Intelligent trolley obstacle avoidance system based on image processing

Abstract

The invention provides an intelligent trolley obstacle avoidance system based on image processing. The camera shooting assembly is arranged on the three-wheel trolley and is used for carrying out image shooting on the condition in front of the three-wheel trolley; the preprocessing module is used for preprocessing image information shot by the camera shooting assembly so as to identify a road area and a background area in an image; the recognition module is used for further analyzing and recognizing the curve of the road in front of the three-wheel trolley and the direction of the curve; and the control module is used for further controlling the driving of the three-wheel trolley based on the recognition condition of the recognition module. The curve condition of the road in front of the three-wheel trolley is recognized, the vertical distance between the front wheels of the trolley is adjusted through the intelligent control system, the stability and safety of the trolley running on the curve are optimized, the system effectively controls the trolley body inclination, the rollover risk is reduced, the outer side stability in the turning process is enhanced, and the safety of the trolley is improved. And the safety and the efficiency of the three-wheel trolley in the running process are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle obstacle avoidance systems, and in particular to a vehicle obstacle avoidance system based on image processing intelligence. Background Art

[0002] Smart three-wheeled cars are small mobile platforms that integrate autonomous driving, the Internet of Things, and artificial intelligence technologies. They are usually used in logistics distribution, security patrols, home services, education and scientific research, and other fields. With the continuous advancement of intelligent and automated technologies, these cars have realized functions such as autonomous navigation, real-time obstacle avoidance, and remote control through components such as sensors, GPS, control systems, and communication modules.

[0003] This experimental team has been browsing and researching a large amount of relevant records and materials on the relevant technologies of smart cars for a long time. At the same time, it relies on relevant resources and conducts a large number of relevant experiments. After a lot of searches, it is found that there are existing technologies such as CN110244718B, CN110182205B, CN114253273B, and CN113885532B disclosed in the prior art. For example, the prior art discloses an intelligent obstacle avoidance unmanned transport vehicle control system, and the system includes: a vehicle sensing module, which is used to collect sensing data of the unmanned transport vehicle during driving based on a preset ultrasonic sensing device, and upload the sensing data to an analysis module; an analysis module, which is used to receive the sensing data, analyze the sensing data, and transmit the analysis result to the control module; a control module, which is used to read the analysis result and generate a target control instruction, and at the same time, control the unmanned transport vehicle to drive normally based on the target control instruction. It can determine the position of obstacles on the driving path of the unmanned transport vehicle, accurately plan the driving path of the unmanned transport vehicle, improve the accuracy of the unmanned transport vehicle's automatic obstacle avoidance, and also improve the driving safety of the unmanned transport vehicle.

[0004] The present invention is made in order to solve the common problems in the art such as inaccurate recognition of road conditions during driving of three-wheeled vehicles. Summary of the invention

[0005] The purpose of the present invention is to propose a car obstacle avoidance system based on image processing intelligence in view of the shortcomings existing in the current field.

[0006] In order to overcome the shortcomings of the prior art, the present invention adopts the following technical solutions:

[0007] A vehicle obstacle avoidance system based on image processing intelligence, the vehicle obstacle avoidance system comprising a three-wheeled vehicle, a camera assembly arranged on the three-wheeled vehicle for capturing images of the situation in front of the three-wheeled vehicle, a preprocessing module that preprocesses the image information captured by the camera assembly to identify the road area and the background area in the image, a recognition module that further analyzes and identifies the curve of the road in front of the three-wheeled vehicle and the direction of the curve, and a control module that further controls the travel of the three-wheeled vehicle based on the recognition situation of the recognition module.

[0008] Furthermore, the three-wheeled vehicle includes a vehicle body, a rear wheel arranged at the bottom of the vehicle body and correspondingly located at the rear end of the vehicle body in the direction of travel, a steering controller arranged on the vehicle body for controlling the rotation direction of the rear wheel, a motor driver for driving the rear wheel to rotate, two front wheels arranged at the bottom of the vehicle body and correspondingly located at the front end of the vehicle body in the direction of travel, and two electric telescopic control levers respectively used to control the distance between the front wheels and the vehicle body.

