CAN bus and V2I goose group optimization ice and snow removal operation platform obstacle avoidance system and method

Abstract

The invention discloses a goose group optimization ice and snow removal work platform obstacle avoidance system based on a CAN bus and V2I, and the system is characterized in that the system comprises a signal receiver, a camera, a radar, and an upper computer, the camera and the radar are connected with the upper computer through the CAN bus, the camera transmits a signal to the upper computer for processing, the signal receiver is connected with the upper computer through V2I communication, and the signal receiver is connected with the upper computer through V2I communication. The signal receiver obtains environment data from airport infrastructures and transmits the environment data to the upper computer for processing through V2I communication, the upper computer is connected with the vehicle-mounted ECU, and after processing of the upper computer is completed, the vehicle-mounted ECU controls the direction control execution mechanism of the ice and snow removing operation platform and the external machine tool control execution mechanism to work. The system not only can effectively improve the real-time communication capability of the operation platform in a complex environment, but also can perform dynamic path planning and optimization based on a bionic intelligent algorithm, and solves the problems of low efficiency and insufficient obstacle avoidance capability in traditional ice and snow removal operation.

Description

Technical Field

[0001] The present invention belongs to the technical field of ice and snow removal operation platforms, and specifically relates to a CAN bus, V2I goose flock optimization ice and snow removal operation platform obstacle avoidance system and method, the system realizes efficient and accurate ice and snow removal operations and obstacle avoidance through collaborative communication between vehicles, real-time environmental perception and intelligent optimization algorithm. Background Art

[0002] As global climate change intensifies, extreme weather occurs frequently, especially on key infrastructure such as airports, urban roads and highways. Snow and ice accumulation seriously affect the normal operation of transportation and airports. Traditional ice and snow removal platforms mostly rely on manual driving and a single sensor for obstacle avoidance, facing problems of low efficiency and poor safety, and cannot meet the needs of normal work. Summary of the invention

[0003] In view of the problems existing in the above-mentioned prior art, the present invention provides a CAN bus and V2I goose flock optimization snow and ice removal operation platform obstacle avoidance system and method. The snow and ice removal operation platform and infrastructure (V2I) communication technology are combined with CAN bus technology to provide an efficient information transmission method, which can obtain road information, environmental conditions and obstacle information in real time. In addition, the use of goose flock optimization algorithm to plan the operation path and optimize the obstacle avoidance behavior can greatly improve the operation efficiency and safety.

[0004] As a high-reliability, high-speed data transmission protocol, CAN bus technology is widely used in vehicle internal communications and can effectively solve the problem of unstable data transmission in complex environments. V2I technology communicates with roadside infrastructure through the platform to obtain real-time road and traffic information and supplement the limitations of platform sensors. The goose flock optimization algorithm is a bionic intelligent algorithm that simulates the behavior of geese in flight by guiding the rest of the individuals to optimize the flight path through the leader goose. In this way, the vehicle can effectively avoid obstacles and optimize its operation path.

[0005] In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a goose flock optimization ice and snow removal operation platform obstacle avoidance system based on CAN bus and V2I, including: a signal receiver, a camera, a radar, and a host computer. The camera and the radar are connected to the host computer through the CAN bus. The camera transmits the signal to the host computer for processing. The signal receiver is connected to the host computer through V2I communication. The signal receiver obtains environmental data from the airport infrastructure and transmits it to the host computer through V2I communication for processing. The host computer is connected to the on-board ECU. After the host computer completes the processing, the on-board ECU controls the direction control actuator and the external equipment control actuator of the ice and snow removal operation platform.

[0006] Furthermore, the host computer includes: a communication module, a processor, and a memory. The processor is connected to the communication module and the memory respectively, and the communication module is connected to the signal receiver through V2I communication.

[0007] A method for a CAN bus and V2I goose flock optimization ice and snow removal operation platform obstacle avoidance system comprises the following steps:

[0008] Step 1: The host computer obtains the snow and ice removal operation platform information and the surrounding environment information through the vehicle-mounted ECU and the signal receiver;

[0009] Step 2: The host computer determines whether the operating conditions are met based on the snow thickness and road width;

[0010] Step 3: The host computer uses cameras and radars to detect in real time and determine whether the snow and ice removal operation platform is at a safe distance from obstacles;

[0011] Step 4: Use the goose flock algorithm to optimize the operation path and adjust the tool parameters;

[0012] Step 5: Perform slip compensation and safety assessment;

[0013] Step 6: Determine the operation path and adjust the strategy to carry out the operation.

