the accumulated water; is the influencing parameter of pavement temperature; is the pavement temperature weight; is the road surface temperature; The best temperature for adhesion; is the humidity weight; for humidity; is the road damage information weight; It is the road damage information.

4. The method for dynamic walking control of an indicating machine based on traffic lane control according to claim 1, characterized in that: The dynamic path planning model includes: a global navigation path planning unit, a local trajectory optimization unit and a control strategy construction unit; the global navigation path planning unit calculates the global navigation path of the device from the space coordinates to the event coordinates using the Dijkstra algorithm based on the environmental data, the event coordinates and the influence domain; The local trajectory optimization unit performs real-time local optimization on the global navigation path based on the flow parameter, the road topology data and the environmental resistance coefficient in combination with a model predictive control method to obtain an optimized path; The control strategy construction unit formulates a control strategy according to the influence domain and the optimization path based on expert experience, and publishes control information to surrounding vehicles; the control strategy includes: dynamic speed limit, lane closure, variable lane adjustment and detour.

5. The method for dynamic walking control of an indicating machine based on traffic lane control according to claim 1, characterized in that: The control instruction set includes: movement speed control instructions and direction control amount control instructions; The specific generation process of the control instruction set includes: a moving speed control instruction generation unit and a direction control amount control instruction generation unit; The moving speed control instruction generating unit calculates the turning radius of the device according to the dynamically adjusted moving speed and the direction control amount; calculates the moving speed difference of each wheel based on the turning radius and the geometric structure parameters of the device, and generates the moving speed control instruction of each wheel; The direction control amount control instruction generating unit calculates the actual steering angle difference of each wheel according to the Ackerman steering model, and generates the direction control amount control instruction of each wheel.

Images