[0009] Furthermore, two open grooves are respectively arranged on the bottom wall of the vehicle body, each of the open grooves comprises a groove opening located on the bottom wall of the vehicle and a corresponding groove cavity recessed upward from the groove opening, the groove cavity comprises cavity walls surrounded by five sides, and a cavity wall arranged opposite to the groove opening is the top cavity wall of the groove cavity, wherein the front wheels are universal wheels, and the front wheel correspondingly located on the left side of the vehicle body in the direction of travel is the left front wheel, and the front wheel correspondingly located on the right side of the vehicle body in the direction of travel is the right front wheel.

[0010] Further, the distance between each front wheel and the vehicle body is controlled by telescopic adjustment of the electric telescopic control lever, one of the two electric telescopic drive levers is used to control the distance between the left front wheel and the vehicle body, and the other of the two electric telescopic drive levers is used to control the distance between the right front wheel and the vehicle body, and the electric telescopic control lever used to control the distance between the left front wheel and the vehicle body is the left electric telescopic control lever, and the electric telescopic control lever used to control the distance between the right front wheel and the vehicle body is the right electric telescopic control lever;

[0011] The top of the left electric telescopic control rod is fixed to the top cavity wall of one of the opening slots, and the bottom is fixed to the left front wheel. The top of the right electric telescopic control rod is fixed to the top cavity wall of the other opening slot, and the bottom is fixed to the right front wheel.

[0012] Furthermore, the spacing of the right front wheel is kept unchanged, and the vertical distance between the axle of the left front wheel and the vehicle body is adjusted by extending the left electric telescopic control lever, thereby increasing the vertical spacing between the left front wheel and the vehicle body, causing the vehicle body to tilt to the right, increasing the grip of the right rear front, and providing more stability when the three-wheeled vehicle is driving on a right curve.

[0013] Furthermore, the spacing of the left front wheel is kept unchanged, and the vertical distance between the axle of the right front wheel and the vehicle body is adjusted by extending the right electric telescopic control lever, thereby increasing the vertical spacing between the right front wheel and the vehicle body, causing the vehicle body to tilt to the left, increasing the grip of the left front wheel, and providing more stability when the three-wheeled vehicle is driving on a left curve.

[0014] Furthermore, the control module is electrically connected to the two electric telescopic control rods to control the telescopic operation of the two electric telescopic control rods;

[0015] When the recognition module determines that the road ahead of the three-wheeled vehicle is a left curve, the control module controls the extension operation of the right electric telescopic control rod;

[0016] When the recognition module determines that the road ahead of the three-wheeled vehicle is a right curve, the control module controls the extension operation of the left electric telescopic control rod.

[0017] The beneficial effects achieved by the present invention are:

[0018] 1. The method of the present invention controls the inclination of the vehicle body by adjusting the vertical distance between the front wheels on both sides of the vehicle body and the vehicle body. The inclination of the vehicle body effectively resists the centrifugal force generated on the outer side during curve driving, and provides more lateral support by increasing the ground contact pressure of the inner tire, thereby increasing stability and reducing the risk of rollover, so as to enhance the stability of the three-wheeled vehicle under specific turning conditions, so that the three-wheeled vehicle can show better controllability and safety under various road turning requirements.

[0019] 2. The present invention can identify the curve condition of the road ahead of the three-wheeled vehicle, and adjust the vertical spacing of the front wheels of the vehicle through an intelligent control system to optimize the stability and safety of the vehicle driving on the curve, so that the system can not only accurately analyze the boundary movement in the fused image and realize real-time curve recognition, but also dynamically adjust the height configuration of the vehicle to adapt to different driving environments. By automatically adjusting the spacing between the front wheels and the vehicle body, the system effectively controls the tilt of the vehicle body, reduces the risk of rollover, enhances the outer stability during turning, and improves the safety and efficiency of the three-wheeled vehicle during driving.

[0020] 3. The method of the present invention controls the inclination of the vehicle body by adjusting the vertical distance between the front wheels on both sides of the vehicle body and the vehicle body. The inclination of the vehicle body effectively resists the centrifugal force generated on the outer side during curved driving, and provides more lateral support by increasing the ground contact pressure of the inner tires, thereby increasing stability and reducing the risk of rollover, so as to enhance the stability of the three-wheeled vehicle under specific turning conditions, so that the three-wheeled vehicle exhibits better controllability and safety under various road turning requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0022] Figure 1 It is a modular schematic diagram of the vehicle obstacle avoidance system based on image processing intelligence of the present invention.

[0023] Figure 2 It is a schematic diagram of the operation flow of the pre-processing module of the present invention.