[0014] Furthermore, in step 1, the host computer obtains the information of the ice and snow removal operation platform through the vehicle-mounted ECU, wherein the dynamic model of the ice and snow removal operation platform is used to control the steering and speed adjustment during the ice and snow removal operation; assuming that the steering angle of the platform is θ, the motion model of the operation platform can be expressed as:

[0015]

[0016] Where: v is the driving speed of the platform, L is the wheelbase of the platform, and δ is the steering angle of the front wheel;

[0017] The host computer obtains the surrounding environment information through the signal receiver, and needs to perform noise filtering and state estimation through the Kalman filter. The state update formula of the Kalman filter is:

[0018]

[0019] P k =AP k-1 A T +Q k

[0020] In the measurement phase, the state estimate is corrected using the measurement update formula:

[0021] K k =P k H T (HPk H T +R k ) -1

[0022]

[0023] P k =(IK k H)P k K k is the Kalman gain, z k is the measured value, H is the measurement matrix, R k is the measurement noise covariance matrix. Further, the specific steps of step three are as follows:

[0024] In the airport environment, the de-icing platform needs to determine whether it needs to avoid obstacles by calculating the distance between the platform and the obstacle. Assume that the current position of the de-icing platform is (x v ,y v ), the position of the obstacle is (x o ,y o ), the distance d between them is calculated as:

[0025]

[0026] When d≤d safe (set safety distance), the platform triggers obstacle avoidance operation;

[0027] During the obstacle avoidance process, the steering angle of the de-icing and snow removal platform needs to be adjusted according to the obstacle distance and driving speed; assuming that the angle θ between the current driving direction of the de-icing and snow removal platform and the obstacle position min , and its calculation formula is:

[0028]

[0029] In order to effectively avoid obstacles, the new steering angle θ is calculated based on the distance and speed. new , and the adjustment amount Δθ is calculated by the following formula:

[0030]

[0031] Among them, K is the steering sensitivity coefficient, and v is the current speed of the platform.

[0032] Furthermore, the step 4 uses the goose flock algorithm to optimize the operation path and adjust the tool parameters. The specific steps are as follows:

[0033] (1) Initialize the goose flock: Initialize multiple candidate paths, where each “goose” represents a path state (position, speed, direction).

[0034] X i=[x i ,y i ,v i ,θ i ]

[0035] Fitness evaluation: Each path is evaluated for fitness based on path length, obstacle avoidance effect, and operation stability, and the objective function is calculated.

[0036] f(X i )=w1·PathLength(X i )+w2·ObstacleAvoidance(X i )+w3·StabilityCost(X i ). Distance calculation: The Euclidean distance between each goose’s current position and the obstacle is calculated as

[0037]

[0038] Position update: The remaining geese adjust their paths based on the position of the leader goose and the influence of random geese.

[0039]

[0040] Update speed and steering: The speed and steering angle of the platform will also be adjusted as the position changes. The update formula is:

[0041]

[0042] The fitness of each path is evaluated based on the path length, obstacle avoidance effect and operation stability, and the objective function is calculated; the host computer uses V2I communication to obtain environmental data from the airport infrastructure and uses the goose flock algorithm for optimal path planning.

[0043] Furthermore, the step 5 performs slip compensation and safety assessment, and the specific steps are as follows:

[0044] Assume that the starting point of the snow and ice removal platform is (x s ,y s ), the end point is (x d ,y d ), the cost function of path planning

[0045] f(x,y)=g(x,y)+h(x,y)

[0046] g(x,y) is the actual cost from the starting point to the current point, and h(x,y) is the heuristic estimated cost from the current point to the end point;

[0047] Furthermore, to optimize the obstacle avoidance operation, the snow and ice removal operation platform uses a weighted decision control function to select the path and adjust the speed. The optimization goal is to minimize the obstacle avoidance cost.

[0048]

[0049] Q d , Q v are the weight coefficients of distance and speed, v t is the expected vehicle speed, T is the control time;

[0050] On a snow-covered runway, the friction between the tires of the work platform and the ground is reduced, and slippage may occur. The slip distance S slip Estimated by the following formula:

[0051]

[0052] The slip compensation formula is used to determine the possible slip distance of the platform during obstacle avoidance or emergency braking, and to adjust the control strategy accordingly.

[0053] In an ice and snow environment, the friction coefficient between the tire and the ground is low, and slippage becomes a common phenomenon. In order to describe the slippage phenomenon more accurately, the Dugoff tire model can be used, and the slip rate is defined as:

[0054]

[0055] v0 is the linear speed of the wheel, v is the travel speed of the work platform;

[0056] Lateral force F for the Dugoff tire model y The calculation formula is:

[0057]

[0058] On a snow-covered runway, the vehicle may skid or spin out during steering and obstacle avoidance. To prevent this, the vehicle stability control (VSC) is used to adjust the yaw rate. Target yaw angle The speed is calculated based on the desired steering angle δ:

[0059]

[0060] Actual yaw rate It can be obtained through the inertia model of the vehicle;

[0061]

[0062] The VSC system in the snow and ice removal platform adjusts the steering angle δ and the braking torque to make and Approaching, ensuring the stability of the vehicle during obstacle avoidance;

[0063] When avoiding obstacles, the operating platform needs to dynamically adjust its speed according to the obstacle distance and environmental conditions. The optimization problem can be expressed as a control problem. The goal is to minimize the cost function J so that the platform can quickly avoid obstacles and maintain a stable operating speed. The optimization problem is as follows:

[0064]

[0065] Q δ , Q v , Q a are the weight coefficients of steering, speed and acceleration, v t is the expected vehicle speed, T is the control time, and by solving the optimization problem, the optimal speed v and acceleration a are determined to ensure safe obstacle avoidance and efficient operation of the working platform.

[0066] Furthermore, when dealing with complex obstacles, the platform's obstacle avoidance strategy can adopt a nonlinear control algorithm - sliding mode control; the sliding mode surface is defined as:

[0067] s=c1(x desired -x)+c2(v desired -v)

[0068] Where c1 and c2 are control gains,

[0069] The control law of the sliding mode controller is:

[0070] u=-Ksgn(s)

[0071] Among them, K is taken as the control gain, sgn(s) is the sign function, which is used to quickly converge to the sliding surface;

[0072] The sliding mode controller can ensure the rapid obstacle avoidance and path tracking of the working platform in complex environments.

[0073] The beneficial effects of the present invention are:

[0074] (1) The system can not only effectively improve the real-time communication capability of the operation platform in complex environments, but also perform dynamic path planning and optimization based on bionic intelligent algorithms, solving the problems of inefficiency and insufficient obstacle avoidance in traditional snow and ice removal operations;

[0075] (2) Through the CAN bus, the system can collect various status information of the platform in real time and control multiple operation modules. With the help of V2I communication technology, the platform can obtain road conditions and obstacle information provided by the roadside unit in real time, enhancing the platform's environmental perception ability; combined with the goose flock optimization algorithm, the platform can dynamically adjust the driving path, automatically avoid obstacles, reduce the risk of slippage, and ensure the safety and efficiency of operations. At the same time, the use of this system can greatly reduce vehicle energy consumption and operation time, and optimize resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 is a flow chart of the method of the present invention;

[0077] Figure 2 This is a schematic diagram of obstacle avoidance for the snowplow operation platform;

[0078] Figure 3 It is a structural schematic diagram of the system of the present invention;

[0079] Figure 4 It is a flow chart of the algorithm of the present invention; DETAILED DESCRIPTION

[0080] In order to make the purpose, technical solution and advantages of the present invention more clear, the present invention is further described in detail below through the accompanying drawings and embodiments. However, it should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the scope of the present invention.