[0024] Figure 3 It is a schematic diagram of the operation flow of the recognition module of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention is further described in detail in combination with its embodiments below; it should be pointed out that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present case. For those skilled in the art, after reviewing the following detailed description, other systems, methods and / or features of this embodiment will become apparent. And the terms describing the positional relationship in the accompanying drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to the specific circumstances.

[0026] Embodiment 1: Combining with the attached Figure 1 , Attachment Figure 2 and attached Figure 3 This embodiment constructs a car obstacle avoidance system based on image processing intelligence, the car obstacle avoidance system includes a three-wheeled car, a camera component arranged on the three-wheeled car for capturing images of the situation in front of the three-wheeled car, a preprocessing module for preprocessing the image information captured by the camera component to identify the road area and the background area in the image, a recognition module for further analyzing and identifying the curve of the road in front of the three-wheeled car and the direction of the curve, and a control module for further controlling the travel of the three-wheeled car based on the recognition situation of the recognition module.

[0027] The three-wheeled vehicle comprises a vehicle body, a rear wheel arranged at the bottom of the vehicle body and correspondingly located at the rear end of the vehicle body in the direction of travel, a steering controller arranged at the vehicle body for controlling the rotation direction of the rear wheel, a motor driver for driving the rear wheel to rotate, two front wheels arranged at the bottom of the vehicle body and correspondingly located at the front end of the vehicle body in the direction of travel, and two electric telescopic control rods respectively used to control the distance between the front wheels and the vehicle body.

[0028] Two opening grooves are respectively arranged on the bottom wall of the vehicle body, each opening groove comprises a notch located on the bottom wall of the vehicle and a corresponding groove cavity recessed upward from the notch, the groove cavity comprises five surrounding walls, and a cavity wall opposite to the notch is a top cavity wall of the groove cavity,

[0029] The front wheels are universal wheels of the prior art, and the front wheel located on the left side of the vehicle body in the direction of travel is the left front wheel, and the front wheel located on the right side of the vehicle body in the direction of travel is the right front wheel.

[0030] The distance between each front wheel and the vehicle body is controlled by telescopic adjustment of the electric telescopic control lever. One of the two electric telescopic driving levers is used to control the distance between the left front wheel and the vehicle body, and the other of the two electric telescopic driving levers is used to control the distance between the right front wheel and the vehicle body. The electric telescopic control lever used to control the distance between the left front wheel and the vehicle body is the left electric telescopic control lever, and the electric telescopic control lever used to control the distance between the right front wheel and the vehicle body is the right electric telescopic control lever.

[0031] Specifically, the top of the left electric telescopic control rod is fixed to the top cavity wall of one of the opening slots, and the bottom is fixed to the left front wheel. The top of the right electric telescopic control rod is fixed to the top cavity wall of the other opening slot, and the bottom is fixed to the right front wheel.

[0032] Keep the distance between the right front wheel unchanged, and adjust the vertical distance between the axle of the left front wheel and the vehicle body by extending the left electric telescopic control lever, thereby increasing the vertical distance between the left front wheel and the vehicle body, so that the vehicle body tilts to the right, increasing the grip of the right rear front, providing more stability when the three-wheeled vehicle is driving on a right curve, and reducing the possibility of rollover.

[0033] Keep the distance between the left front wheel unchanged, and adjust the vertical distance between the axle of the right front wheel and the vehicle body by extending the right electric telescopic control lever, thereby increasing the vertical distance between the right front wheel and the vehicle body, so that the vehicle body tilts to the left, increasing the grip of the left front wheel, providing more stability when the three-wheeled vehicle is driving on a left curve, and reducing the possibility of rollover.

[0034] The control module is electrically connected to the two electric telescopic control rods to control the telescopic operation of the two electric telescopic control rods. When the recognition module determines that the road ahead of the three-wheeled vehicle is a left curve, the control module controls the extension operation of the right electric telescopic control rod. When the recognition module determines that the road ahead of the three-wheeled vehicle is a right curve, the control module controls the extension operation of the left electric telescopic control rod.

[0035] The method of the present invention controls the inclination of the vehicle body by adjusting the vertical distance between the front wheels on both sides of the vehicle body and the vehicle body. The inclination of the vehicle body effectively resists the centrifugal force generated on the outer side during curved driving, and provides more lateral support by increasing the ground contact pressure of the inner tires, thereby increasing stability and reducing the risk of rollover, so as to enhance the stability of the three-wheeled vehicle under specific turning conditions, and enable the three-wheeled vehicle to exhibit better controllability and safety under various road turning requirements.

[0036] Embodiment 2: Combining with Figure 1 , Attachment Figure 2 and attached Figure 3 In addition to the contents of the above embodiments, the preprocessing module implements the following operation steps:

[0037] S101: receiving an image captured by a camera assembly,

[0038] S102: applying a Gaussian filter to remove image noise and using a histogram equalization method to enhance image contrast so as to make the visual difference between road and non-road areas more obvious, thereby obtaining a preprocessed image.

[0039] S103: Analyzing the texture features of the preprocessed image through a gray level co-occurrence matrix, the texture features include contrast, uniformity, and homogeneity indicators, distinguishing the road and non-road areas based on the differences in texture features between the road and non-road areas, and representing the identified road and non-road areas as a first binary image, wherein the pixels of the road area in the first binary image are marked as 1, and the pixels of the non-road area are marked as 0,

[0040] S104: Segment the image into road and non-road areas based on the grayscale thresholds of the road and non-road areas in the image, and represent the identified road and non-road areas as a second binary image, wherein the pixels of the road area in the second binary image are marked as 1, and the pixels of the non-road area are marked as 0.

[0041] S105: Perform fusion processing on the first binary image and the second binary image to obtain a fused image with fusion marks:

[0042] When the same position in both images is marked as a road, the same position is determined as a road in the fused image;

[0043] When the same position in the two images is the background, the same position is determined as the background in the fused image;

[0044] When the first binary image and the second binary image have different marks at the same position, the pixel at the same position is taken as the target pixel in the preprocessed image, and the grayscale co-occurrence confidence C of the target pixel in the preprocessed image is calculated. GLCM and grayscale threshold confidence CThre Compute and compare:

[0045] If C GLCM >C Thre , the same position in the fused image adopts the marking result determined by the first binary image,

[0046] If C GLCM ≤C Thre , the same position in the fused image adopts the marking result determined by the second binary image;

[0047] S106: Outputting the fused image after fusion processing;

[0048] The first binary image of S103 and the second binary image of S104 are implemented by the technicians in the field by using a wide range of existing relevant experience thresholds, functions, and methods provided by OpenCV and skimage, and will not be described in detail here.

[0049] The grayscale co-occurrence confidence C of the target pixel in the pre-processed image in step S105 is GLCM The calculation steps are as follows:

[0050] S201: Select a 7x7 square window centered on the target pixel of the preprocessed image.

[0051] S202: Obtain the contrast value Con, uniformity value Uni, and homogeneity value Hom within the 7x7 square window through gray level co-occurrence matrix analysis and calculation.

[0052] Among them, the contrast value Con, the uniformity value Uni, and the homogeneity value Hom are calculated and obtained by using the existing related functions in the OpenCV and skimage libraries of the existing Python language, which will not be described in detail here.

[0053] S203: Obtaining grayscale symbiosis confidence C GLCM :

[0054] C GLCM =w1×Con+w2×Uni+w3×Hom,

[0055] Among them, w1, w2 and w3 are gray-level co-occurrence weight factors, and w1+w2+w3=1;

[0056] The grayscale threshold confidence C of the target pixel in the preprocessed image in step S105 is Thre The calculation steps are as follows:

[0057] S301: Apply the Sobel operator and apply a 3x3 Sobel kernel to each pixel in the 7x7 square window to calculate the horizontal gradient value Gx and the vertical gradient value Gy of each pixel in the 7x7 square window.

[0058] S302: The gradient amplitude Gxy of the i-th pixel in the 7x7 square window is calculated as:

[0059]

[0060] Where Gx(i) is the horizontal gradient value of the i-th pixel in the 7x7 square window, Gy(i) is the vertical gradient value of the i-th pixel in the 7x7 square window, i = 1, 2, 3...49,

[0061] S303: Calculate the average value Ag of the gradient amplitude of all pixels in the 7x7 square window:

[0062]

[0063] S304: Move the 3x3 sub-window within the 7x7 window. In the 7x7 window, the 3x3 sub-window may start from the upper left corner of the window, move rightward and downward, and eventually cover the entire area of ​​the 7x7 window.