[0081] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0082] like Figure 3 As shown, a goose flock optimization snow and ice removal operation platform obstacle avoidance system based on CAN bus and V2I includes: a signal receiver, a camera, a radar, and a host computer. The camera and the radar are connected to the host computer through the CAN bus. The camera transmits the signal to the host computer for processing. The signal receiver is connected to the host computer through V2I communication. The signal receiver obtains environmental data from the airport infrastructure and transmits it to the host computer through V2I communication for processing. The host computer is connected to the vehicle-mounted ECU. After the host computer completes the processing, the vehicle-mounted ECU controls the direction control actuator and the external equipment control actuator of the snow and ice removal operation platform to work.

[0083] Furthermore, the host computer includes: a communication module, a processor, and a memory. The processor is connected to the communication module and the memory respectively, and the communication module is connected to the signal receiver through V2I communication.

[0084] like Figure 1 , 4 As shown, a method for a CAN bus and V2I goose flock optimization ice and snow removal operation platform obstacle avoidance system includes the following steps:

[0085] Step 1: The host computer obtains the snow and ice removal operation platform information and the surrounding environment information through the vehicle-mounted ECU and the signal receiver;

[0086] Step 2: The host computer determines whether the operating conditions are met based on the snow thickness and road width;

[0087] Step 3: The host computer uses cameras and radars to detect in real time and determine whether the snow and ice removal operation platform is at a safe distance from obstacles;

[0088] Step 4: Use the goose flock algorithm to optimize the operation path and adjust the tool parameters;

[0089] Step 5: Perform slip compensation and safety assessment;

[0090] Step 6: Determine the operation path and adjust the strategy to carry out the operation.

[0091] Furthermore, in step 1, the host computer obtains the snow and ice removal operation platform information through the vehicle-mounted ECU, wherein, Figure 2 As shown in the figure, the dynamic model of the snow and ice removal operation platform is used to control the steering and speed adjustment during snow and ice removal operations; assuming that the steering angle of the platform is θ, the motion model of the operation platform can be expressed as:

[0092]

[0093] Where: v is the driving speed of the platform, L is the wheelbase of the platform, and δ is the steering angle of the front wheel;

[0094] The host computer obtains the surrounding environment information through the signal receiver, and needs to perform noise filtering and state estimation through the Kalman filter. The state update formula of the Kalman filter is:

[0095]

[0096] P k =AP k-1 A T +Q k

[0097] In the measurement phase, the state estimate is corrected using the measurement update formula:

[0098] K k =P k H T (HP k H T +Rk ) -1

[0099]

[0100] P k =(IK k H)P k K k is the Kalman gain, z k is the measured value, H is the measurement matrix, R k is the measurement noise covariance matrix. Further, the specific steps of step three are as follows:

[0101] In the airport environment, the de-icing platform needs to determine whether it needs to avoid obstacles by calculating the distance between the platform and the obstacle. Assume that the current position of the de-icing platform is (x v ,y v ), the position of the obstacle is (x o ,y o ), the distance d between them is calculated as:

[0102]

[0103] When d≤d safe (set safety distance), the platform triggers obstacle avoidance operation;

[0104] During the obstacle avoidance process, the steering angle of the de-icing and snow removal platform needs to be adjusted according to the obstacle distance and driving speed; assuming that the angle θ between the current driving direction of the de-icing and snow removal platform and the obstacle position min , and its calculation formula is:

[0105]

[0106] In order to effectively avoid obstacles, the new steering angle θ is calculated based on the distance and speed. new , and the adjustment amount Δθ is calculated by the following formula:

[0107]

[0108] Among them, K is the steering sensitivity coefficient, and v is the current speed of the platform.

[0109] Furthermore, the step 4 uses the goose flock algorithm to optimize the operation path and adjust the tool parameters. The specific steps are as follows:

[0110] (1) Initialize the goose flock: Initialize multiple candidate paths, where each “goose” represents a path state (position, speed, direction).

[0111] X i =[x i ,yi ,v i ,θ i ]

[0112] Fitness evaluation: Each path is evaluated for fitness based on path length, obstacle avoidance effect, and operation stability, and the objective function is calculated.

[0113] f(X i )=w1·PathLength(X i )+w2·ObstacleAvoidance(X i )+w3·StabilityCost(X i ). Distance calculation: The Euclidean distance between each goose’s current position and the obstacle is calculated as

[0114]

[0115] Position update: The remaining geese adjust their paths based on the position of the leader goose and the influence of random geese.

[0116]

[0117] Update speed and steering: The speed and steering angle of the platform will also be adjusted as the position changes. The update formula is:

[0118]

[0119] The fitness of each path is evaluated based on the path length, obstacle avoidance effect and operation stability, and the objective function is calculated; the host computer uses V2I communication to obtain environmental data from the airport infrastructure and uses the goose flock algorithm for optimal path planning.

[0120] Furthermore, the step 5 performs slip compensation and safety assessment, and the specific steps are as follows:

[0121] Assume that the starting point of the snow and ice removal platform is (x s ,y s ), the end point is (x d ,y d ), the cost function of path planning

[0122] f(x,y)=g(x,y)+h(x,y)

[0123] g(x,y) is the actual cost from the starting point to the current point, and h(x,y) is the heuristic estimated cost from the current point to the end point;

[0124] Furthermore, to optimize the obstacle avoidance operation, the snow and ice removal operation platform uses a weighted decision control function to select the path and adjust the speed. The optimization goal is to minimize the obstacle avoidance cost.

[0125]

[0126] Q d , Q v are the weight coefficients of distance and speed, v t is the expected vehicle speed, T is the control time;

[0127] On a snow-covered runway, the friction between the tires of the work platform and the ground is reduced, and slippage may occur. The slip distance S slip Estimated by the following formula:

[0128]

[0129] The slip compensation formula is used to determine the possible slip distance of the platform during obstacle avoidance or emergency braking, and to adjust the control strategy accordingly.

[0130] In an ice and snow environment, the friction coefficient between the tire and the ground is low, and slippage becomes a common phenomenon. In order to describe the slippage phenomenon more accurately, the Dugoff tire model can be used, and the slip rate is defined as:

[0131]

[0132] v0 is the linear speed of the wheel, v is the travel speed of the work platform;

[0133] Lateral force F for the Dugoff tire model y The calculation formula is:

[0134]

[0135] On a snow-covered runway, the vehicle may skid or spin out during steering and obstacle avoidance. To prevent this, the vehicle stability control (VSC) is used to adjust the yaw rate. Target yaw angle The speed is calculated based on the desired steering angle δ:

[0136]

[0137] Actual yaw rate It can be obtained through the inertia model of the vehicle;

[0138]

[0139] The VSC system in the snow and ice removal platform adjusts the steering angle δ and the braking torque to make and Approaching, ensuring the stability of the vehicle during obstacle avoidance;

[0140] When avoiding obstacles, the operating platform needs to dynamically adjust its speed according to the obstacle distance and environmental conditions. The optimization problem can be expressed as a control problem. The goal is to minimize the cost function J so that the platform can quickly avoid obstacles and maintain a stable operating speed. The optimization problem is as follows:

[0141]

[0142] Q δ , Q v , Q a are the weight coefficients of steering, speed and acceleration, v t is the expected vehicle speed, T is the control time, and by solving the optimization problem, the optimal speed v and acceleration a are determined to ensure safe obstacle avoidance and efficient operation of the working platform.

[0143] Furthermore, when dealing with complex obstacles, the platform's obstacle avoidance strategy can adopt a nonlinear control algorithm - sliding mode control; the sliding mode surface is defined as:

[0144] s=c1(x desired -x)+c2(v desired -v)

[0145] Where c1 and c2 are control gains,

[0146] The control law of the sliding mode controller is:

[0147] u=-Ksgn(s)

[0148] Among them, K is taken as the control gain and sgn(s) is the sign function, which is used to quickly converge to the sliding mode surface. The sliding mode controller can ensure the rapid obstacle avoidance and path tracking of the working platform in complex environments.

[0149] The combination of Kalman filter and goose flock optimization algorithm significantly improves the obstacle avoidance capability of the snow and ice removal platform in complex environments. Kalman filter eliminates sensor noise and ensures accurate state estimation, so that the platform can operate stably even in low visibility or snow-covered conditions. Goose flock optimization algorithm selects the optimal obstacle avoidance route through dynamic path planning, balances operation efficiency and safety, and combines the dynamic model to achieve real-time adjustment of speed and direction to ensure that the platform can avoid obstacles smoothly. In addition, the combination of CAN bus and V2I communication technology improves information transmission and environmental perception capabilities. CAN bus ensures efficient communication within the platform, and V2I provides real-time data on the road environment, enabling the platform to better plan paths and respond quickly to external changes. This combination of technologies ensures the efficient and safe operation of the platform in complex operating environments.