[0064] There are 25 3x3 sub-windows with different positions in the 7x7 window. The standard deviation SS of each 3x3 sub-window in the 7x7 square window is calculated:

[0065]

[0066] Among them, Gra(m) is the gray value of the mth pixel in the 3x3 sub-window, u is the average gray value of all pixels in the 3x3 sub-window,

[0067] S305: Calculate the average ALS of the standard deviations of all sub-windows:

[0068]

[0069] Where SS(j) is the standard deviation of the j-th sub-window within the 7x7 window,

[0070] S306: Obtaining threshold segmentation confidence C Thre :

[0071] C Thre =Gxy×w4+w5×ALS,

[0072] w4 and w5 are grayscale threshold weight factors, and w4+w5=1;

[0073] The present invention significantly improves the ability of the autonomous driving vehicle to distinguish the road ahead and the surrounding environment in complex environments by innovatively combining the edge detection of the Sobel operator and the texture analysis of the gray-level co-occurrence matrix. It not only realizes the efficient fusion of edge and texture information at the algorithm level, but also optimizes the data processing flow by fine-tuning the weights of local and global features, thereby enhancing the accuracy and robustness of image recognition.

[0074] Embodiment 3: Combining with Figure 1 , Attachment Figure 2 and attached Figure 3 In addition to the contents of the above embodiments, the identification module implements the following steps:

[0075] S401: Scan the fused image, wherein each pixel position in the fused image recognition is represented by a coordinate position (x, y), wherein x represents a horizontal coordinate value, and y represents a vertical coordinate value. The coordinate origin (0,0) of the fused image is at the lower left corner of the image, and the bottom row in the fused image is the first row. The position of the kth row in the fused image corresponds to the position of the k+1th row, which is the area ahead of the car.

[0076] S402: Determine the positions of the left and right boundaries of each row in the fused image. The left boundary L(k) of the k-th row and the right boundary L(k) of the k-th row in the fused image are determined as follows:

[0077] L(k)=min[x|M(x,y)=1],

[0078] R(k)=max[x|M(x,y)=1],

[0079] min[x|M(x, y)=1] represents the value x corresponding to the coordinate position of the first pixel marked as 1 from left to right in the kth row of the fused image.

[0080] max[x|M(x, y)=1] represents the value x corresponding to the coordinate position of the last pixel marked as 1 from left to right in the kth row of the fused image.

[0081] S403: Obtain the left boundary movement amount ΔL(k) in the fused image:

[0082] ΔL(k)=L(k+1)-L(k),

[0083] S404: Obtain the right boundary movement amount ΔR(k) in the fused image:

[0084] ΔR(k)=R(k+1)-R(k),

[0085] S405: Calculate the left boundary moving average LShift of a preset number of rows M in the fused image:

[0086]

[0087] S406: Calculate the right edge moving average RShift of a preset number of rows M in the fused image:

[0088]

[0089] S407: When LShift>left curve threshold Tleft, it is determined that the road ahead of the tricycle is a left curve.

[0090] If RShift>right curve threshold Tright exists, it is judged that the road ahead of the tricycle is a right curve.

[0091] Tleft and Tright are determined by evaluating a large amount of historical data using the neighborhood technology and statistical analysis to determine the initial thresholds, and further field tests are conducted to collect boundary movement data under left-curve and right-curve driving conditions. The initial thresholds are optimized and dynamically adjusted by support vector machines, decision trees and / or deep learning models to obtain Tleft for judging left curves and Tright for judging right curves.

[0092] In this embodiment, those skilled in the art can refer to the above value examples and make adjustments according to actual conditions. In short, the specific value ranges and trends of the above Tleft, Tright, W1, W2, W3, W4, and W5 will be determined by the designer or operator of the processing system according to the actual electromagnetic measurement processing requirements and system response, and will not be repeated here.

[0093] The present invention can identify the curve condition of the road ahead of the three-wheeled vehicle, and adjust the vertical spacing of the vehicle's front wheels through an intelligent control system to optimize the stability and safety of the vehicle driving on the curve, so that the system can not only accurately analyze the boundary movement in the fused image and realize real-time curve recognition, but also dynamically adjust the height configuration of the vehicle to adapt to different driving environments. By automatically adjusting the spacing between the front wheels and the vehicle body, the system effectively controls the tilt of the vehicle body, reduces the risk of rollover, enhances the outer side stability during turning, and improves the safety and efficiency of the three-wheeled vehicle during driving.