[0150] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, equivalent substitution or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A goose flock optimization snow and ice removal platform obstacle avoidance system based on CAN bus and V2I, characterized in that: include: Signal receiver, camera, radar, host computer, the camera and radar are connected to the host computer through the CAN bus, the camera transmits the signal to the host computer for processing, the signal receiver is connected to the host computer through V2I communication, the signal receiver obtains environmental data from the airport infrastructure and transmits it to the host computer through V2I communication for processing, the host computer is connected to the on-board ECU, and after the host computer completes the processing, the on-board ECU controls the direction control actuator of the ice and snow removal operation platform and the external equipment control actuator.

2. According to the CAN bus, V2I goose flock optimization snow and ice removal operation platform obstacle avoidance system of claim 1, characterized in that: The host computer includes: a communication module, a processor, and a memory. The processor is connected to the communication module and the memory respectively, and the communication module is connected to the signal receiver through V2I communication.

3. The method of the CAN bus and V2I goose flock optimization snow and ice removal platform obstacle avoidance system according to claim 1, characterized in that: The steps include: Step 1: The host computer obtains the snow and ice removal operation platform information and the surrounding environment information through the vehicle-mounted ECU and the signal receiver; Step 2: The host computer determines whether the operating conditions are met based on the snow thickness and road width; Step 3: The host computer uses cameras and radars to detect in real time and determine whether the snow and ice removal operation platform is at a safe distance from obstacles; Step 4: Use the goose flock algorithm to optimize the operation path and adjust the tool parameters; Step 5: Perform slip compensation and safety assessment; Step 6: Determine the operation path and adjust the strategy to carry out the operation.

4. The method of the CAN bus and V2I goose flock optimization snow and ice removal platform obstacle avoidance system according to claim 3 is characterized by: In step 1, the host computer obtains the information of the ice and snow removal operation platform through the vehicle-mounted ECU, wherein the dynamic model of the ice and snow removal operation platform is used to control the steering and speed adjustment during the ice and snow removal operation; assuming that the steering angle of the platform is θ, the motion model of the operation platform can be expressed as: Where: v is the driving speed of the platform, L is the wheelbase of the platform, and δ is the steering angle of the front wheel; The host computer obtains the surrounding environment information through the signal receiver, and needs to perform noise filtering and state estimation through the Kalman filter. The state update formula of the Kalman filter is: P k =AP k-1 From T +Q k In the measurement phase, the state estimate is corrected using the measurement update formula: K k =P k H T (HP k H T +R k ) -1 P k =(I-K k H)P k K k is the Kalman gain, z k is the measured value, H is the measurement matrix, R k is the measurement noise covariance matrix.

5. The method of a CAN bus and V2I goose flock optimization snow and ice removal platform obstacle avoidance system according to claim 4, characterized in that: Step 3 The specific steps are as follows: In the airport environment, the de-icing platform needs to determine whether it needs to avoid obstacles by calculating the distance between the platform and the obstacle. Assume that the current position of the de-icing platform is (x v ,y v ), the position of the obstacle is (x o ,y o ), the distance d between them is calculated as: When d≤d safe (set safety distance), the platform triggers obstacle avoidance operation; During obstacle avoidance, the steering angle of the snow and ice removal platform needs to be adjusted according to the distance to the obstacle and the driving speed; Assume that the angle θ between the current driving direction of the deicing platform and the obstacle position is min , and its calculation formula is: In order to effectively avoid obstacles, the new steering angle θ is calculated based on the distance and speed. new , and the adjustment amount Δθ is calculated by the following formula: Among them, K is the steering sensitivity coefficient, and v is the current speed of the platform.

6. The method of the CAN bus and V2I goose flock optimization snow and ice removal platform obstacle avoidance system according to claim 5, characterized in that: Step 4 uses the goose flock algorithm to optimize the operation path and adjust the tool parameters. The specific steps are as follows: (1) Initialize the goose flock: Initialize multiple candidate paths. Each "goose" represents a path state, which includes: position, speed, and direction; X i [x i ,y i ,v i ,θ i ] Fitness evaluation: Each path is evaluated for fitness based on path length, obstacle avoidance effect, and operation stability, and the objective function is calculated; f(X i )=w1·PathLength(X i )+w2·ObstacleAvoidance(X i )+w3·StabilityCost(X i ). Distance calculation: The Euclidean distance between each goose’s current position and the obstacle is calculated as Position update: The remaining "geese" adjust their paths according to the position of the leading goose and the influence of the random goose; Update speed and steering: The speed and steering angle of the platform will also be adjusted as the position changes. The update formula is: The fitness of each path is evaluated based on the path length, obstacle avoidance effect and operation stability, and the objective function is calculated; the host computer uses V2I communication to obtain environmental data from the airport infrastructure and uses the goose flock algorithm for optimal path planning.

7. The method of the CAN bus and V2I goose flock optimization snow and ice removal platform obstacle avoidance system according to claim 6, characterized in that: The step 5 performs slip compensation and safety assessment, and the specific steps are as follows: Assume that the starting point of the snow and ice removal platform is (x s ,y s ), the end point is (x d ,y d ), the cost function of path planning f(x,y)=g(x,y)+h(x,y) g(x,y) is the actual cost from the starting point to the current point, and h(x,y) is the heuristic estimated cost from the current point to the end point; Furthermore, to optimize the obstacle avoidance operation, the snow and ice removal operation platform uses a weighted decision control function to select the path and adjust the speed. The optimization goal is to minimize the obstacle avoidance cost. Q d , Q v are the weight coefficients of distance and speed, v t is the expected vehicle speed, T is the control time; On a snow-covered runway, the friction between the tires of the work platform and the ground is reduced, and slippage may occur. The slip distance S slip Estimated by the following formula: The slip compensation formula is used to determine the possible slip distance of the platform during obstacle avoidance or emergency braking, and to adjust the control strategy accordingly. In an ice and snow environment, the friction coefficient between the tire and the ground is low, and slippage becomes a common phenomenon. In order to describe the slippage phenomenon more accurately, the Dugoff tire model can be used, and the slip rate is defined as: v0 is the linear speed of the wheel, v is the travel speed of the work platform; Lateral force F for the Dugoff tire model y The calculation formula is: On a snow-covered runway, the vehicle may skid or spin out during steering and obstacle avoidance. To prevent this, the vehicle stability control (VSC) is used to adjust the yaw rate. Target yaw angle The speed is calculated based on the desired steering angle δ: Actual yaw rate It can be obtained through the inertia model of the vehicle; The VSC system in the snow and ice removal platform adjusts the steering angle δ and the braking torque to make and Approaching, ensuring the stability of the vehicle during obstacle avoidance; When avoiding obstacles, the operating platform needs to dynamically adjust its speed according to the obstacle distance and environmental conditions. The optimization problem can be expressed as a control problem. The goal is to minimize the cost function J so that the platform can quickly avoid obstacles and maintain a stable operating speed. The optimization problem is as follows: Q δ , Q v , Q a are the weight coefficients of steering, speed and acceleration, v t is the expected vehicle speed, T is the control time, and by solving the optimization problem, the optimal speed v and acceleration a are determined to ensure safe obstacle avoidance and efficient operation of the working platform.

8. The method of the CAN bus and V2I goose flock optimization snow and ice removal platform obstacle avoidance system according to claim 7, characterized in that: When dealing with complex obstacles, the platform's obstacle avoidance strategy can adopt a nonlinear control algorithm - sliding mode control; the sliding mode surface is defined as: s=c1(x desired -x)+c2(v desired -v) Where c1 and c2 are control gains, The control law of the sliding mode controller is: u=-Ksgn(s) Among them, K is taken as the control gain, sgn(s) is the sign function, which is used to quickly converge to the sliding surface; The sliding mode controller can ensure the rapid obstacle avoidance and path tracking of the working platform in complex environments.

Images