[0094] Although the present invention has been described above with reference to various embodiments, it should be understood that many changes and modifications may be made without departing from the scope of the present invention. That is, the methods, systems and devices discussed above are examples. Various configurations may appropriately omit, replace or add various processes or components. For example, in alternative configurations, the method may be performed in an order different from that described, and / or various components may be added, omitted and / or combined. Moreover, the features described with respect to certain configurations may be combined in various other configurations, such as different aspects and elements of the configuration may be combined in a similar manner. In addition, as technology develops, the elements therein may be updated, i.e., many elements are examples and do not limit the scope of the present disclosure or claims. And it should be understood that after reading the contents of the record of the present invention, the technician may make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. A car obstacle avoidance system based on image processing intelligence, characterized in that: The vehicle obstacle avoidance system includes a three-wheeled vehicle, a camera assembly arranged on the three-wheeled vehicle for capturing images of the situation in front of the three-wheeled vehicle, a preprocessing module that preprocesses the image information captured by the camera assembly to identify the road area and the background area in the image, a recognition module that further analyzes and identifies the curve of the road in front of the three-wheeled vehicle and the direction of the curve, and a control module that further controls the travel of the three-wheeled vehicle based on the recognition situation of the recognition module.

2. The vehicle obstacle avoidance system according to claim 1, characterized in that: The three-wheeled vehicle includes a vehicle body, a rear wheel arranged at the bottom of the vehicle body and located at the rear end of the vehicle body in the direction of travel, a steering controller arranged on the vehicle body for controlling the rotation direction of the rear wheel, a motor driver for driving the rear wheel to rotate, two front wheels arranged at the bottom of the vehicle body and located at the front end of the vehicle body in the direction of travel, and two electric telescopic control rods respectively used to control the distance between the front wheels and the vehicle body.

3. The vehicle obstacle avoidance system as claimed in claim 2, characterized in that: Two open grooves are respectively arranged on the bottom wall of the vehicle body, each of the open grooves comprises a groove opening located on the bottom wall of the vehicle and a corresponding groove cavity recessed upward from the groove opening, the groove cavity comprises cavity walls arranged on five sides, and a cavity wall arranged opposite to the groove opening is a top cavity wall of the groove cavity, wherein the front wheels are universal wheels, and the front wheel correspondingly located on the left side of the vehicle body in the direction of travel is the left front wheel, and the front wheel correspondingly located on the right side of the vehicle body in the direction of travel is the right front wheel.

4. The vehicle obstacle avoidance system as claimed in claim 3, characterized in that: The distance between each front wheel and the vehicle body is controlled by telescopic adjustment of the electric telescopic control lever, one of the two electric telescopic drive levers is used to control the distance between the left front wheel and the vehicle body, and the other of the two electric telescopic drive levers is used to control the distance between the right front wheel and the vehicle body, and the electric telescopic control lever used to control the distance between the left front wheel and the vehicle body is the left electric telescopic control lever, and the electric telescopic control lever used to control the distance between the right front wheel and the vehicle body is the right electric telescopic control lever; The top of the left electric telescopic control rod is fixed to the top cavity wall of one of the opening slots, and the bottom is fixed to the left front wheel. The top of the right electric telescopic control rod is fixed to the top cavity wall of the other opening slot, and the bottom is fixed to the right front wheel.

5. The vehicle obstacle avoidance system as claimed in claim 4, characterized in that: Keeping the spacing of the right front wheel unchanged, the vertical distance between the axle of the left front wheel and the vehicle body is adjusted by extending the left electric telescopic control lever, thereby increasing the vertical spacing between the left front wheel and the vehicle body, causing the vehicle body to tilt to the right, increasing the grip of the right rear front, and providing more stability when the three-wheeled vehicle is driving on a right curve.

6. The vehicle obstacle avoidance system according to claim 5, characterized in that: Keeping the distance between the left front wheel unchanged, the vertical distance between the axle of the right front wheel and the vehicle body is adjusted by extending the right electric telescopic control lever, thereby increasing the vertical distance between the right front wheel and the vehicle body, causing the vehicle body to tilt to the left, increasing the grip of the left front wheel, and providing more stability when the three-wheeled vehicle is driving on a left curve.

7. The vehicle obstacle avoidance system according to claim 6, characterized in that: The control module is electrically connected to the two electric telescopic control rods to control the telescopic operation of the two electric telescopic control rods; When the recognition module determines that the road ahead of the three-wheeled vehicle is a left curve, the control module controls the extension operation of the right electric telescopic control rod; When the recognition module determines that the road ahead of the three-wheeled vehicle is a right curve, the control module controls the extension operation of the left electric telescopic control rod.

Images